Search

In image processing and computer vision, image segmentation plays a crucial role. It finds a place in many image applications. Texture and colour features and its combination are among the main features used in image segmentation. This paper presents the literature review for colour-based segmentation techniques and texture-based segmentation techniques. The main objective for this paper is to provide the recent trends of both the color and texture segmentation technique in image segmentation as well as presenting the most popular evaluation measurements used for image segmentation. At the end of this paper, the conclusion for future work and its direction is presented. [ABSTRACT FROM AUTHOR]

Various object detection models are presented in this paper. Definition of object is well defined in order to understand object detection models. Now-a-days the object detection which is computer vision and image processing related technology is widely used. Applications of object detections are infinite as it can be used all over like objects tracking, surveillance of videos, face recognition, detection of anomaly, counting of people, and the records still continue to many more. This paper compares various object detection algorithms the basic splitting is based on machine learning based and deep learning based. Fundamental objective of the paper focuseson Single stage object detectors (SSD) like You Only Look Once (YOLO) and Two stage object detectors as RCNN, Fast RCNN, etc. This paper's main goal is to highlight such object detection models and their use in various fields. [ABSTRACT FROM AUTHOR]

In recent years, multi-element detection and tracking is an essential application of computer vision, including civilian or military surveillance systems. However, the precision and system's capacity to track cars is the key challenges these systems experience in their work. the speed of system interaction, and the reduction of noise associated with the video sequences captured by the system. Therefore, vehicle detection is an important stage in vehicle tracking. The approach to finding moving cars in a video is known as tracking. Vehicle tracking has many applications, including robot vision, traffic control, video surveillance, and simulation. Over the years, many scientists have sought to design useful and efficient algorithms. In this paper, a Kalman filter (KF) was developed to identify and track moving vehicles. The topic of vehicle monitoring and tracking with a fixed camera is addressed in this work. This includes a three-stage work in the first stage, the acquired video is converted to frames and the video is converted from RGB to gray in the first step of preprocessing, then the salt and pepper noise is eliminated using an average filter technology. Background subtraction is performed in the next phase of moving vehicle detection and extraction due to its ability to handle complex backgrounds and appearance changes due to lighting and size, and vehicle detection. The exposed front part is cleaned by applying the shaping process. The detected object is marked as a vehicle with a bounding box. The vehicles are then tracked using a Kalman filter in the next stage. This paper aims to identify and track vehicles in video frames sequence. An average filter was used to remove 70-80 percent of the noise during the noise reduction step. Since the noise, presumably salt and pepper, is less complex than that of the Wiener filter, an intermediate filter was used in place of the Wiener filter. KF was used as a discretionary filter during the tracing step. We conclude that the accuracy of the composite detection achieved using the Kalman filter approach is about 94 percent. It is a great technology for tracking the movement of moving vehicles and has a lot of potential in a traffic control system. The complete system was developed and tested using MATLAB. [ABSTRACT FROM AUTHOR]

The purpose of the research is to detect defects in textile industry using computer vision and fuzzy logic techniques. The paper presents various practices used for edge detection, including a fuzzy logic applied. By testing, a fuzzy logic method has been chosen to obtain a respectable result. The algorithm that is observed in the paper is improved by dividing the processing into two phases: a fast one, which allows us to assume that there is a defect, and a searching one, which allows a defect to be highlighted in color. The advanced algorithm was tested on several types of fabrics. An average background arrangement is obtained for them. That allows separating fabric texture and color from potential defects. The tests were also performed on fabrics (cloths) with different brightness, number and type of defects. We obtained the percentage ratios of the defect detection quality and so we suggested the ways to develop the system. [ABSTRACT FROM AUTHOR]

Face Emotion Detection Music Player is an innovative idea that combines computer vision and machine learning techniques to create a unique and interactive music player. This Research Paper studies the uses of Convolutional Neural Networks (CNN) to detect and analyze facial emotions in real-time and dynamically create playlists based on detected emotions. The music player is designed to record facial expressions using a webcam or other suitable camera. To reliably identify facial expressions including happiness, sorrow, rage, surprise, and more, a CNN model is trained on a sizable collection of face images. The trained model demonstrated an astounding 74.46% accuracy in identifying emotions when combined with music player software running on a PC or other suitable device. The CNN model analyses the photos to determine the user's emotional state as they interact with the music player in real-time, as captured by the camera. Based on the detected emotions, the player automatically selects and plays songs from a predefined music collection that matches the user's emotional state. For example, if the user looks happy, the player can play happy and energetic songs, while if the user looks angry, it can play more calming and soothing music. Face Detection Music Player offers a personalized and dynamic music listening experience as the music selection is constantly updated according to the user's emotions. This research paper illustrates how computer vision and machine learning techniques may be used to produce interactive programs that can instantly adjust to the moods and preferences of their users. It has uses in user experience research, entertainment, and mental health, among others. [ABSTRACT FROM AUTHOR]

This state-of-the-art review paper provides a comprehensive overview of meta-learning techniques for learning to learn in machine learning. Meta-learning called "learning to learn," is an approach that enables models to learn from new tasks learning quickly and efficiently, based on prior knowledge and experience. The paper discusses various meta-learning techniques, such as model-based meta-learning, metric-based meta-learning, optimization-based meta-learning, and memory-based meta-learning. The review also covers the applications of meta-learning in different domains, including natural language processing, computer vision, and reinforcement learning. Additionally, the paper discusses the benchmark datasets, challenges along with the future directions of meta-learning research, highlighting the need for developing more efficient and scalable meta-learning algorithms. Moreover, the proposed Meta-Learn framework incorporates a hierarchical structure to facilitate knowledge transfer across multiple levels of abstraction, and it also includes a memory component that enables the system to store and reuse previous experiences. Overall, this review aims to provide a comprehensive overview of Meta-Learning techniques for learning to learn in Machine Learning and proposes a novel Meta-Learn framework that could potentially enhance the performance and scalability of Meta-Learning algorithms. [ABSTRACT FROM AUTHOR]

The paper proposes a novel approach for recognizing and classifying gym exercises using human pose detection with Mediapipe and LSTM, followed by matching the accuracy of the exercises using the Hungarian algorithm and cosine similarity. The proposed approach involves the use of a combination of cutting-edge technologies, including computer vision and deep learning, to recognize and classify a range of gym exercises accurately and efficiently. This study presents several advantages of this approach, including the ability to leverage temporal information, robustness to variations in lighting, camera angle, and occlusions, and the ability to handle a wide variety of gym exercises. Experimental results demonstrate that the proposed approach achieves high accuracy and outperforms existing methods for gym exercise recognition and classification. The paper also compares the proposed approach with existing techniques, highlighting its strengths and cost-effectiveness. It concludes by outlining the methodology, including dataset collection and pre-processing, landmark extraction, LSTM model training, exercise classification, and similarity analysis. Finally, the paper discusses potential future research areas in this field. [ABSTRACT FROM AUTHOR]

With recent advances in computer vision, benefits and challenges related to the adoption of Information and Communications Technology ICT tools in the higher education systems, a retrieval process based on teachers' perspective have become a key component in achieving high efficiency survey queries. In this paper, it is proposed and developed software called, "Smart Survey System", supporting quick access to identify the benefits and challenges related to the adoption of ICT tools in the higher education systems. The proposed system applies data analytics as a backbone, which uses PHP-WAMP server and MySQL database structure. This paper dwells on the analysis of a set of survey data for around 350 teachers. This paper also incorporates recommendations, limitations and future research directions. More efficiently search activities can be conducted through this proposed database system. [ABSTRACT FROM AUTHOR]

Chest X-ray (CXR) imaging is often used to diagnose pneumonia caused by COVID-19. The advantage of CXR is that it is cheap, fast, widespread, and uses less radiation. Studies of distinguishing object regions from one to another or image segmentation have been used in the medical field for further image analysis. This paper has proposed a method for segmenting lungregions using region-based active contour to measure the area segmented in CXR images. Active contour segmentation was performed using a computer vision image segmented in MATLAB. We assessed the CXR image in Andalas University Hospital and composed the data consisting of lung opacity (pneumonia) and regular. The result shows that, in both the left and right of the chest, the area in the pixel of the lung affected by COVID-19 is smaller than in the normal lung. In conclusion, this technique will benefit biomedical research investigating the regional lung. [ABSTRACT FROM AUTHOR]

Pose estimation is a fascinating aspect of pattern recognition that is used in a variety of industries, such as technology, healthcare, gaming, etc. The goal of human posture estimation is to foretell the positions of joints and body components in still photos and moving pictures. Given the wide range of uses for such a system, it constitutes one of the most intriguing domains of computer vision research and has had significant growth. The compact convolutional neural networks architecture for human posture estimation proposed in this study, called BlazePose, is intended towards mobile device legitimate prediction. During analysis, the network operates from over 30 fps on something like a Pixel 2 mobile, providing 33 body keypoints for such a specific individual. As a result, it is particularly well-suited for real-time applications like as fitness tracking and action recognition comprehension. This paper makes two major contributions: a novel body posture tracking approach and a lightweight body pose estimation computational model that evaluates parameters utilizing heatmaps and regression. The suggested method has improved estimate accuracy, which is useful when it is used for robotics, augmented reality, sports and fitness, action recognition, motion analysis, and human-computer interface. [ABSTRACT FROM AUTHOR]

Atopic dermatitis is a chronic disease that makes skin red and itchy. The atopic dermatitis extremity is primarily evaluated on visual inspection by medical practitioners. There is no standard and automated method for evaluating atopic dermatitis severity. This paper proposes atopic dermatitis detection using computer vision and machine learning-based techniques. The proposed method combines feature extraction using GLCM-based Haralick features and Light Gradient Boosting Machine Classifier. This paper represents the effectiveness of using a computer vision-based approach for atopic dermatitis detection with a medium-scale dataset and its potential for dermatitis classification with 83% accuracy. [ABSTRACT FROM AUTHOR]

A weapon is an item that threatens a person's life. Therefore, the use of weapons needs very close supervision. These supervisory activities could be carried out automatically using deep learning. Deep learning enables a computer to have a vision like humans. One of the deep learning methods is Single Shot Multibox Detector (SSD). SSD is one object detection method that has impressive accuracy and speed [1]. This paper used SSD MobileNet V2 and SSD ResNet 50 methods. The difference between SSD MobileNet V2 and SSD ResNet 50 lies in the backbone used. SSD MobileNet V2 used MobileNet V2 as a backbone, while SSD ResNet 50 used Residual Network 50 (ResNet 50) as a backbone. Weapons that could be detected in this paper are handguns and knives. The most excellent accuracy that is achieved by SSD MobileNet V2 is 79% and SSD ResNet 50 is 62%. [ABSTRACT FROM AUTHOR]

Federated Learning (FL) has emerged as a promising approach for distributed machine learning. FL enables multiple parties to collaboratively train a model without sharing their local data, which addresses privacy concerns associated with traditional centralized machine learning approaches. However, FL faces several challenges, such as the non-IID nature of data, hindering diversity and performance. This paper provides an overview of FL, including its challenges and applications in the healthcare, finance industry, data security and a number of IoT applications. We discuss the state-of-the-art in FL research and explore its potential for future development. FL has been applied in various domains, such as natural language processing, computer vision, healthcare and finance. In this paper, we focus on the application of FL in healthcare, finance, IoT, insurance industry, discussing its potential impact on data security and privacy. We also highlight the challenges and opportunities associated with FL in these topics. The paper also covers methods proposed to address the challenges in FL, including federated averaging, transfer learning, differential privacy, and secure multi-party computation. Overall, this paper provides an insightful overview of FL, its challenges and applications, and its potential for future development. [ABSTRACT FROM AUTHOR]

In a practical and real-world, colour matching is achieved effectively only by the colour constancy. This colour matching plays a very important role in each and every fields of our daily uses. Colour constancy refers to the study of how every humans will perceive the colours. The goal of colour correction is to obtain the colour of objects correctly regardless of the differences in light sources, illumination, etc. In this paper, we will learn to achieve the colour correction of the objects or materials used in our day to day life with the help pf the open computer vision and python programming. This respective technique can be effectively used for photographers, and also the computer vision practitioners. [ABSTRACT FROM AUTHOR]

In this study, we take a different approach to feature extraction by focusing on the diagonal rather than the horizontal in order to statistically and structurally utilise handwritten characters. Substances and Techniques: This paper employs the Computer Vision Laboratory's (CVL) publicly available database for its dataset (NTHU). Using a G intensity of 0.8 and alpha and beta quality values of 0.05., 0.2, and a 95% confidence interval, we determined that a sample size of 280 (group 1=140, group 2=140) handwritten characters would provide adequate statistical power. Novel sample number (N=10) diagonal feature extraction and sample number (N=10) horizontal feature extraction are used to classify statistical and structural aspects of handwritten characters, resulting in greater precision. The outcomes show that the accuracy of the diagonal feature extraction classifier is 95.883, while that of the horizontal feature extraction classifier is 92.736. This study has a significance level of p=0.0213. In conclusion, statistical and structural features of handwritten characters make diagonal feature extraction more accurate than horizontal feature extraction. [ABSTRACT FROM AUTHOR]

One of the areas of computer vision is superpixel segmentation, and the widespread use of superpixels in a wide range of practical applications shows that it has unique properties. A superpixel is created by combining pixels with similar content, which significant reduce the computational complexity of the algorithm at the next stages of image processing. After the superpixel is built, it is possible to solve problems such as classification, reduction of image dimensions, construction of spectral combination, selection of a certain channel, noise reduction, and change detection based on the application of superpixel to spectral images. This paper presents an analysis of SLIC, SEEDS, LSC, DFIC, AHP, DRW, WSS, BACA, and superpixel segmentation approaches on remote sensing images. The analysis of approaches was considered according to the characteristics of the color model, scale, regularity, connection, smoothness, texture, and boundary strength. Approaches were evaluated using the criteria of Undersegmentation error, Achievable segmentation accuracy, and Boundary Recall. The study revealed that superpixel segmentation techniques that employ all of the spectral image channels have not received enough attention; instead, they are typically applied using PCA to shrink the size or convert them to color models. Additionally, it is important to investigate the issue of applying deep learning techniques to the implementation of superpixel segmentation in remotely sensing spectral images. [ABSTRACT FROM AUTHOR]

OpenCV (Open Source Computer Vision) library can be used for face, nose and mouth detection. And the library was ready to use with the Haar-Cascade Classifier method. In this paper, the library was used to predict the incorrect use of facemask. Furthermore, the system was equipped with the knowledge that if the mouth and nose or one of them was detected, then the face had not used a mask correctly. The system was supported by an image capture device such as a camcorder, a processing device was used a single board computer, such as a Raspberry Pi and the output device was a display. And the result that the system was able to make a decision whether the face was wearing a mask correctly or not. If you don't use the mask correctly, a label will appear around the face in the form of a red angular line. The detection success rate was 88.4% using the detector parameters, namely: scale factor = 1.1 for all face, nose and mouth object libraries. [ABSTRACT FROM AUTHOR]

Technologies of Industry 4.0 are revolutionizing the way companies manufacture their products. Modern manufacturing systems are connected with the application of advanced sensors, increased automatization, embedded software, and robotics that collect and analyze data and allow for better decision-making. These trends are also reflected in recent innovations in the field of electrical discharge machining (EDM). One can state that recent progress in EDM is connected with the following areas: increase of automatization and robotization of the process, real-time data analysis, adaptive control and application of artificial intelligence, use of advanced sensors (especially machine vision systems), improvement of communication between machine tool and operator (i.e., voice-operated assistant technology) and application of additive manufacturing to shaping electrodes. All listed above and detailed innovations discussed in the paper cause EDM to become faster, more reliable, and more efficient technology, and the amount of unattended machining hours increases. [ABSTRACT FROM AUTHOR]

In recent years, improvements in natural language processing and computer vision have come together to provide automatic image caption generation. Image captioning is the process of creating a description for an image. Captioning an image needs the recognition of significant items, their properties, and their connections within the image. Additionally, it must create phrases that are syntactically and semantically accurate. Deep learning approaches can address the complexities and difficulties associated with image captions. This paper describes a joint model which is capable of automatically captioning images using EfficientNet-B0 and a transformer with multi-head attention. The model is an aggregation of an EfficientNet & Transformer single encoder and decoder. The encoder utilizes EfficientNet-B0, a convolutional neural network-based algorithm that generates a detailed input image, represented by embedding them into a fixed-length vector. The decoder employs a transformer, and a multi-head attention mechanism to selectively concentrate attention on certain regions of images to predict the sentence. The proposed model was trained using a large dataset Flickr8k to optimize BLEU N-Gram (N=1,2,3,4), METEOR score, and CIDEr, to assess the probability of the target description phrase given in the training images. Our studies show that the proposed model can produce captions for images automatically. [ABSTRACT FROM AUTHOR]

The agricultural industry is the most prominent sector for the economic growth of the country. Cotton is an important crop that brings out major returns to the economy. In the current era, smart agriculture technology is incorporated which includes various modern techniques such as sensors, artificial intelligence, and computer vision to digitalize the whole process. This digitalization through modern technology enhances the fast and intelligent productivity of crops. In this paper convolutional neuralnetwork-based methods have been used to predict the maturity of the cotton balls using image features of mature and immature images. Real-time maturity detection is a challenging task for cotton fiber because of the many constraints in natural light conditionsand environmental effects. The proposed scheme uses annotation to classify the cotton balls. The classification is labeled as matureand immature images then the annotated images are used for training the deep learning models Resnet 50 and VGG 16. The averageaccuracy achieved from these methods is 92.47% for Resnet 50 and 96.58% for VGG16. The loss of the model is 21.05% for Resnet50 and 14.91% for VGG16. [ABSTRACT FROM AUTHOR]

The paper discusses the prerequisites for the creation, technical solutions and implementation of an automated control system for the assembly of a small spacecraft. Both the hardware and software implementation of the system that provides control and logging of the assembly process of individual units at various workplaces are analyzed. The article presents solutions to reduce the requirements for equipment used to control the assembly technology, in particular, to use cameras with a lower resolution, through the use of special algorithms for the formation and processing of technological marks. A tool is presented that allows you to control the tightening torques of threaded connections and limit the tightening torque according to a given algorithm with wireless control. The developed system provides the functions of not only control, but also logging of the technological process, which can be useful in the future when creating a digital twin of the product. [ABSTRACT FROM AUTHOR]

Nowadays in India, due to the increase in the number of accidents vehicles are being automated using a variety of Computer vision algorithms. This paper focuses on the detection of tail signals of cars under different illumination circumstances. This system is implemented using FAST and SIFT algorithm which helps to extract features from the images. The obtained features were optimized by using K-Means Clustering Algorithm. This huge feature vector is converted into 8 clusters. These optimized feature vectors were trained on five different classifiers as Decision Tree, SVM(RBF), Random Forest, and Voting Classifier. The trained data set used in this algorithm contains around 9052 images. The obtained accuracy results of different classifiers are as follows, Decision tress has 76.36%, SVM(RBF) has 77.91%, Random Forest has 87.52%, KNN has 89.72%, the Voting classifier has 86.52%. It is observed that KNN gives the highest accuracy among the five used classifiers. This has, to the best of the authors' knowledge, not been presented in literature before. [ABSTRACT FROM AUTHOR]

Currently, many companies are competing to produce robots that can help humans. Robots can work with high accuracy, efficiency, and low power in the production of goods. Automated Guided Vehicle is one form of robot that is useful in industry. Automated Cars are another form of functional industrial robot that transports with programmable paths and directions automatically. In this paper, we will discuss the navigation system in Automatic Cars based on previously mapped paths. The robot wheel serves to adjust the direction and position of the robot. The automatic movement can be carried out using computer vision. Warehouses that are not neatly arranged cause the navigation system to be less than optimal. The types of controllers used include classical controllers, fuzzy logic, artificial neural networks, and H∞. The purpose of this research is to produce a precise car front view monitoring system using image processing with high enough quality for automatic car navigation. The benefit for science is the development of automatic cars, which so far have not been widely carried out in Indonesia. The results of this study can be useful for the development of methods to build an automatic car system. The benefit for the electronics industry is the availability of control equipment designs to be able to control cars automatically. The effect on society is in the form of future vehicles that can move automatically without a driver. Based on the computer vision system test for Raspberry Pi-based car navigation, it can be ascertained that the car works well and has a small physique, so it looks neat and concise. The movement of the car from the first coordinate point to the next coordinate point is very precise and precise. By installing the L298N motor driver module, it is easier to set the program in python, so that the results sent to the DC motor can be used directly. Using a DC motor that has an excellent performance in terms of torque and speed. [ABSTRACT FROM AUTHOR]

This paper describes the detection of unusual event that occurs in ATM machine. ATM is a simple source for people to get their money in a faster way. Also, there are many thefts and crime happening in ATM. The COVID-19 outbreak is the toughest challenge we have faced. The main precautions to avoid the transmission of virus are to wear a mask and maintaining the social distance between us. Here we introduce a system to solve such problems by using a computer vision to keep track of activity and detect violations (Not Wearing Mask) and alerts a mail with violation photo attached to concerned authority. In addition to this object detection and weapon detection is also appended. [ABSTRACT FROM AUTHOR]

The deaths caused by road accidents are one of India's most pressing issues. The inattentiveness of the driver is responsible for almost 80% of all collisions. Mobile phone use, conversing with passengers, reaching behind the wheel to grab something, and drinking while driving are just a few of the factors that can cause a driver to become distracted. This project aims to create a reliable and effective system for detecting and classifying distracted drivers. The efficacy of CNNs in the field of computer vision was the inspiration for this paper, which proposes a paradigm based on Convolutional Neural Network which not only senses but also recognizes the driver who is distracted. For this purpose it is using a publicly available dataset from the Kaggle website as an input for this model. There are several different forms of distractions, but this study focuses on the manual distraction, which is focused on the driver's stance. The goal of this work is to keep an eye on the driver's actions and seek for diversion signs. Distractions are divided into two groups in the model: safe driving and unsafe or distracted driving. For this purpose, various architectures of CNN can be used. This work, however, employs sequential architecture and achieved the highest observed accuracy of 99% with a total of 9.5M trainable parameters. The primary goal of this research is to classify a test image into two states of the driver that have been considered. [ABSTRACT FROM AUTHOR]

In this paper, we are trying to make Surveillance Car using real time computer vision. Our model will focus on intelligence gathering and react according to prevention of crime or the investigation of crime with the help of feed which we are getting from image and the feed is then processed with the help of image processing. In this paper, we proposed a model to save time as we have a lack of time to be involved in society. The surveillance car is used as a robotic car, it can control the car through our web page from anywhere anytime. It can be used in parking if we are not able to come and do parking work on our own then we can control it by Web page. In this paper, we are going to make a camera surveillance car using a real time computer vision concept. We will capture images using a camera present on the car and send these images to our mobile phone using Web Socket through Wi-Fi connection. We will also control the car with the web page. We build a robot using a pre-built custom robot chassis. For movement DC geared motors are used along with small wheels to get the required torque. To generate the power to the motor driver module and ESP32-CAM we have used the battery for its objectives. [ABSTRACT FROM AUTHOR]

Cancer is a disease with a high mortality rate. Cancer is developed when the cell does not undergo a cell division process, the presence of uncontrolled cell growth turns to tumor cells and spread to various other organ systems. Early detection of such cancer improves the chances of favourable outcomes. Despite the fact that the early prognosis of cancer has made considerable improvement. Lung cancer is the second leading cancer worldwide. The identification of lung cancer and lung nodule segmentation is a crucial preliminary step. The Deep Learning network works best for medical image automation. Deep learning models and computer vision applications are expanding rapidly in the modern era. This paper includes Computed Tomography (CT) images to segment challenging lung nodules. The modified U Net introduced in this paper performs the segmentation of lung nodules. The dataset is obtained from the Radiology Department at Chennai Rajiv Gandhi General Government Hospital. The ResNodNet outproduces the segmented nodule, the model combines Respath and U Net to facilitate the categorization of multi-featured data that has been proposed as ResNodNet. The classification results produced by the suggested method are accurate at 98.6%. [ABSTRACT FROM AUTHOR]

The emergence of edge computing allows the processing of data at the source of data. By combining edge computing with the cloud and the Internet of Things (IoT), data collection, processing, and storage can be managed effectively. This combined architecture has given hope for an automated surveillance system. This paper presents an edge–cloud – IoT-based Surveillance System that uses computer vision algorithms in the edge devices to process the video feed captured by cameras and store the required video backup in the cloud through IoT. This paper discusses the protocols used, task scheduling methods, metrics used to analyze the quality of service, and security and privacy issues. The dataset is collected from the SRMIST, Kattankulathur campus. The architecture is tested on the students' activities and is found efficient. [ABSTRACT FROM AUTHOR]

State-of-the-art solutions in the areas of language modelling, generating text, speech recognition, generating image descriptions or video tagging, have been using Recurrent Neural Networks as the foundation for their approaches. Understanding the underlying concepts is therefore of tremendous importance if we want to investigate frontier methods and develop new approaches for building smart digital solutions. This paper proposes a smart city control system architecture based on deep convolutional neural networks. The control system has a multilayer architecture that combines loosely coupled intelligent components. As the main layer, a solution based on deep learning technology is applied, which allows solving several tasks simultaneously: segmentation, detection and classification of images received from surveillance cameras of the smart city system. The data obtained at the output of this layer is used for further analysis and decision-making in the smart city system. The proposed architecture has a high degree of modularity and allows the replacement of individual elements in a loosely coupled architecture. In this paper, deep learning and computer vision technologies are also considered, on the basis of which the image processing layer from video cameras is implemented. A masked recurrent neural network is used for this task. [ABSTRACT FROM AUTHOR]

From the past few years, The navigation systems are advancing with every possible technology. Researchers are do-ing there best to improve the navigation system and guidance systems. These advancement in the navigation systems with some modification can be helpful to the visually impaired people to navigate in there day to day life. This paper gives a review of the better technologies present in the society to help the visually impaired. This paper covers the use of different technologies like AI(artificial intelligence),Deep learning, IOT etc in creating useful gadgets for the visually impaired people. Traditional approaches such as: cane or guide dog, And there are gadgets such as infrared based cane or ultrasonic blind stick with are limited by the distance of identifying the objects. And there are some gadgets which are microcontroller based and microprocessor based. Some of the proposed systems uses the computer vision for object detection, character recognition, face detection etc. There are wide range of gadgets involving various technologies to help the visually impaired. The review covers various technologies used in different proposed systems for the visually impaired people and help to develop a better navigating device for visually impaired. [ABSTRACT FROM AUTHOR]

Object tracking is a vital component of various applications. It plays a significant role in various applications such as machine vision, object/face recognition, and classification. This paper presents the comprehensive study of various object tracking procedures, which are usually carried out in diverse conservational circumstances. Object tracking is the most attractive field of investigation also a game-changer for finding the feature intensities. In this paper, tracking on an object is considered on Colour, shapes, texture, object of interest in single or multiple object detection, motion direction and calculated in multiple frames. Due to the development of machine learning schemes and various other related tools, the evolution of deep learning methods is widely expected. Through investigational assessment of tracking outcomes in the standards in whole and by the assembly, the researcher demonstrates the success of deep-networks for tracking activity in distinct compartments and associate the benefits of these networks and their healthiness under distinct tracking circumstances. Furthermore, they examine the confines of modern approaches and entice some valuable decisions to examine novel directions for multi-object tracking. [ABSTRACT FROM AUTHOR]

This paper proposes a method for a grocery assistance system with object detection and recognition for people with visual impairment. Several solutions have been presented till date to improve the quality of life of visually impaired and blind persons. But, purchasing items in a grocery store without the assistance of others is still difficult for them. Some Computer Vision based systems gave an inconsistent performance in real-world environments because of problems such as motion blur. This paper proposes a method wherein, the system will recognize an object and then convert its real-time object to an audio output. This will help them recognize a grocery item at a shop or elsewhere. The system uses SIFT for feature extraction and PCA for dimensionality reduction. The system mainly identifies and classifies 3 products in a grocery store namely beverages, dairy products and chocos. Five different classifiers viz. SVM (OVO), SVM (OVR), KNN, Decision Tree and Random Forest were used to classify the products and overall, Random Forest classifier gave the best accuracy amongst others. The proposed system gives better results i.e., an accuracy of about 87% when it comes to object recognition and classification. [ABSTRACT FROM AUTHOR]

Cancer is one of the most dangerous diseases which is the cause of death of around half a million people every year. Research scientists and doctors are still finding methods to avoid these casualties. Brain tumor and Liver lesions are among the most fatal cancers and early detection of these diseases can help in reducing large human loss every year. Various methods are used for early detection of brain tumor and liver lesion from medical images using computer vision and image processing. This paper provides a detailed analysis on various methods used for detection and segmentation of brain tumor and liver lesion. Due to the large availability of image data and complex computing resources which can process them has made a deep learning approach popular for medical image analysis. Deep learning architectures like Convolutional Neural Network (CNN), Fully Convolutional Network, Auto Encoders and Generative Adversarial Network (GAN) has transformed the research in brain tumor and liver lesion analysis. This paper discusses these deep learning architectures in brief along with the various variations in these architectures for medical image analysis. The datasets used for brain tumor and liver lesion analysis are also listed and compared in the paper. The advantages, limitation and research challenges of using deep learning methods is discussed in detail along with the possible solutions for overcoming these limitations. This paper will explore possible research gaps in deep learning in terms of analyzing the medical image with different modalities, resource computation, ensemble of CNN and optimization of the deep learning model for classification and prediction of medical data. [ABSTRACT FROM AUTHOR]

Pothole detection is a challenging task as it involves inhomogeneity in intensity, complex topologies, contrast less, and noise rich background. Still, it's a very important task concerning the maintenance of roads. Potholes are being detected using computer vision which generally involves analysis of a two-dimensional image of the road or modeling of the road surface. Provided both these methods are independently used. The accuracy of this method of pothole detection is far from the top point. These bring the usage of digital image processing which develops the detection of potholes with at most accuracy. Digital Image processing provides strong receptivity, usage of huge actions, and broad benefits. In this paper, we propose a system that supports digital image processing techniques of high efficiency to result in consistent and accurate detection of potholes. This project studies an intelligent digital industrial pothole detection mechanism to increase human safety, detection capability and decrease the factor of risk. Firstly, the sources of images from the road are pre-processed to remove noise and other irrelevant features. Then a training model was developed to train the system to classify between path holes and normal cracks using convolution neural networks and MATLAB. Also, an IoT device is used in this system which updates the detected potholes on the road to the respective web server along with the location coordinates, as a part to notify a complaint to check. This system works on providing a better pothole detection technique and also updating the same to the concerned. [ABSTRACT FROM AUTHOR]

Applications of deep learning to solve complex problems related to computer vision and human level control system has been successfully implemented in real life. On the other hand, deep leaning based systems can also cause harm to the privacy and security of the personnel or a system. One of the threats that is powered by deep learning and AI is deep fake technique which is used to create fake images, video and audios that are not identified by human visual or audio system. This makes it difficult for human to distinguish between the original data and the deep fake data. This paper aims at discussing the techniques or algorithm require to create deepfake and to detect the deepfake in audiodata. [ABSTRACT FROM AUTHOR]

Accidents on the road are happened in Low visibility Conditions like overcast, rainy night, foggy day in order to enhance machine vision in bad climate conditions. We suggest in this paper, a Different class climate classification method. Firstly, visual feathers are obtained from different traffic scene pictures, and features are state as eight dimensions of matrix. Secondly, Six supervised learning techniques are used to train six classifiers. The suggested approach has a high rate of identification precision and adaptability. The Proposed method is used to detect night time illumination changes and driver's vision in foggy day. [ABSTRACT FROM AUTHOR]

The article presents an overview of the well-known locomotive systems of machine vision. A search was made for scientific papers aimed at the development of machine vision systems. The limiting parameters of locomotive machine vision systems are defined and described, namely the illumination factor, which directly affects the quality of detection of objects of interest. A method for providing dynamic lighting for locomotive machine vision systems is proposed, which allows obtaining more detailed information about objects of interest in curved sections of the track and in conditions of limited visibility. [ABSTRACT FROM AUTHOR]

A bigger role in our lives is being played by deep learning (DL). It has already had a significant effect in fields including self-driving cars, speech recognition, cancer diagnosis, precision medicine, and forecasting. Generative adversarial networks, convolutional neural networks, and visual geometry groups employing computer vision are a few of the key facilitators of DL algorithms. Using the defined keywords "deep learning," "image quality," and "computer vision and their application," the current study conducts an exhaustive search of all pertinent research articles on deep learning in image enhancement in three easily accessible databases, namely IEEE, ScienceDirect, ResearchGate, and Kaggle. Two categories are used to separate the final collection of papers on deep learning's application to image improvement. In the first category, you'll find publications that made an effort to build and construct deep learning, especially those that focused on novel architecture, system designs, frameworks, schemes, models, techniques, and algorithms. The second group of studies includes those that made an effort to assess and examine the use of generative adversarial networks in picture improvement. [ABSTRACT FROM AUTHOR]

This study makes a speciality of a way to use the Statistical Analysis for Data Science approach to a real-international commercial enterprise scenario. Through this paper, the prominence of the Statistical Learning is known. Statistical Learning helps us, locating out the answer for a statistical inferential trouble through which it is easy to discover a predictive characteristic primarily based on the information we have. Statistical learning performs a distinguished position in the various fields like Computer Vision, Speech Recognition, Emotion and Gender identification of Data Science. [ABSTRACT FROM AUTHOR]

Early identification and diagnosis of Autism Spectrum Disorder (ASD), along with primary prevention, are crucial and may have long-term positive impacts on the lives of individuals with ASD. Research developments indicate towards current processes for early ASD evaluation that include facial expressions, body movement, eye movement monitoring, machine learning, computer vision, as well as other assessment techniques. This paper provides an examination of previous research, focusing on the stimuli, dataset, methodology, eye movement, and facial expressions for detection of ASD with the accuracy measures. Evidence suggests that combination of more than one biomarker conjunction with machine and deep learning techniques might be a useful tool for accurate and early diagnosis of autism. [ABSTRACT FROM AUTHOR]

Image processing domain involves various steps like preprocessing, augmentation, segmentation and recognition of images. Consistent image segmentation technique plays crucial role in computer vision domain. Using sophisticated segmentation techniques or segmentation models on image datasets resolves recognition, detection, feature extraction and classification issues in image processing and computer vision problems. Several literature surveys have shown improvement in the results after applying these segmentation techniques in the domain of machine learning as well as in deep learning. In this paper, we are analyzing mainly wheat leaf diseases by applying segmentation techniques or segmentation models in both machine learning and deep learning areas. We are also reviewing various segmentation techniques applied on other crops for comparative analysis with the wheat crops. [ABSTRACT FROM AUTHOR]

This paper discusses the importance of communication for human interaction, especially for individuals with hearing impairments who rely on sign language. However, learning sign language is not easy, and not many people are familiar with it. To bridge the communication gap between deaf individuals and the general public, this study focuses on developing a deep convolutional neural network (CNN) model to recognize sign language patterns, specifically SIBI Sign Language used for formal activities. The VGG16 architecture is employed, which has been trained on a sign language dataset with 1440 images. The results show an accuracy of over 98.32% in training data. This research demonstrates how technology, particularly deep learning and computer vision, can help solve communication problems and improve accessibility for individuals with hearing impairments. [ABSTRACT FROM AUTHOR]

Computer vision is an area of machine learning that enables computers and systems to take actions and make recommendations based on information from digital images, videos, and other visual inputs. The purpose of this paper is to discuss the selection of optimal parameters in car classification training. This paper discusses computer vision training using the CNN algorithm on vehicle miniature classification. One of the factors that affect the performance of Convolutional Neural Network (CNN) is the selection of appropriate parameters. The data we use comes from the primary data we collect. We took photos of 3 types of vehicles, namely buses, cars, and motorcycles with a total of 486 instances. Next we do data preprocessing by resizing 256*256px. Then we conducted various trials of data augmentation i.e: including "horizontal", "vertical", "horizontal and vertical". We experimented with different augmentations to get the highest accuracy. We present several variations of the epoch to identify the best model of CNN. The accuracy results obtained are 97.34%. [ABSTRACT FROM AUTHOR]

Endoscopy is one of the cornerstones in the field of gastroenterology. The growth of image technology in recent years has given technological support for the expertise of the medical device sector, particularly in the area of medical imaging. Computer vision uses real-time Localization and Mapping Create SLAM (simultaneous localization and mapping). The purpose of SLAM technology is to map the location environment, and at the same time use the signal provided by the sensors to locate the sensor system in the environment. In order to simplify the navigation system for minimally invasive abdominal surgery, a laparoscopic navigation system based on SLAM was developed. Combining medical information with real-time laparoscopic video can increase the doctor's field of view, assist in identifying critical areas, and enable safer and more effective surgical procedures. The purpose of this paper is to study how SLAM technology can solve some problems in minimally invasive surgery in medical endoscopy and to look forward to the bright future of SLAM technology and medical endoscopy. [ABSTRACT FROM AUTHOR]

Image denoising is a very important part of image processing. Denoising is utilized in a variety of fields and applications, including medicine, satellite television, and computer vision. Recently, several methods and approaches proposed to improve image denoising. This paper proposes an Enhanced Median Filter (EMF) for minimizing noise specifically salt and pepper noising. The proposed EMF uses standard median filter (MF) conditions. EMF improved the standard MF method, to restore the grey values of damaged pixels. The proposed method filters out noisy pixels by replacing the new values found by the median filter in the same image. As a result, EMF outperforms both the standard median filter and the Comprehensive Median Filter in terms of performance (CMF). The suggested method was evaluated on a range of standard images from the MATLAB library. According to the findings, the proposed method outperforms the standard median filter for high-noise images. [ABSTRACT FROM AUTHOR]

The paper considers a comparison of the main approaches to tracking human movements for subsequent use in virtual reality systems. Qualitative and quantitative differences between the following technologies are investigated: depth sensors, cameras using computer vision methods, laser grid, virtual reality trackers, motion capture suit. An analysis of the advantages and disadvantages of each of the approaches was carried out, taking into account the need to solve the problem of accurately recreating a digital copy of a person in virtual reality. The comparison evaluated positioning accuracy, tracking area, number of tracking points, data processing speed and other objective criteria that directly affect the quality of human tracking. As a result of the comparison, it was found that none of the methods provides sufficient universality. An approach based on the use of motion capture systems, virtual reality trackers and computer vision is proposed, which will eliminate the weaknesses of these approaches to solve the problem of tracking human motion capture and subsequent transfer of a digital copy to virtual reality. [ABSTRACT FROM AUTHOR]

The distribution and transmission of high-voltage transmission networks (HVTLNs) have become increasingly important for renewable energy. It is impossible for a power transmission network to function without an insulator. By utilizing automation and computer vision techniques, power system infrastructures such as component inspections, insulation inspections, transformer bushing inspections, etc. are monitored and controlled. The use of computer vision and component classification techniques has become increasingly popular in recent years rather than traditional methods of inspection. Using Unmanned Aerial Vehicles (UAV) images, this paper presents a system for classifying faulty insulators. In this research work noise reduction begins with pre-processing through median filters. Then, Segmenting the data is then accomplished using a clustering algorithm with k-means. From the segmented data, features are extracted using GLCM. Finally, Support Vector Machines (SVMs) are used to locate and classify, the insulator fault with higher recall and precision rate. [ABSTRACT FROM AUTHOR]

Proper heliostat alignment is a crucial point for the optimal operation of Solar Power Tower plants. To quantify canting errors in heliostat facets, we propose a target reflection technique that uses computer vision to overcome the limitations of existing methods. In our approach, a high-resolution camera is mounted on the back structure of a target heliostat. The reflection of the object heliostat mirrors contains the reflection of the back structure with the camera. This paper explains the 7-step methodology that ends up with the comparison of detected and modelled reflected borders. Preliminary results in a lab-scale testbed show a technique's uncertainty of around 0.2 mrad, including the experimental error associated with the manual adjustment of facets. [ABSTRACT FROM AUTHOR]

Solar Power Tower systems use a series of tracking mirrors (heliostats) to concentrate sunlight into a central receiver. Each heliostat is composed of a series of smaller mirrors, called facets, that need to be correctly aligned to focus the beams into the receiver. A common problem associated with this technology is finding canting errors in the heliostat facets. One of the techniques proposed to overcome this problem includes using computer vision to accurately locate the facets and then using a heliostat's theoretical model to calculate the errors. This paper describes the computer vision mechanisms necessary to perform facet detection, proposing a quasi-automated process that minimizes the need for human input. Results show that the quasi-automated solution provides low errors in distance and slope with respect to a manual edge labelling. [ABSTRACT FROM AUTHOR]

Image denoising is one of the most fundamental difficulties in image processing and computer vision, with the objective of recovering the original image by suppressing noise from a noise-contaminated version of the image. Image noise can be created by a variety of internal (sensor) and external (environment) factors that are difficult to prevent in real-world settings. As a result, image denoising is useful in a variety of applications, including image restoration, visual tracking, image registration, image segmentation, and image classification, where recovering the original image content is essential for good performance. While various methods for image denoising have been proposed, the problem of image noise suppression remains unsolved. The purpose of this paper is to present a comprehensive study on vector median filters for removing the adverse impact of impulse noise from color images. Color images are vectored value signals that are nonstationary in nature. As a result, nonlinear filters such as vector median filters outperform linear filters. In the literature, a variety of nonlinear filters have been proposed. [ABSTRACT FROM AUTHOR]