Wavelet Descriptors Research Articles

Discriminating Scleromystax barbatus (Siluriformes: Callichthyidae) populations from Atlantic Rainforest streams employing otolith shape

Abstract This study assessed the lapillus otolith shapes of males and females of Scleromystax barbatus from southern and southeastern regions in the Atlantic Rainforest biome employing Fourier and Wavelet descriptors. The utricular otoliths of S. barbatus are ovoid, with the gibbus maculae occupying almost all the ventral portion, similar to most Callichthyidae species. Otoliths of males and females of S. barbatus from the southeastern studied region are more elongated in the anterior-posterior direction and present larger sulcus and gibbus maculae, with heterogeneous borders. We found no sexual-based dimorphism in otolith shape within regions, however regional differences were registered and attributed to variations in fish life history mediated by differences in environmental factors (e.g., climatic conditions) between the southern and southeastern regions in the Atlantic Rainforest biome. Additional studies are suggested to investigate the influence of genetic effects and their environmental interactions to better understand how these factors are related with otolith shape and influence the discrimination among S. barbatus populations.

Intelligent Simulation Design and Application of Garment Digitization Based on Virtual Image Recognition Technology

Abstract Realizing the digital design of clothing is an effective means to improve the design efficiency and effect, for this reason, this paper designs a virtual simulation design assistance system based on virtual image recognition technology. Wavelet Fourier descriptor and LDA technology are utilized to extract features and decrease the dimensionality of the clothing style image, while the extreme learning machine is utilized as a classifier to categorize the clothing style image. Based on the classification results, a virtual simulation model of the garment is constructed and stored in the parts library for the convenience of designers to call and design at any time to complete the construction of the design assistance system. The application of this paper’s image recognition method results in an overall style recognition rate of 94.8%, an average recognition time of 3.2 milliseconds for each sample, and an average Fourier wavelet descriptor classification accuracy of 97.5%. The size error is controlled within ±2.5%, and the mean customer satisfaction scores for all the finished sweaters are higher than 2. This paper proposes a style map recognition method that achieves high accuracy, reduces time consumption, produces finished products with minimal size errors, and increases customer satisfaction with the designed styles.

Age affects otolith shape in a coastal pelagic fish (Scomber colias Gmelin, 1789)

Otolith shape analysis is a common and efficient technique to study the population structure of fish species. This approach compares the overall otolith shape among individuals collected along the species´ distribution range. Otolith shape may change during ontogeny; thus, comparing otolith sample collections comprising multiple and variable age classes may lead to biased results. Therefore, it is crucial to test for possible effects of age on the otolith shape for a given species before interpreting potential differences in otolith collections. Here, we explored the effect of age on the otolith shape of a coastal pelagic fish species with a wide geographical distribution and fast growth rate, the Atlantic chub mackerel Scomber colias (Gmelin, 1789). This effect was tested across different years using different age assignment techniques (direct age reading and age back-calculation) and otolith shape descriptors (Elliptic Fourier and Discrete Wavelet). The results show that the age effect on otolith shape is most noticeable between age-1 and older fish, possibly due to rapid growth during the first year of life. Also, the age effect on otolith shape depended on the descriptor used, being more detected when using the Discrete Wavelet descriptor compared to Elliptic Fourier. Our results highlight the need to carefully examine age effects on otolith shape before conducting population structure analysis on mixed-age sample collections.

Comparing otolith shape descriptors for population structure inferences in a small pelagic fish, the European sardine Sardina pilchardus (Walbaum, 1792).

Otolith shape analysis has been one of the most used approaches to study population structure in the past decades. Currently, two sets of shape descriptors are used to perform otolith shape analysis, namely, Elliptic Fourier descriptor (EFd), which focuses on the overall otolith shape differences, and Discrete Wavelet descriptor (DWd), which is sensible to local differences along the otolith contour. Here, the authors conducted a comparative analysis of the performance of both the descriptors in reconstructing the population structure and connectivity patterns in a small pelagic fish species with a wide geographical distribution and fast growth rate, the European sardine Sardina pilchardus (Walbaum, 1792), for the first time. A combination of each otolith shape descriptor and shape indices was explored using multivariate statistical methods. The two otolith shape descriptors showed similar, although limited, overall classification success associated with the population dynamic characteristics of the species. Both descriptors point to migration among adjacent areas, such as northern Atlantic locations, eastern Mediterranean and even across well-defined physical obstacles, such as the Strait of Gibraltar, among Atlantic and western Mediterranean locations. Both descriptors supported the division of the populations of Mediterranean waters into three main groups but slightly differed in the group limits of the Atlantic waters. A comparison of the present results with those from previous otolith shape analysis studies using EFd on a decadal time scale revealed differences in the population structure and connectivity patterns compared to the earlier period. These differences not only may be attributed to changes in environmental variables leading to changes in population dynamics but can also be the result of the sardine biomass sharp decrease that occurred in the past decade.

Peanut kernel integrity detection based on deep learning convolution neural network

The edge features of peanut grain image are not considered in peanut grain integrity detection, and there are many noises, resulting in low accuracy of peanut grain integrity detection and poor effect of image edge noise removal. Therefore, this paper designs a peanut seed integrity detection method based on deep learning convolution neural network. The edge contour of peanut grain image is closed, the edge contour curve characteristics of peanut grain image are extracted, the noise area of peanut grain edge image is determined according to the filter window of Gaussian kernel function, and the wavelet descriptor in contour description operator is used to reduce the edge noise of peanut grain image. Input the image into the convolution neural network, update the weight by gradient descent method, construct the peanut seed integrity detection model, output the peanut seed integrity detection results, and realize the peanut seed integrity detection. The experimental results show that the proposed detection method can improve the accuracy of peanut grain detection and has certain feasibility.

Wavelet descriptor network for arbitrary-shaped text detection

Arbitrary-shaped scene text detection is still a challenging task in computer vision, due to its high versatility and complexity. Most methods directly describe text instances by rectangles, quadrangles, or curves, probably leading to insufficient representations. We introduce wavelet descriptor (WD) for arbitrary-shaped text representation that decomposes text contours to wavelet coefficients and extracts feature sequences by discrete wavelet transform (DWT). Based on WD, we propose WD network, which predicts wavelet coefficients then reconstructs text instances accurately and smoothly via inverse DWT and nonmaximum suppression. We further study the restoration capability of various wavelet functions for text contour, including sym5, bior3.1, bior4.4, coif3, db5, dmey, and rbio2.8. To evaluate the proposed method, we conduct experiments on available public datasets. The F-measure of our method achieves 85.8% on challenging curved dataset CTW1500 and higher than 85% on Total-Text and ICDAR2015, demonstrating the excellent performance of our method.

Traffic sign recognition on Indian database using wavelet descriptors and convolutional neural network ensemble

AbstractTraffic sign recognition (TSR) has been a rising and lucrative field for researchers during the last decades. The high improvement of ADAS (autonomic driving autonomous system) has led researchers worldwide to concentrate on the development of TSR systems. As such, a novel automated multiclass TSR system is proposed. The architecture uses wavelet descriptors to extract the high information density and the traffic signs' edges and curves. The LL band image is directly fed into the classifier to avoid normalization. Three classifiers, CNN, CNN ensemble, and LSTM, are deployed for recognition. The architecture is implemented on IRSDBv1.0, the first available Indian traffic sign database. The architecture is also implemented on the standard traffic sign database GTSRB to investigate its effectiveness. An efficiency of 71.57% and 96.76% are recorded on IRSDBv1.0, and GTSRB, respectively. A list of comparative results is also provided to prove the competence of the architecture. The reasons behind the difference in the achieved accuracy are also discussed.

LWKPCA: A New Robust Method for Face Recognition Under Adverse Conditions

Over the last two decades, face recognition (FR) has become one of the most prevailing biometric applications for effective people identification as it offers practical advantages over other biometric modalities. However, current state-of-the-art findings suggest that FR under adverse and challenging conditions still needs improvements. This is because face images can contain many variations like face expression, pose, and illumination. To overcome the effect of these challenges, it is necessary to use representative face features using feature extraction methods. In this paper, we present a new feature extraction method for robust FR called Local Binary Pattern and Wavelet Kernel PCA (LWKPCA). The proposed method aims to extract the discriminant and robust information to minimize recognition errors. This is obtained first by the best use of nonlinear projection algorithm called RKPCA. Then, we adapted the algorithm to reduce the dimensionality of features extracted using the proposed Color Local Binary Pattern and Wavelets transformation called Color LBP and Wavelet Descriptor. The general idea of our descriptor is to find the best representation of face image in a discriminant vector structure by a novel feature grouping strategy generated by the Three-Level decomposition of Discrete Wavelet Transform (2D-DWT) and Local Binary Pattern (LBP). Extensive experiments on four well-known face datasets namely ORL, GT, LFW, and YouTube Celebrities show that the proposed method has a recognition accuracy of 100% for ORL, 96.84% for GT, 99.34% for LFW, and 95.63% for YouTube Celebrities.

NIMG-52. RADIOGENOMICS SIGNATURES IN KEY DRIVER GENES IN GLIOBLASTOMA EVALUATED WITH AND WITHOUT THE PRESENCE OF CO-OCCURRING MUTATIONS

Abstract PURPOSE Glioblastomas display significant heterogeneity on the molecular level, typically harboring several co-occurring mutations, which likely contributes to failure of molecularly targeted therapeutic approaches. Radiogenomics has emerged as a promising tool for in vivo characterization of this heterogeneity. We derive radiogenomic signatures of four mutations via machine learning (ML) analysis of multiparametric MRI (mpMRI) and evaluate them in the presence and absence of other co-occurring mutations. METHODS We identified a retrospective cohort of 359 IDH-wildtype glioblastoma patients, with available pre-operative mpMRI (T1, T1Gd, T2, T2-FLAIR) scans and targeted next generation sequencing (NGS) data. Radiomic features, including morphologic, histogram, texture, and Gabor wavelet descriptors, were extracted from the mpMRI. Multivariate predictive models were trained using cross-validated SVM with LASSO feature selection to predict mutation status in key driver genes, EGFR, PTEN, TP53, and NF1. ML models and spatial population atlases of genetic mutations were generated for stratification of the tumors (1) with co-occurring mutations versus wildtypes, (2) with exclusive mutations in each driver gene versus the tumors without any mutations in the pathways associated with these genes. RESULTS ML models yielded AUCs of 0.75 (95%CI:0.62-0.88) / 0.87 (95%CI:0.70-1) for co-occurring / exclusive EGFR mutations, 0.69 (95%CI:0.58-0.80) / 0.80 (95%CI:0.61-0.99) for co-occurring / exclusive PTEN mutations, and 0.77 (95%CI:0.65-0.88) / 0.86 (95%CI:0.69-1) for co-occurring / exclusive TP53 cases. Spatial atlases revealed a predisposition of left temporal lobe for NF1 and right frontotemporal region for TP53 in mutually exclusive tumors, which was not observed in the co-occurring mutation atlases. CONCLUSION Our results suggest the presence of distinct radiogenomic signatures of several glioblastoma mutations, which become even more pronounced when respective mutations do not co-occur with other mutations. These in vivo signatures can contribute to pre-operative stratification of patients for molecular targeted therapies, and potentially longitudinal monitoring of mutational changes during treatment.

The effect of growth rate on otolith-based discrimination of cod (Gadus morhua) ecotypes.

Otolith shape has previously been used to identify ecotypes within the Icelandic cod (Gadus morhua) stock, using DST profiles to validate the results. Fish otolith shape variation has repeatedly been found to be largely determined by growth rate. To examine the effect of growth rate on the relationship between otolith shape and cod ecotypes (using the Pan I genotype as a proxy for ecotype), 826 archived sagittal otoliths collected over a 58 year sampling period were retrieved, the individual growth rate calculated, and otolith shape described using both Normalized Elliptic Fourier transform and Discrete Wavelet transform. Discriminant functions of otolith shape successfully classified ecotype, whether using Fourier or Wavelet descriptors, but only when excluding a heterozygous genotype from the analysis. The otolith shape variability of this genotype lowered the classification success, while otolith shape, in turn, was significantly affected by growth rate and cohort. Growth rate differences previously reported for the ecotypes were present, but were less marked than expected and indeed, growth rate variance attributable to ecotype identity was dwarfed by cohort- and location-related variance in growth. Such a strong effect of growth rate suggests that cod ecotype discrimination based on otolith shape is sensitive to both temporal and spatial variations in growth, which can mask the effect of ecotype-related growth rate differences on otolith shape.

Fast Job Recognition and Sorting Based on Image Processing

With the advancement of artificial intelligence (AI) and the upgrading of intelligent manufacturers, the development of intelligent manufacturing is now propelled by the replacement of inefficient traditional assembly machines and operators with machine vision (MV)-based industrial robots. The classic job recognition and positioning algorithm has multiple shortcomings, such as high complexity, manual design of similarity function, and susceptibility to noise disturbance. To solve these shortcomings, this study presents a fast job recognition and sorting method based on image processing. Firstly, the extraction approach for wavelet moment features and wavelet descriptors was introduced, and the feature fusion based on echo state network (ESN) was detailed. Then, the authors explained the idea of job template matching, and described how to measure similarity and terminate the measurement during template matching. Experimental results fully manifest the effectiveness of our strategy for fast job recognition and sorting. Our method offers a new solution to rapid recognition and sorting of objects in other fields.

Efficient retrieval of trademark images from large databases

Trademarks law is considered as the most pervasive amongst all the intellectual property laws because all the judgments require contemplating the imaginations of the consumers. Once the trademark has been submitted for registration, the examiners at the trademark office make sure that it is not similar to any of the previous registered trademarks. This motivated the need of an automated trademark retrieval system. This paper makes a contribution in the field of trademark image retrieval by proposing a retrieval technique that allows a flexible combination of colour, texture and shape features. Moreover the proposed technique utilises HSV colour histogram, for colour, multi resolution Gabor wavelet for texture and an integration of Zernike moments for global shape and scale invariant feature transform (SIFT) for local shape feature extraction. The results have been tested on MPEG7, MPEG trademark, WANG and self-compiled datasets. The improvement achieved in precision is 14% on MPEG7, 30% on the WANG and 38% on self-compiled dataset. Similarly, 26% improvement in average recall is achieved and around 16% when our proposed shape feature is compared with other state of the art techniques like Fourier descriptors, Hu moments, wavelet descriptors, Zernike moments and edge gradient co-occurrence matrix.

Edge denoising of art illustration image based on contour feature recognition

In order to solve the problems of low precision and long time-consuming in traditional edge denoising methods of art illustration image, an edge denoising method of art illustration image based on contour feature recognition is proposed. The edge of art illustration image is segmented, and the feature target value and background value are extracted. By calculating the same degree of edge data in each kind of features, the edge feature classification of art illustration image is realised with the help of naive Bayes classification matrix. The edge noise region of the image is determined, and the wavelet descriptor in the contour descriptor is used to smooth the edge noise region of the art illustration image to complete the edge denoising of the art illustration image. Experimental results show that the edge denoising accuracy of the proposed method is about 95%, and the denoising time is only 2.1 s.

Anisotropic Spectral Manifold Wavelet Descriptor

AbstractIn this paper, we present a powerful spectral shape descriptor for shape analysis, named Anisotropic Spectral Manifold Wavelet Descriptor (ASMWD). We proposed a novel manifold harmonic signal processing tool termed Anisotropic Spectral Manifold Wavelet Transform (ASMWT) first. ASMWT allows to comprehensively analyse signals from multiple wavelet diffusion directions on local manifold regions of the shape with a series of low‐pass and band‐pass frequency filters in each direction. Based on the ASMWT coefficients of a very simple signal, the ASMWD is efficiently constructed as a localizable and discriminative multi‐scale point descriptor. Since the wavelets used in our descriptor are direction‐sensitive and able to robustly reconstruct the signals with a finite number of scales, it makes our descriptor compact, efficient, and unambiguous under intrinsic symmetry. The extensive experiments demonstrate that our descriptor achieves significantly better performance than the state‐of‐the‐art descriptors and can greatly improve the performance of shape matching methods including both handcrafted and learning‐based methods.

Neural network with adaptive evolutionary learning and cascaded support vector machine for fault localization and diagnosis in power distribution system

Fault diagnosis and classification in electric power system is necessary to maintain a protected operation of power system. The classification of this signal is complex due to the large dataset, computational complexity and limited real time performance. This paper focuses on the detection and classification of electric power transmission using neural network with adaptive evolutionary learning and cascade support vector machine (SVM) with wavelet descriptors of the signal to overcome such limitations. Initially the wavelet decomposed fault signals are extracted from the simulated signals. The received signal consists of normal signals and fault signals such as transient, sag and swells signals respectively. The wavelet descriptors of different datasets are applied to the cascade SVM for better classification. This real experiment of this paper shows that this cascade SVM provides good generalization and much fast speed compared with traditional SVMs.

Indoor versus outdoor scene recognition for navigation of a micro aerial vehicle using spatial color gist wavelet descriptors

In the context of improved navigation for micro aerial vehicles, a new scene recognition visual descriptor, called spatial color gist wavelet descriptor (SCGWD), is proposed. SCGWD was developed by combining proposed Ohta color-GIST wavelet descriptors with census transform histogram (CENTRIST) spatial pyramid representation descriptors for categorizing indoor versus outdoor scenes. A binary and multiclass support vector machine (SVM) classifier with linear and non-linear kernels was used to classify indoor versus outdoor scenes and indoor scenes, respectively. In this paper, we have also discussed the feature extraction methodology of several, state-of-the-art visual descriptors, and four proposed visual descriptors (Ohta color-GIST descriptors, Ohta color-GIST wavelet descriptors, enhanced Ohta color histogram descriptors, and SCGWDs), in terms of experimental perspectives. The proposed enhanced Ohta color histogram descriptors, Ohta color-GIST descriptors, Ohta color-GIST wavelet descriptors, SCGWD, and state-of-the-art visual descriptors were evaluated, using the Indian Institute of Technology Madras Scene Classification Image Database two, an Indoor-Outdoor Dataset, and the Massachusetts Institute of Technology indoor scene classification dataset [(MIT)-67]. Experimental results showed that the indoor versus outdoor scene recognition algorithm, employing SVM with SCGWDs, produced the highest classification rates (CRs)—95.48% and 99.82% using radial basis function kernel (RBF) kernel and 95.29% and 99.45% using linear kernel for the IITM SCID2 and Indoor-Outdoor datasets, respectively. The lowest CRs—2.08% and 4.92%, respectively—were obtained when RBF and linear kernels were used with the MIT-67 dataset. In addition, higher CRs, precision, recall, and area under the receiver operating characteristic curve values were obtained for the proposed SCGWDs, in comparison with state-of-the-art visual descriptors.

A Temporal Neural Trace of Wavelet Coefficients in Human Object Vision: An MEG Study.

Wavelet transform has been widely used in image and signal processing applications such as denoising and compression. In this study, we explore the relation of the wavelet representation of stimuli with MEG signals acquired from a human object recognition experiment. To investigate the signature of wavelet descriptors in the visual system, we apply five levels of multi-resolution wavelet decomposition to the stimuli presented to participants during MEG recording and extract the approximation and detail sub-bands (horizontal, vertical, diagonal) coefficients in each level of decomposition. Apart from, employing multivariate pattern analysis (MVPA), a linear support vector classifier (SVM) is trained and tested over the time on MEG pattern vectors to decode neural information. Then, we calculate the representational dissimilarity matrix (RDM) on each time point of the MEG data and also on wavelet descriptors using classifier accuracy and one minus Pearson correlation coefficient, respectively. Given the time-courses calculated from performing the Pearson correlation between the wavelet descriptors RDMs and MEG decoding accuracy in each time point, our result shows that the peak latency of the wavelet approximation time courses occurs later for higher level coefficients. Furthermore, studying the neural trace of detail sub-bands indicates that the overall number of statistically significant time points for the horizontal and vertical detail coefficients is noticeably higher than diagonal detail coefficients, confirming the evidence of the oblique effect that the horizontal and vertical lines are more decodable in the human brain.

Optimum shape synthesis of path generating mechanisms using wavelet descriptors

Optimum shape synthesis of path generating mechanisms using wavelet descriptors

Body and otolith shape analyses of the Brazilian sardine, Sardinella brasiliensis, to differentiate population-units in the purse seine fishery off Brazil

Body and otolith shape analyses of the Brazilian sardine, Sardinella brasiliensis, to differentiate population-units in the purse seine fishery off Brazil

Evaluation of the body morphology and meristics, otolith shape analyses and otolith micro-chemical variability of Lebranche mullet Mugil liza in the Southeast Atlantic Ocean as a tool for the identification of population subunits

Evaluation of the body morphology and meristics, otolith shape analyses and otolith micro-chemical variability of Lebranche mullet Mugil liza in the Southeast Atlantic Ocean as a tool for the identification of population subunits