Search

Background: Due to the uniqueness of individual fingerprint patterns, fingerprint recognition is a critical biometric identifying tool. Because of its pervasiveness and dependability, this technology requires ongoing refining and comprehension of its core concepts and applications in diverse real-world circumstances. Objective: This article aims to show how to use Gabor filters and the Euclidean distance to extract and match features. The system aims to explain the fundamental ideas of fingerprint recognition and show how accurate and efficient it is at identifying people. Methods: The system uses Gabor filters to capture fine details in fingerprint images, producing a fixed-length finger code. The Euclidean distance is employed to compare finger codes, making the matching process more efficient. The suggested algorithm is rigorously tested using the FVC2000 database, with picture quality improvements such as Gaussian filtering and histogram equalization implemented. Results: The system demonstrated its proficiency in fingerprint identification with a significant accuracy of 98.22%. The results highlight the system's basic character while recognizing the need for sophisticated methodologies and application adjustments. Conclusion: While the system serves as a core model for comprehending fingerprint identification, it emphasizes the significance of future study and development in picture pretreatment, feature extraction methods, matching approaches, and database administration. This article's insights contribute to the continuous advances in biometric identification technology by resolving problems and improving the reliability of fingerprint recognition systems.

【Objective】A practical mobile APP recognition system based on Android was designed for the requirement of real-time detection of various apple bark diseases in orchards.【Method】The images of ring rot, canker and dry rot were collected through network searching and field shooting. After amplification and labeling, the training set and test set were divided according to the ratio of 8 ∶ 2. The YOLOv5s algorithm was used to train the apple bark disease recognition network model. The lightweight network model trained was deployed on the Android end, and the corresponding APP interface was designed to realize the rapid diagnosis of ring rot, canker and dry rot.【Result】The recognition effect of the deep learning network obtained after training is good, the accuracy rate is stable at 88.7%, the recall rate is stable at 85.8%, and the average accuracy value is stable at 87.2%. Among them, the accuracy of canker is 93.5%, dry rot is 88.2%, and ring rot is 84.3%. After it is deployed on the Android end, the processing time of each disease picture is less than 1s, and the detection confidence is 87.954%. The lightweight recognition system not only realizes the rapid detection of the three diseases, but also ensures high recognition accuracy.【Conclusion】The YOLOv5s network weight model is small, which can be easily deployed on the Android. The APP designed based on YOLOv5s is simple to operate with high detection accuracy and fast recognition speed, which is helpful for precise management of orchards.

Injuries and the associated surgery to the anterior cruciate ligament (ACL) can often trigger unpredictable effects, such as the so-called giving way effect, which is an uncontrolled buckling of the knee joint. For this purpose, the KneTex project has developed a smart textile-integrated sensor and actuator bandage system to record the movement of such patients and to monitor and support the rehabilitation process. Long-term monitoring and analysis of the movement data will identify patterns or gait types that can lead to a giving way effect. This paper describes the recent developments of the random forest model-based motion classification system developed within the project. Improvements have been achieved by reducing the number of features needed by 25% using feature importance analysis, speeding up the computation time by 14%, and increasing the classification efficiency. Feature elimination is a useful tool to improve classification systems in settings where feature count is high and feature importance analysis contributed by improving our understanding which sensor of our system are important for the motion classification task.

Identity documents recognition is far beyond classical optical character recognition problems. Automated ID document recognition systems are tasked not only with the extraction of editable and transferable data but with performing identity validation and preventing fraud, with an increasingly high cost of error. A significant amount of research is directed to the creation of ID analysis systems with a specific focus for a subset of document types, or a particular mode of image acquisition, however, one of the challenges of the modern world is an increasing demand for identity document recognition from a wide variety of image sources, such as scans, photos, or video frames, as well as in a variety of virtually uncontrolled capturing conditions. In this paper, we describe the scope and context of identity document analysis and recognition problem and its challenges; analyze the existing works on implementing ID document recognition systems; and set a task to construct a unified framework for identity document recognition, which would be applicable for different types of image sources and capturing conditions, as well as scalable enough to support large number of identity document types. The aim of the presented framework is to serve as a basis for developing new methods and algorithms for ID document recognition, as well as for far more heavy challenges of identity document forensics, fully automated personal authentication and fraud prevention.

After surgery of the anterior cruciate ligament (ACL), unpredictable effects can occur in the patient’s gait patterns. Thus, patients often experience instability and uncontrolled buckling of the knee joint (“giving way” effect). The “giving way” effect is also difficult to measure due to the uncontrolled and rare occurrence. Within the KneTex project a smart textile-integrated sensor and actuator bandage system is developed to detect instability of the knee joint and actively support the rehabilitation process. Based on the sensor data the calculation of the knee angles as well as a recognition system is implemented. The bandage system can be controlled via a custom app which is developed as part of the project. This paper describes the recent developments and current status of the project. In addition, the results and steps for future work are described as well.

Sign language is used by people who have hearing and speaking difficulties, but not understood by many without these difficulties. Therefore, sign language recognition systems are developed to aid communication between hearing impaired people and others. This paper developed a static American Sign Language Recognition (ASLR) system using canny-edge and histogram of oriented gradient (HOG) for feature extraction with K-Nearest Neighbour (K-NN) as classifier. The sign language image datasets used consist of English alphabets from both Massey University and Kaggle, and numbers (0-9) from Massey University. Median filter was used to remove noise after images were converted to grayscale. Otsu algorithm was used for segmentation while edges in the images were preserved using canny edge detection technique with HOG parameters tuning to obtain feature vectors. The extracted features were used by K-NN for classification. An average recognition accuracy and computational testing time of 97.57% and 0.39s respectively were obtained based on experiments with the Massey University dataset. Similarly, an average recognition accuracy and computational testing time of 98.97% and 0.43s respectively were obtained based on experiments with the Kaggle dataset. The developed system successfully recognized static English alphabets and numbers and outperformed some existing systems.

Sign language is used by people who have hearing and speaking difficulties, but not understood by many without these difficulties. Therefore, sign language recognition systems are developed to aid communication between hearing impaired people and others. This paper developed a static American Sign Language Recognition (ASLR) system using canny-edge and histogram of oriented gradient (HOG) for feature extraction with K-Nearest Neighbour (K-NN) as classifier. The sign language image datasets used consist of English alphabets from both Massey University and Kaggle, and numbers (0-9) from Massey University. Median filter was used to remove noise after images were converted to grayscale. Otsu algorithm was used for segmentation while edges in the images were preserved using canny edge detection technique with HOG parameters tuning to obtain feature vectors. The extracted features were used by K-NN for classification. An average recognition accuracy and computational testing time of 97.6% and 0.39s respectively were obtained based on experiments with the Massey University dataset. Similarly, an average recognition accuracy and computational testing time of 99.0% and 0.43s respectively were obtained based on experiments with the Kaggle dataset. The developed system successfully recognized static English alphabets and numbers and outperformed some existing systems.

This paper proposes a deep learning approach to recognize Tamil Letter from images which contains text. This is recognition process, the text in the images are divided to letter or characters. Each recognized letters are sending to recognition system and filter the text using deep learning algorithms. Our proposed algorithm is used to separate letter from the text using convolution neural network approach. The filtering system is used for identifying font based on that letters are found. The Tamil letters are test data and loaded in recognition systems. The trained data are input which contains filtered letter from image. For example, Tamil letters such as are available in test dataset. The trained data are applied into deep convolution neural network process. The two dataset are created which contains test data with Tamil letter and second one for recognized input data or trained data. 15 thousands of letters are taken and 512 X 512 X 3 size deep convolution network is created with font and letters. As the result, 85% Tamil letters are recognized and 82% are tested using font. TensorFlow is used for testing the accuracy and success rate.

People with autistic spectrum disorders (ASDs) have difficulty recognizing and engaging with others. The symptoms of ASD may occur in a wide range of situations. There are numerous different types of functions for people with an ASD. Although it may be possible to reduce the symptoms of ASD and enhance the quality of life with appropriate treatment and support, there is no cure. Developing expert systems for identifying ASD based on the facial landmarks of children is the main contribution for improvements in the healthcare system in Saudi Arabia for detecting ASD at an early stage. However, deep learning algorithms have provided outstanding performances in a variety of pattern-recognition studies. The use of techniques based on convolutional neural networks (CNNs) has been proposed by several scholars to use in investigations of ASD. At present, there is no diagnostic test available for ASD, making this diagnosis challenging. Clinicians focus on a patient’s behavior and developmental history. Therefore, using the facial landmarks of children has become very important for detecting ASDs as the face is thought to be a reflection of the brain; it has the potential to be used as a diagnostic biomarker, in addition to being an easy-to-use and practical tool for the early detection of ASDs. This study uses a variety of transfer learning approaches observed in deep CNNs to recognize autistic children based on facial landmark detection. An empirical study is conducted to discover the ideal settings for the optimizer and hyperparameters in the CNN model so that its prediction accuracy can be improved. A transfer learning approach, such as MobileNetV2 and hybrid VGG19, is used with different machine learning programs, such as logistic regression, a linear support vector machine (linear SVC), random forest, decision tree, gradient boosting, MLPClassifier, and K-nearest neighbors. The deep learning models are examined using a standard research dataset from Kaggle, which contains 2940 images of autistic and non-autistic children. The MobileNetV2 model achieved an accuracy of 92% on the test set. The results of the proposed research indicate that MobileNetV2 transfer learning strategies are better than those developed in existing systems. The updated version of our model has the potential to assist physicians in verifying the accuracy of their first screening for ASDs in child patients.

Stair region detection and recognition from a stair candidate image is a challenging work in the computer vision research area. In the last few decades, researchers use many recognition systems to recognize and verify the stair region from other analogous objects. However, all the verification systems such as vanishing point (VP) do not achieve the desired result for various reasons. In this regard, a method is proposed in this paper to investigate the vanishing point’s problem arising in the case of stair region verification based on the three basic criteria, i.e. focal angle of the camera, height of the camera from the ground, and distance of the camera from the stair image. For that, primarily, the stair region is extracted by utilizing the geometrical features of a stair. The detected stair candidate region is verified through the y coordinate value of the vertical VP, i.e.y

In this age of artificial intelligence, facial expression recognition is an essential pool to describe emotion and psychology. In recent studies, many researchers have not achieved satisfactory results. This paper proposed an expression recognition system based on ResNet-152. Statistical analysis showed our method achieved 96.44% accuracy. Comparative experiments show that the model is better than mainstream models. In addition, we briefly described the application of facial expression recognition technology in the IoT (Internet of things).

Footstep recognition is relatively new biometrics and based on the learning of footsteps signals captured from people walking on the sensing area. The footstep signals classification process for security systems still has a low level of accuracy. Therefore, we need a classification system that has a high accuracy for security systems. Most systems are generally developed using geometric and holistic features but still provide high error rates. In this research, a new system is proposed by using the Mel Frequency Cepstral Coefficients (MFCCs) feature extraction, because it has a good linear frequency as a copycat of the human hearing system and Artificial Neural Network (ANN) as a classification algorithm because it has a good level of accuracy with a dataset of 500 recording footsteps. The classification results show that the proposed system can achieve the highest accuracy of validation loss value 57.3, Accuracy testing 92.0%, loss value 193.8, and accuracy training 100%, the accuracy results are an evaluation of the system in improving the foot signal recognition system for security systems in the smart home environment.

As an essential basic function of grassland resource surveys, grassland-type recognition is of great importance in both theoretical research and practical applications. For a long time, grassland-type recognition has mainly relied on two methods: manual recognition and remote sensing recognition. Among them, manual recognition is time-consuming and laborious, and easily affected by the level of expertise of the investigator, whereas remote sensing recognition is limited by the spatial resolution of satellite images, and is not suitable for use in field surveys. In recent years, deep learning techniques have been widely used in the image recognition field, but the application of deep learning in the field of grassland-type recognition needs to be further explored. Based on a large number of field and web-crawled grassland images, grassland-type recognition models are constructed using the PyTorch deep learning framework. During model construction, a large amount of knowledge learned by the VGG-19 model on the ImageNet dataset is transferred to the task of grassland-type recognition by the transfer learning method. By comparing the performances of models with different initial learning rates and whether or not data augmentation is used, an optimal grassland-type recognition model is established. Based on the optimal model, grassland resource-type map, and meteorological data, PyQt5 is used to design and develop a grassland-type recognition system that uses user-uploaded grassland images and the images’ location information to comprehensively recognize grassland types. The results of this study showed that: (1) When the initial learning rate was set to 0.01, the model recognition accuracy was better than that of the models using initial learning rates of 0.1, 0.05, 0.005, and 0.001. Setting a reasonable initial learning rate helps the model quickly reach optimal performance and can effectively avoid variations in the model. (2) Data augmentation increases the diversity of data, reducing the overfitting of the model; recognition accuracies of the models constructed using the augmented data can be improved by 3.07–4.88%. (3) When the initial learning rate was 0.01, modeling with augmented data and with a training epoch = 30, the model performance reached its peak—the TOP1 accuracy of the model was 78.32% and the TOP5 accuracy of the model was 91.27%. (4) Among the 18 grassland types, the recognition accuracy of each grassland type reached over 70.00%, and the probability of misclassification among most of the grassland types was less than 5.00%. (5) The grassland-type recognition system incorporates two reference grassland types to further improve the accuracy of grassland-type recognition; the accuracy of the two reference grassland types was 72.82% and 75.01%, respectively. The recognition system has the advantages of convenient information acquisition, good visualization, easy operation, and high stability, which provides a new approach for the intelligent recognition of grassland types using grassland images taken in a field survey.

The unrestricted consumption of fossil fuels negatively impacts the economic, social and environmental aspects, observed from a sustainable perspective. Therefore, it is necessary to develop and adopt skills that enable the monitoring and mitigation of risks to the environment. In view of this, we propose a method with multiple approaches emphasizing a three-dimensional perspective of energy consumption by diesel engines, which represent one of the main pollutants emitters in transport. As a methodology, fuzzy logic was adopted, together with a recognition system, in order to mitigate the uncertainties inherent to the applied data. The procedure was applied to the city of Rio de Janeiro, Brazil, with information collected from seven toll plazas and a radar with volumetric counting. The results indicate a good adherence of the sustainability index to real cases, allowing a better observation of changes in environmental criteria and a more efficient inspection in the application of good practices, in addition to enabling greater participation of society in the inspection and adoption of environmental criteria in transport.

The paper presents an alternative fast pornographic image recognition using compact holistic features and multi-layer neural network (MNN). The compact holistic features of pornographic images, which are invariant features against pose and scale, is extracted by shape and frequency analysis on pornographic images under skin region of interests (ROIs). The main objective of this work is to design pornographic recognition scheme which not only can improve performances of existing methods (i.e., methods based on skin probability, scale invariant feature transform, eigenporn, and Multilayer-Perceptron and Neuro-Fuzzy (MP-NF)) but also can works fast for recognition. The experimental outcome display that our proposed system can improve 0.3% of accuracy and reduce 6.60% the false negative rate (FNR) of the best existing method (skin probability and eigenporn on YCbCr, SEP), respectively. Additionally, our proposed method also provides almost similar robust performances to the MP-NF on large size dataset. However, our proposed method needs short recognition time by about 0.021 seconds per image for both tested datasets.

The paper is dedicated to algorithms for constructing a logical tree of classification. Nowadays, there exist many algorithms for constructing logical classification trees. However, all of them, as a rule, are reduced to the construction of a single classification tree based on the data of a fixed training sample. There are very few algorithms for constructing recognition trees that are designed for large data sets. It is obvious that such sets have objective factors associated with the peculiarities of the generation of such complex structures, methods of working with them and storage. In this paper, we focus on the description of the algorithm for constructing classification trees for a large training set and show the way to the possibility of a uniform description of a fixed class of recognition trees. A simple, effective, economical method of constructing a logical classification tree of the training sample allows you to provide the necessary speed, the level of complexity of the recognition scheme, which guarantees a simple and complete recognition of discrete objects.

An approach is proposed for solution of the problem for increasing the effectiveness of the recognition of the car number plate by using a priori information. Are proposed scheme of additional measurements, sequence of priori data statistical analysis and decision rule. An example of the proposed approach in the system recognition, built on the basis of the DVR is reviewed.

In Asia, decreasing farmer and labor populations due to various factors is a serious problem that leads to increases in labor costs, higher harvesting input energy consumption and less resource utilization. To solve these problems, researchers are engaged in providing long term and low-tech alternatives in terms of mechanization and automation of agriculture by way of efficient, low cost and easy to use solutions. This paper reviews various design strategies in recognition and picking systems, as well as developments in fruit harvesting robots during the past 30 years in several countries. The main objectives of this paper are to gather all information on fruit harvesting robots; focus on the technical developments so far achieved in picking devices; highlight the problems still to be solved; and discuss the future prospects of fruit harvesting robots.

Unmanned aerial vehicle (UAV)-based spraying systems have recently become important for the precision application of pesticides, using machine learning approaches. Therefore, the objective of this research was to develop a machine learning system that has the advantages of high computational speed and good accuracy for recognizing spray and non-spray areas for UAV-based sprayers. A machine learning system was developed by using the mutual subspace method (MSM) for images collected from a UAV. Two target lands: agricultural croplands and orchard areas, were considered in building two classifiers for distinguishing spray and non-spray areas. The field experiments were conducted in target areas to train and test the system by using a commercial UAV (DJI Phantom 3 Pro) with an onboard 4K camera. The images were collected from low (5 m) and high (15 m) altitudes for croplands and orchards, respectively. The recognition system was divided into offline and online systems. In the offline recognition system, 74.4% accuracy was obtained for the classifiers in recognizing spray and non-spray areas for croplands. In the case of orchards, the average classifier recognition accuracy of spray and non-spray areas was 77%. On the other hand, the online recognition system performance had an average accuracy of 65.1% for croplands, and 75.1% for orchards. The computational time for the online recognition system was minimal, with an average of 0.0031 s for classifier recognition. The developed machine learning system had an average recognition accuracy of 70%, which can be implemented in an autonomous UAV spray system for recognizing spray and non-spray areas for real-time applications.

Finger Braille is one of the communication media of deafblind people. In one-handed Finger Braille, a sender dots the left part of the Braille code on the distal interphalangeal (DIP) joints of the index, middle and ring fingers of a receiver, and subsequently dots the right part of the Braille code on the proximal interphalangeal (PIP) joints of the same fingers. Because there is a small number of non-disabled people who are skilled in Finger Braille, deafblind people communicate in this medium only through an interpreter. In this study, we developed a Finger Braille recognition system using small piezoelectric accelerometers worn by the receiver. We first conducted a measurement experiment to derive algorithms for the recognition of the dotted fingers and positions. The results showed that the accuracy of the recognition of dotted fingers was 92.9%, and the recognition system was independent of the dotted strength, dotted position and receiver. The accuracy of the recognition of dotted positions was 81.9%, and the recognition system could recognize dotted positions if the receiver's hand formed a natural longitudinal arch on the desk. Next, an evaluation experiment was carried out. The results showed that the accuracy of the recognition of dotted fingers by dotting was 89.7%, and the accuracy of recognition of dotted positions by dotting was 92.3%. Therefore, the recognition system could recognize sentences accurately when the interpreter dotted clearly.

This paper presents a robust algorithm for ear identification based on geometrical features of the ear and Kohnen Self Organization Maps (SOM). Using ears in identifying people has been interesting at least 100 years. The researches still discuss if the ears are unique or unique enough to be used as biometrics. Ear shape applications are not commonly used, yet, but the area is interesting especially in crime investigation. In this paper we present the basics of using ear as biometric for person identification and authentication. High resolution ear images are taken by high resolution digital camera. Six images have been taken for twenty three persons. Four geometrical distances were calculated for each image. These geometrical distances are used as an input to the unsupervised Kohonen self organization maps. The accuracy of identification were found to be equal to 98%, for the proposed system .We conclude that that the proposed model gives faster and more accurate identification of persons based on the ear biometrics and it works as promising tool for person identification of persons from the mage of their ear for criminal investigation purposes.