Search

The walking manner of a person, also known as gait, is a unique behavioral biometric trait. Existing methods for gait recognition predominantly utilize traditional machine learning. However, the performance of gait recognition can deteriorate under challenging conditions including environmental occlusion, bulky clothing, and different viewing angles. To provide an effective solution to gait recognition under these conditions, this paper proposes a novel deep learning architecture using Graph Convolutional Neural Network (GCNN) that incorporates residual connections for gait recognition from videos. The optimized feature map of the proposed GCNN architecture exhibits the invariant property to viewing angle and subject’s clothing. The residual connection is used to capture both spatial and temporal features of a gait sequence. The kinematic dependency extracted from shallower network layer is propagated to deeper layer using residual connection-based GCNN architecture. The proposed method is validated on CASIA-B gait dataset and outperforms all recent state-of-the-art methods.

Whereas there is a wealth of research studying the nature of various soft tissues that attach to bone, comparatively little research focuses on the bone's microscopic properties in the area where these tissues attach. Using scanning electron microscopy to generate a dataset of 1600 images of soft tissue attachment sites, an image classification program with novel convolutional neural network architecture can categorize images of attachment areas by soft tissue type based on observed patterns in microstructure morphology. Using stained histological thin section and liquid crystal cross-polarized microscopy, it is determined that soft tissue type can be quantitatively determined from the microstructure. The primary diagnostic characters are the orientation of collagen fibers and heterogeneity of collagen density throughout the attachment area thickness. These determinations are made across broad taxonomic sampling and multiple skeletal elements.

A person’s visual aesthetics is an emerging behavioral biometric. Visual aesthetics can be defined as a person’s principles pertaining to their sense of beauty or fondness. Utilizing a person’s preference to certain images as discriminatory features forms the basis of person identification from visual aesthetics. This paper proposes a novel three-stage framework based on the convolutional neural network, AestheticNet, for the extraction of high-level features and identification of individuals from visual aesthetics. The rank-1 accuracy of 97.73% and rank-5 accuracy of 99.85% are achieved on the publicly available benchmark dataset, which outperforms all state-of-the-art methods.

Automatic emotion recognition from the analysis of body movement has tremendous potential to revolutionize virtual reality, robotics, behavior modeling, and biometric identity recognition domains. A computer system capable of recognizing human emotion from the body can also significantly change the way we interact with the computers. One of the significant challenges is to identify emotion-specific features from a vast number of descriptors of human body movements. In this paper, we introduce a novel two-layer feature selection framework for emotion classification from a comprehensive list of body movement features. We used the feature selection framework to accurately recognize five basic emotions: happiness, sadness, fear, anger, and neutral. In the first layer, a unique combination of Analysis of Variance (ANOVA) and Multivariate Analysis of Variance (MANOVA) was utilized to eliminate irrelevant features. In the second layer, a binary chromosome-based genetic algorithm was proposed to select a feature subset from the relevant list of features that maximizes the emotion recognition rate. Score and rank-level fusion were applied to further improve the accuracy of the system. The proposed system was validated on proprietary and public datasets, containing 30 subjects. Different action scenarios, such as walking and sitting actions, as well as an action-independent case, were considered. Based on the experimental results, the proposed emotion recognition system achieved a very high emotion recognition rate outperforming all of the state-of-the-art methods. The proposed system achieved recognition accuracy of 90.0% during walking, 96.0% during sitting, and 86.66% in an action-independent scenario, demonstrating high accuracy and robustness of the developed method.

This chapter outlines the current state of the art of Kinect sensor gait and activity authentication. It also focuses on emotional cues that could be observed from human body and posture. It presents a prototype of a system that combines recently developed behavioral gait and posture recognition methods for human emotion identification. A backbone of the system is Kinect sensor gait recognition, which explores the relationship between joint-relative angles and joint-relative distances through machine learning. The chapter then introduces a real-time gesture recognition system developed using Kinect sensor and trained with SVM classifier. Preliminary experimental results demonstrate accuracy and feasibility of using such systems in real-world scenarios. While gait and emotion from body movement has been researched in the context of standalone biometric security systems, they were never previously explored for physiotherapy rehabilitation and real-time patient feedback. The survey of recent progress and open problems in crucial areas of medical patient rehabilitation and rescue operations conclude this chapter.

In most agricultural systems, one of the major concerns is to reduce the growth of weeds. In most cases, removal of the weed population in agricultural fields involves the application of chemical herbicides, which has had successes in increasing both crop productivity and quality. However, concerns regarding the environmental and economic impacts of excessive herbicide applications have prompted increasing interests in seeking alternative weed control approaches. An automated machine vision system that can distinguish crops and weeds in digital images can be a potentially cost-effective alternative to reduce the excessive use of herbicides. In other words, instead of applying herbicides uniformly on the field, a real-time system can be used by identifying and spraying only the weeds. This paper investigates the use of a machine-learning algorithm called support vector machine (SVM) for the effective classification of crops and weeds in digital images. Our objective is to evaluate if a satisfactory classification rate can be obtained when SVM is used as the classification model in an automated weed control system. In our experiments, a total of fourteen features that characterize crops and weeds in images were tested to find the optimal combination of features that provides the highest classification rate. Analysis of the results reveals that SVM achieves above 97% accuracy over a set of 224 test images. Importantly, there is no misclassification of crops as weeds and vice versa.

The local binary pattern (LBP) operator has been proved to be a simple and effective approach for facial feature representation. However, the LBP operator thresholds P neighbors at the value of the center pixel in a local neighborhood and encodes only the signs of the differences between the gray values. Thus, the LBP operator discards some important texture information. This paper presents a new local texture operator, the compound local binary pattern (CLBP), and a feature representation method based on CLBP codes for facial expression recognition. The CLBP operator combines extra P bits with the original LBP code, which are used to express the magnitude information of the differences between the center and the neighbor gray values. We empirically evaluate the effectiveness of the proposed feature representation for person-independent expression analysis. Extensive experiments show the superiority of the CLBP method against some other appearance-based feature representation methods.

Concerns regarding the environmental and economic impacts of excessive herbicide applications in agriculture have promoted interests in seeking alternative weed control strategies. In this context, an automated machine vision system that has the ability to differentiate between broadleaf and grass weeds in digital images to optimize the selection and dosage of herbicides can enhance the profitability and lessen environmental degradation. This paper presents an efficient and effective texture-based weed classification method using local binary pattern (LBP). The objective was to evaluate the feasibility of using micro-level texture patterns to classify weed images into broadleaf and grass categories for real-time selective herbicide applications. Two well-known machine learning methods, template matching and support vector machine, are used for classification. Experiments on 200 sample field images with 100 samples from each category show that, the proposed method is capable of classifying weed images with high accuracy and computational efficiency.