Search

The number of herbal plants in Indonesia is 30,000, but only about 1,200 plants are used in medicine. The large number of herbal plants makes it difficult for people to distinguish one type of herbal plant from another. From these conditions, this research has conducted tests to compare the performance of the K-Nearest Neighbor (KNN) and Convolutional Neural Network (CNN) methods using Fourier Descriptor (FD) feature extraction on herbal plants, namely moringa (moringa oleifera) and katuk (sauropus androgynus). The amount of data used is 480 data using image conditions, namely dark and light images which are then divided into 20% testing data and 80% training data. Classification is done using the KNN method using 5 distance calculations (Euclidean, Chebyshev, Manhattan, Minkowski, and Hamming) and CNN with FD feature extraction. From the tests that have been carried out, it is found that the use of FD feature extraction for the KNN method produces the best performance on both light and dark image data. While the use of the CNN method, for dark image data, the best accuracy results are obtained with FD feature extraction and CNN. Meanwhile, for bright image data, the best performance accuracy results are obtained in the CNN method without going through feature extraction. Of these three methods, using FD and KNN feature extraction is more recommended because it produces 100% accuracy in moringa and katuk images with light and dark intensity.

This paper studies the problem of linkage-bar synthesis by means of multiple deep neural networks (DNNs), which requires the inverse solution of linkage parameters based on a desired trajectory curve. This problem is highly complex due to the fact that the solution space is nonlinear and may contain multiple solutions, while a good quality of learning cannot be obtained by a single neural network approach. Therefore, this paper proposes employing Fourier descriptors to represent trajectory curves in a systematic and normalized form, developing a multi-solution distribution evaluation by random restart local searches (MDE-RRLS) to examine a better solution-space partitioning scheme, utilizing multiple DNNs to learn subspace regions separately, and creating a multi-facet query (MFQuery) to cooperatively predict multiple solutions. The experiments demonstrate that the proposed approach can obtain better or at least competitive outcomes compared to previous work in the literature. Furthermore, to verify the effectiveness and applicability, this paper investigates the design problem of an industrial six-linkage-bar ladle mechanism used in a die-casting system, and the proposed method can obtain several superior design solutions and offer alternatives in a short period of time when faced with redesign requirements. [ABSTRACT FROM AUTHOR]

Hal yang kritis dalam proses pengenalan pola adalah ekstraksi fitur. Merupakan suatu metode untuk mendapatkan ciri-ciri suatu citra (image) sehingga dapat dikenali satu sama lain. Pada penelitian ini, metode deskriptor Fourier digunakan untuk mengekstraksi pola aksara Lontara yang terdiri dari 23 huruf. Deskriptor Fourier adalah metode yang digunakan dalam pengenalan objek dan pemrosesan citra untuk merepresentasikan bentuk batas segmen citra. Pengenalan karakter dilakukan dengan menggunakan jarak Euclidean dan Manhattan. Hasil pengujian menunjukkan bahwa tingkat pengenalan tertinggi mencapai akurasi 91,30% dengan menggunakan koefisien Fourier sebesar 50. Pengenalan huruf menggunakan Manhattan dan Euclidean cenderung sama atau menghasilkan akurasi yang cenderung serupa. Akurasi tertinggi dicapai saat menggunakan Manhattan sebesar 91,30%.

The study is a comparative analysis of two fast reflection symmetry axis detection methods: an algorithm to refine the symmetry axis found with a chain of skeletal primitives and a boundary method based on the Fourier descriptor. We tested the algorithms with binary raster images of plant leaves (FLAVIA database). The symmetry axis detection quality and performance indicate that both methods can be used to solve applied problems. Neither method demonstrated any significant advantage in terms of accuracy or performance. It is advisable to integrate both methods for solving real-life problems.

This paper studies the problem of linkage-bar synthesis by means of multiple deep neural networks (DNNs), which requires the inverse solution of linkage parameters based on a desired trajectory curve. This problem is highly complex due to the fact that the solution space is nonlinear and may contain multiple solutions, while a good quality of learning cannot be obtained by a single neural network approach. Therefore, this paper proposes employing Fourier descriptors to represent trajectory curves in a systematic and normalized form, developing a multi-solution distribution evaluation by random restart local searches (MDE-RRLS) to examine a better solution-space partitioning scheme, utilizing multiple DNNs to learn subspace regions separately, and creating a multi-facet query (MFQuery) to cooperatively predict multiple solutions. The experiments demonstrate that the proposed approach can obtain better or at least competitive outcomes compared to previous work in the literature. Furthermore, to verify the effectiveness and applicability, this paper investigates the design problem of an industrial six-linkage-bar ladle mechanism used in a die-casting system, and the proposed method can obtain several superior design solutions and offer alternatives in a short period of time when faced with redesign requirements.

As an effective tool for data analysis, formal concept analysis (FCA) is widely used in software engineering and machine learning. The construction of concept lattice is a key step of the FCA. How to effectively to update the concept lattice is still an open, interesting and important issue. To resolve this problem, an incremental algorithm for concept lattice on image structure similarity (SsimAddExten) was presented. The proposed method mapped each knowledge class on the conceptlattice into a graphic, when a new object was added or deleted in a knowledge class, the boundary profile of graphic will be changed, the graphic edge structure similarity was introduced as the calculation index of the change degree before and after the knowledge, and the concept lattice will be updated on the basis of the index. We performed experiments to test SsimAddExtent, whose computational efficiency obtains obvious advantages over mainstream methods on almost all test points, especially on the data set with a large number of attributes. But, its complexity is not reduced compared with mainstream methods. Both theoretical analysis and performance test show SsimAddExtent algorithm is better choice when we apply the FCA to large scale data or non-sparse data. [ABSTRACT FROM AUTHOR]

Abstract Robust vision-based hand pose estimation is highly sought but still remains a challenging task, due to its inherent difficulty partially caused by self-occlusion among hand fingers. In this paper, an innovative framework for real-time static hand gesture recognition is introduced, based on an optimized shape representation build from multiple shape cues. The framework incorporates a specific module for hand pose estimation based on depth map data, where the hand silhouette is first extracted from the extremely detailed and accurate depth map captured by a time-of-flight (ToF) depth sensor. A hybrid multi-modal descriptor that integrates multiple affine-invariant boundary-based and region-based features is created from the hand silhouette to obtain a reliable and representative description of individual gestures. Finally, an ensemble of one-vs.-all support vector machines (SVMs) is independently trained on each of these learned feature representations to perform gesture classification. When evaluated on a publicly available dataset incorporating a relatively large and diverse collection of egocentric hand gestures, the approach yields encouraging results that agree very favorably with those reported in the literature, while maintaining real-time operation.

Sign language is a natural language mostly used by persons with hearing- and speech-based impairments to communicate with other people. In these modern times, sign language guides are used to eliminate the communication gap between people having hearing impairments and those with or without hearing impairments; however, they are very limited in number. To solve this challenge, automatic sign language recognition systems are developed to better reduce the communication gap for people with hearing disabilities. This paper presents the development of an automatic Amharic sign language translator which translates Amharic alphabet signs into their corresponding text using digital image processing and machine learning algorithms. The proposed system has four major developmental stages which include preprocessing, segmentation, feature extraction and classification. A total number of thirty-four features were extracted from shape, motion and color of hand gestures to represent both the base and derived class of Amharic sign characters. Classification models were built using artificial neural network (ANN) and multi-class support vector machine (SVM). The results show that the recognition system is capable of recognizing the Amharic alphabet signs with an average accuracy of 80.82% and 98.06% using the ANN and SVM classifiers, respectively. [ABSTRACT FROM AUTHOR]

This paper proposes a feature characterization method that can discriminate between man-made and natural objects on the seabed using a pair of SAS and optical images. Feature matching methods, like scale-invariant feature transform (SIFT), usually utilize gradient information to detect feature points, whereas contour-based features often use geometrical descriptors such as roughness, circularity, and solidity. However, due to the different characteristics of sonar and optical imagery, current descriptors cannot be directly applied over sonar-optical image pairs. The clarity of the water (muddy water, concentration of particles that scatter light) for optical images, and the stability of the platform, and reflections from seabed for SAS images are important parameters that distort the two images and make it hard to match between the two image sources. This paper proposes a feature characterization method that can identify man-made objects in underwater optic-SAS image pairs. Two new contour-based feature descriptors are introduced. The first is the entropy angle feature, which aims to reflect the entropy of the angles that originate from points on the contour. The second feature is local curve fitting, which characterizes the radial-polar space of the local curve polynomial fitting. The descriptors are designed to characterize man-made objects whose contour is expected to be smoother than natural objects such as rocks. Experimental results on a real, large dataset comprised of 1,519 optic-SAS image pairs, are shown to verify that the proposed method has a high level of classification accuracy and good discrimination between man-made and natural objects. [ABSTRACT FROM AUTHOR]

Roundness and sphericity have long been considered as measurements of the basic morphological properties of soil particles. Recent progress in optical image processing and analysis has enabled us to automate and rapidly perform Fourier analysis. Thus, obtaining complex Fourier descriptors describing the outline boundary of a 2-dimensional projected image of a soil particle could be performed. In this regard, we performed correlation analysis with the values of roundness, sphericity, and complex Fourier descriptor coefficients for 115 images of soil particles measured and reported in previous studies. The results of the statistical analysis revealed that roundness was strongly negatively correlated with Fourier descriptors of the order less than −5 or higher than +5. The width-to-length ratio sphericity was strongly correlated with the Fourier descriptor of the order of +2. [ABSTRACT FROM AUTHOR]

Abstract Soil particle shape analysis was conducted on two calcareous sands from Dissa and Matmata in Tunisia and one silica sand from Jumunjin in Korea using an image analysis method. This technique uses complex Fourier shape descriptors and image analysis of sand grains SEM photographs to provide accurate quantification of particle morphology and texture. The Fourier descriptors, denoted “Signature Descriptors”, provide measures of Elongation, Triangularity, Squareness, and Asymmetry and identify the overall shape of soil particles. A summary of higher-order descriptors provides textural information linked up to local roughness and texture characteristics. After analyzing the Fourier descriptors, elongation was found to be the major characteristics of the three sands, mainly for the Dissa and Matmata carbonate sands. In addition, the elongation signature descriptors for the Dissa and Matmata sands have very high values compared to those of Ras Alkhair (Saudi Arabia) and Dog’s bay (Ireland) sands. Therefore, the Dissa and Matmata carbonate sands have higher angles of friction and higher critical state angle of friction than Ras Alkhair and Dog’s bay sands. Furthermore, the Dissa and Matmata carbonate sands show higher roughness than Jumunjin’s silica sand.

This article revisits methods based on global descriptors to estimate the pose of a known object using a monocular camera, in the context of space rendezvous between an autonomous spacecraft and a noncooperative target. These methods estimate the pose by detection, i.e., they do not require any prior information about the pose of the observed object, making them suitable for initial pose acquisition and the monitoring of faults in other on-board estimators. We consider here specifically methods that retrieve the pose of a known object using a precomputed set of invariants and geometric moments. Three classes of global invariant features are analyzed, based on complex moments, Zernike moments, and Fourier descriptors. The robustness, accuracy, and computational efficiency of the different invariants are tested and compared under various conditions. We also discuss certain implementation aspects of the method that lead to improved accuracy and efficiency over previously reported results. Overall, our results can be used to identify which variations of the method offer a sufficiently fast and robust solution for pose estimation by detection, with low computational requirements that are compatible with space-qualified processors. [ABSTRACT FROM AUTHOR]

Robust vision-based hand pose estimation is highly sought but still remains a challenging task, due to its inherent difficulty partially caused by self-occlusion among hand fingers. In this paper, an innovative framework for real-time static hand gesture recognition is introduced, based on an optimized shape representation build from multiple shape cues. The framework incorporates a specific module for hand pose estimation based on depth map data, where the hand silhouette is first extracted from the extremely detailed and accurate depth map captured by a time-of-flight (ToF) depth sensor. A hybrid multi-modal descriptor that integrates multiple affine-invariant boundary-based and region-based features is created from the hand silhouette to obtain a reliable and representative description of individual gestures. Finally, an ensemble of one-vs.-all support vector machines (SVMs) is independently trained on each of these learned feature representations to perform gesture classification. When evaluated on a publicly available dataset incorporating a relatively large and diverse collection of egocentric hand gestures, the approach yields encouraging results that agree very favorably with those reported in the literature, while maintaining real-time operation. [ABSTRACT FROM AUTHOR]

The geometrical modeling of granular objects is a complex challenge that exists in many scientific fields, such as the modeling of granular materials or rocks and coarse aggregates with applications in civil, mechanical, and chemical engineering. In this paper, a model called SPHERE (Stochastic Process for Highly Effective Radial Expansion) is proposed, which is based on the deformation of an ellipsoid mesh using multiple 3D Gaussian random fields. The model is designed to be flexible (full control over 2D and 3D morphological properties of granular objects), ultra-fast (over 1000 aggregates in less than 5 s), and independent of the mesh and base shape used (as long as it is a star-shaped object). The flexibility of the model and its ability to reflect real data is illustrated using images of latex nanoparticle aggregates. Using 2D measurements on images from a morphogranulometer, a method based on the SPHERE model is proposed to estimate the 3D morphological properties of aggregates. A multiscale optimization process is applied, in particular using a partial reconstruction of 2D shapes from elliptic Fourier descriptors, in order to best reproduce the shape, angularity and texture of the aggregates using the SPHERE model. Validation of the method on 3D printed data shows relative errors of less than 3% for all measured 2D and 3D morphological characteristics, and validation on a population of synthetic objects shows relative errors of less than 6%. The results are compared and discussed with those obtained using other models based on overlapping spheres and show consistency with previous work. Finally, suggestions for improvement are given. [Display omitted] • Proposed SPHERE model uses 3D random fields to deform a mesh. • Model generates >1000 aggregates in <5 s with full morphological flexibility. • 3D printed object and numerical validation using multiscale optimization. • SPHERE can estimate 3D morphological properties from 2D image measurements. • SPHERE's adaptability showcases potential for diverse scientific applications. [ABSTRACT FROM AUTHOR]

Firmness is one of the important indicators for the internal quality of fruits. Natural frequency has widely been expected to evaluate the fruit firmness in recent years. Several indices have successfully been applied for the firmness of sphere-shaped fruits using the natural frequency and fruit mass. However, the fruit with non-spherical or irregular shapes cannot be suitable for firmness evaluation, due mainly to the fact that the fruit shape can interfere with the resonance frequency. Thus, some dual-frequency indices were established to measure the firmness of fruit with ellipsoidal shapes. Nevertheless, these indices cannot accurately evaluate the firmness of complex and irregular pears. In this study, a Fourier descriptor was established as a reliable shape descriptor to evaluate the firmness, thereby representing complex, irregular, or a larger variation of pear shapes. Firstly, the shape images of pears were captured by a camera. Then, the boundary edges of pear images were extracted to calculate the normalized radiuses. After that, a Fourier transform was performed on the normalized radius to obtain the Fourier descriptor. Finally, the first 15 Fourier descriptors were screened to describe the complex shapes of pears. Meanwhile, an experimental modal combined with the Finite Element Method (FEM) was utilized to analyze the effect of fruit shape on the natural frequency. Three modes included bending, compression, and breathing during a test. The natural frequency was easy to measure the equatorial region of the pear fruit in the compression mode. The largest deformation appeared, when the pear was impacted on this region. As such, the pear was assumed to be linearly elastic, homogeneous and isotropic material in the FEM. A process of reverse engineering was utilized to form the geometric model of pears. The 3D 4-node tetrahedral structural solid element was selected, allowing three translational and three rotational degrees of freedom at each node. Consequently, three shapes and natural frequencies in FE modal analysis were highly related to the experimental data. Therefore, the FEM model was expected to analyze the influence of Fourier descriptors on the natural frequency of the pear. These results indicated that the first Fourier descriptor (F1) had a significant effect on the natural frequencies of three modes. The frequency decreased linearly for the bending and compression mode, and increased linearly for the breathing mode, with the increasing of the F1. A new firmness index was established using the relationship between the F1 and frequency in the compression mode. Finally, an M-T penetration test was conducted to investigate the correlation between the nondestructive and destructive firmness indices. By comparison, the Coefficient of Determination (COD) was 0.892 for the new index SE(F1) with the destructive M-T firmness tester. Two dual-frequency firmness indices for the ellipsoidal fruit and firmness index SE(q), the COD were 0.733, 0.775, 0.765, and 0.746, respectively, for traditional spherical firmness index. Therefore, the new firmness index can accurately evaluate the firmness of complex and irregular shape pears. Consequently, this finding can provide promising practical guidance for the nondestructive detection of the firmness of differently shaped pears using resonance in intelligent agriculture. [ABSTRACT FROM AUTHOR]

Nowadays, thermal cameras play a major role because of its temperature-based photography in many applications such as video surveillance, monitoring electronics/electrical machines, forest monitoring, monitoring babies/adult patients, and suspicious object detection. Tracking pedestrians in thermal video is a major task for such applications. Thermal cameras usually create images based on temperature emitted by the object only and not on the lighting conditions and outdoor environment conditions. But still thermal images have constraints like no texture or colour information, more number of dead pixels, low resolution, and noticeable visual colour patterns in case of any temperature variations. So the challenge in tracking pedestrians in thermal videos is tracking objects/pedestrians throughout the video without an identity switch by overcoming these constraints which may mislead the tracking process. To overcome these constraints, the proposed system uses tri feature matrix (TFM) as an object descriptor which is used to uniquely identify and represent objects in thermal images. TFM is represented in more compact way as a triple matrix. It is a simple and accurate descriptor suitable for tracking objects in thermal video sequences without an identity switch. The proposed Pedestrian tracking system uses most of the advantages of thermal cameras by overcoming challenges in thermal videos effectively based on a novel descriptor TFM. The proposed system is evaluated with various data sets, and the results are analysed using true positive, true negative, false negative, false positive, accuracy, precision, recall, F-score, global identity mismatch (GMME) and track matching error (TME). The performance metrics such as accuracy, precision, recall, F-score, GMME and TME are computed as 99%, 100%, 99%, 99%, 2.3%, and 2.1%, respectively. From the observation, it is found that the performance of proposed TFM-based system is significantly improved. The experimental result shows that the proposed system achieved more accurate tracking compared to the conventional methods. [ABSTRACT FROM AUTHOR]

With the popularity of automobiles, road traffic accidents and congestion have become increasingly serious. Therefore, technologies are needed to solve problems such as speeding and congestion. The detection and tracking of vehicles based on computer vision and Internet of Things monitoring are an important part of the intelligent traffic monitoring system. The angle between the camera and the vehicle will cause the gradually moving vehicles to have a connection during image segmentation. This paper aims to improve the detection accuracy of vehicles from camera images. A new separation method of the vehicle detection area was proposed in this paper. Moving areas are extracted by inter-frame differences, and vehicle areas are formed from the areas. If more than one vehicle area partially overlaps as one area, it is necessary to separate the area. The existing method extracts a place to be separated from an outline of the area. However, it is impossible for the method to separate vehicles using the extracted shape. Therefore, a new method is proposed that makes the place to be separated defined by the reshaping of the area with the use of the Fourier descriptor. The method tries to detect the place from the area. As a result, this method makes it possible to separate the area that the existing method cannot separate and it has obtained a high accuracy of separation in the experimental data of the Internet of Things monitoring.

Real-time applications of image and video processing algorithms have seen explosive growth in number and complexity over the past decade driven by consumer, scientific and defense applications exploiting inexpensive digital video cameras and networked computing device. This growth has opened up different alternatives to greatly enhance the surveillance capabilities using new architectures and parallelization strategies developed due to the increased accessibility of multicore, multi-threaded processors along with general purpose graphics processing units (GPUs). In this paper, we present a new implementation of a moving human detection algorithm on GPU based on the programming language CUDA. In our approach, the moving object is extracted by background subtraction based on the GMM (Gaussian Mixture Model) on GPU. Then, two complementary features are extracted for moving object classification. They are contour-based description: FD or Fourier Descriptor and region-based description: HOG or Histogram of Oriented Gradient. Both descriptors will then be effectively integrated to SVM (Support Vector Machine), which is able to provide the posterior probability, to achieve better performance. The implementation of such algorithm on a GPU allows a great performance in terms of execution time since it is 19 times faster than that on a CPU. Experimental results show also that the proposed approach outperforms some existing techniques and can detect pedestrians in real-time effectively. [ABSTRACT FROM AUTHOR]

Copyright of China Mechanical Engineering is the property of Editorial Board of China Mechanical Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Purpose: Intracranial aneurysms (IA) are abnormal dilatation of the arteries at the circle of Willis whose rupture can lead to catastrophic complications such as hemorrhagic stroke. The purpose of this work is to detect IA in 2D-DSA images. The proposed detection framework uses local binary patterns for the determination of initial aneurysm candidates and generic Fourier descriptor (GFD) for false positive removal. Methods: Here, the designed framework takes DSA images including IA as input and produces images where the IA is clearly identified and localized. The multi-step approach is defined as the following: The first phase presents the determination of initial aneurysm candidates using the uniform local binary patterns (LBPs). The LBPs are calculated from these images in order to identify texture contents of both aneurysm and no-aneurysm classes. The second phase presents the false positives removal using a shape descriptor based on contours: the GFD. Results: We demonstrated that the proposed detection method successfully recognized morphological features of intracranial aneurysm. The results demonstrated excellent agreement between manual and automated detections. With the computerized IA detection framework, all aneurysms were correctly detected with zero false negative and low FP rates. Conclusion: This study shows the potential of LBP and GFD as a feature descriptors and paves the way for a whole image analysis tool to predict intracranial aneurysm risk of rupture. [ABSTRACT FROM AUTHOR]

Combining synthetic aperture sonar (SAS) imagery with optical images for underwater object classification has the potential to overcome challenges such as water clarity, the stability of the optical image analysis platform, and strong reflections from the seabed for sonar-based classification. In this work, we propose this type of multi-modal combination to discriminate between man-made targets and objects such as rocks or litter. We offer a novel classification algorithm that overcomes the problem of intensity and object formation differences between the two modalities. To this end, we develop a novel set of geometrical shape descriptors that takes into account the geometrical relation between the object's shadow and highlight. Results from 7,052 pairs of SAS and optical images collected during several sea experiments show improved classification performance compared to the state-of-the-art for better discrimination between different types of underwater objects. For reproducability, we share our database. [Display omitted] • A novel features set that uniquely characterizes the object's shape, and the object's highlight-shadow geometrical relations. • A multi-label classification method for underwater objects using both optical and SAS images. • Underwater object classification method that avoids registration and calibration. [ABSTRACT FROM AUTHOR]

With the increase in the number of music files on various devices, it can be difficult to locate a desired file, especially when the title of the song or the name of the singer is not known. We propose a new query-by-singing/humming (QbSH) system that can find music files that match what the user is singing or humming. This research is novel in the following three ways: first, the Fourier descriptor (FD) method is proposed as the first classifier; it transforms the humming or music waveform into the frequency domain. Second, quantized dynamic time warping (QDTW) using symmetrical search space and quantized linear scaling (QLS) are used as the second and third classifiers, respectively, which increase the accuracy of the QbSH system compared to the conventional DTW and LS methods. Third, five classifiers, which include the three already mentioned along with the conventional DTW using symmetrical search space and LS methods, are combined using score level fusion, which further enhances performance. Experimental results with the 2009 MIR-QbSH corpus and the AFA MIDI 100 databases show that the proposed method outperforms those using a single classifier and other fusion methods.