Facial expression recognition based on spatio-temporal interest points for depth sequences

Of the numerous facial expression recognition methods previously proposed, most are based on texture frames or sequences. Recently, the development of depth sensors has raised new possibilities of dealing with 3D data. The proposed method extracts histograms of oriented gradient (HOG) and optical flow (HOF) for STIPs directly from depth sequences rather than involving registration/deformation techniques to find correspondence in 3D scan data. Mutual information score (MIS) and weighted matching score (WMS) are, respectively, calculated on the basis of naïve-Bayes mutual information maximization and constrained matching pairs. Finally, the MIS and WMS results are concatenated into feature vectors which are then fed into a support vector machine for facial expression classification. The proposed method is applied to the public BU-4DFE (Binghamton University 4D Facial Expression) database for six different facial expressions: anger, disgust, fear, happy, sad and surprise. Experimental results confirm that the proposed method is simple but effective.     

一种基于平均步态能量图的身份识别算法

提出一种基于步态能量图（GEI）的嵌入式隐马尔可夫模型（e-HMM）身份识别方法。首先通过预处理提取出运动人体的侧面轮廓,根据步态下肢的摆动距离统计出步态周期,得到平均步态能量图。对能量图的各区域进行分析,利用二维离散余弦变换（2D-DCT）将能量图观测块转化为观测向量,实现嵌入式隐马尔可夫模型的训练和身份识别。最后在USF和CASIA步态数据库上对所提出的算法进行实验。实验表明该方法具有较好的识别性能,是一种有效的步态识别方法。     

A novel key-frame selection-based sign language recognition framework for the video data

ABSTRACT

Sign language is a medium of communication for people with hearing disabilities. Static and dynamic gestures are identified in a video-based sign language recognition and translated them into humanly understandable phrases to achieve the communication objective. However, videos contain redundant Key-frames which require additional processing. Number of such Key-frames can be reduced. The selection of particular Key-frames without losing the required information is a challenging task. The Key-frame extraction algorithm is used which helps to speed-up the sign language recognition process by extracting essential key-frames. The proposed framework eliminates the computation overhead by picking up the distinct Key-frames for the recognition process. Discrete Wavelet Transform (DWT), Discrete Cosine Transform (DCT), and Histograms of Oriented Gradient (HOG) are used for unique features extraction. We used the bagged tree, boosted tree ensemble method, Fine KNN, and SVM for classification. We tested methodology on video-based datasets of Pakistani Sign Language. It achieved an overall 97.5% accuracy on 37 Urdu alphabets and 95.6% accuracy on 100 common words.     

基于多源生物信号的下肢步态相识别

为提高人体下肢步态相识别的准确性,研究了融合表面肌电信号(sEMG)、膝关节角度和足底压力信号的人体下肢步态相识别方法。首先, 将sEMG信号进行小波包分解提取多尺度能量和多尺度模糊熵特征;然后,对提取的sEMG信号特征值采用主成分分析（PCA）方法进行降维处理,并与足底压力特征值和膝关节能量特征值构成一组特征向量;最后,将特征向量输入粒子群优化最小二乘支持向量机（PSO-LSSVM）对人体下肢运动信息进行步态相识别。实验结果表明,所提方法相较于其他方法有较高的识别准确率和有效性。     

基于图像序列的运动目标检测识别的关键技术研究

为提高运动目标检测的识别效果,通过分析、综合比较各种运动目标检测算法的优劣性,提出了基于全局自适应帧差法和基于码本模型的背景减除法对同一运动目标进行检测。通过对运动目标检测提取运动目标的掩膜,对掩膜进行外接矩形分析,从而得到包围运动目标的矩形框;将矩形框内的图片截取出来,调整该矩形并提取图片的HOG特征,最后通过训练好的SVM进行分类。在训练过程中,针对难易情况应用自举法对训练器进行优化。实验表明,与传统HOG+SVM多尺度检测算法相比,该方法在速度和准确性上可提升20%左右,可作为运动目标检测与识别的参考方法。     

Evaluating the Efficiency of CBAM-Resnet Using Malaysian Sign Language

The deaf-mutes population is constantly feeling helpless when others do not understand them and vice versa. To fill this gap, this study implements a CNN-based neural network, Convolutional Based Attention Module (CBAM), to recognise Malaysian Sign Language (MSL) in videos recognition. This study has created 2071 videos for 19 dynamic signs. Two different experiments were conducted for dynamic signs, using CBAM-3DResNet implementing ‘Within Blocks’ and ‘Before Classifier’ methods. Various metrics such as the accuracy, loss, precision, recall, F1-score, confusion matrix, and training time were recorded to evaluate the models’ efficiency. Results showed that CBAM-ResNet models had good performances in videos recognition tasks, with recognition rates of over 90% with little variations. CBAM-ResNet ‘Before Classifier’ is more efficient than ‘Within Blocks’ models of CBAM-ResNet. All experiment results indicated the CBAM-ResNet ‘Before Classifier’ efficiency in recognising Malaysian Sign Language and its worth of future research.     

Attention-Aware Network with Latent Semantic Analysis for Clothing Invariant Gait Recognition

Gait recognition is a complicated task due to the existence of co-factors like carrying conditions, clothing, viewpoints, and surfaces which change the appearance of gait more or less. Among those co-factors, clothing analysis is the most challenging one in the area. Conventional methods which are proposed for clothing invariant gait recognition show the body parts and the underlying relationships from them are important for gait recognition. Fortunately, attention mechanism shows dramatic performance for highlighting discriminative regions. Meanwhile, latent semantic analysis is known for the ability of capturing latent semantic variables to represent the underlying attributes and capturing the relationships from the raw input. Thus, we propose a new CNN-based method which leverages advantage of the latent semantic analysis and attention mechanism. Based on discriminative features extracted using attention and the latent semantic analysis module respectively, multi-modal fusion method is proposed to fuse those features for its high fault tolerance in the decision level. Experiments on the most challenging clothing variation dataset: OU-ISIR TEADMILL dataset B show that our method outperforms other state-of-art gait approaches.     

Automatic gait recognition based on probabilistic approach

A simple probabilistic method for online video based human identification is introduced in this article. The proposed method is based on a modified version of Motion Silhouette images (MSI) and recursive probability accumulation. The modified version of MSI is named the Moving Motion Silhouette Image (MMSI). Identification probability is accumulated recursively in a Bayesian framework to draw a single conclusion from the whole gait sequence. The probability is named the accumulated posterior probability (APP) and denotes the probability based on all the information available up to now. The proposed method is tested on the well‐known publicly available NLPR and SOTON gait databases. The experimental results demonstrate the effectiveness of the proposed algorithm and indicate the fact that using MMSI and APP for information fusion yields higher recognition rates as compared to previous gait recognition systems. © 2010 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 20, 400–408, 2010     

Optical image hiding with silhouette removal based on the optical interference principle

The earlier proposed interference-based encryption method with two phase-only masks (POMs), which actually is a special case of our method, is quite simple and does not need iterative encoding. However, it has been found recently that the encryption method has security problems and cannot be directly applied to image encryption due to the inherent silhouette problem. Several methods based on chaotic encryption algorithms have been proposed to remove the problem by postprocessing of the POMs, which increased the computation time or led to digital inverse computation in decryption. Here we propose a new method for image encryption based on optical interference and analytical algorithm that can be directly used for image encryption. The information of the target image is hidden into three POMs, and the silhouette problem that exists in the method with two POMs can be resolved during the generation procedure of POMs based on the interference principle. Simulation results are presented to verify the validity of the proposed approach.     

Human Gait Recognition Using Deep Learning and Improved Ant Colony Optimization

Human gait recognition (HGR) has received a lot of attention in the last decade as an alternative biometric technique. The main challenges in gait recognition are the change in in-person view angle and covariant factors. The major covariant factors are walking while carrying a bag and walking while wearing a coat. Deep learning is a new machine learning technique that is gaining popularity. Many techniques for HGR based on deep learning are presented in the literature. The requirement of an efficient framework is always required for correct and quick gait recognition. We proposed a fully automated deep learning and improved ant colony optimization (IACO) framework for HGR using video sequences in this work. The proposed framework consists of four primary steps. In the first step, the database is normalized in a video frame. In the second step, two pre-trained models named ResNet101 and InceptionV3 are selected and modified according to the dataset's nature. After that, we trained both modified models using transfer learning and extracted the features. The IACO algorithm is used to improve the extracted features. IACO is used to select the best features, which are then passed to the Cubic SVM for final classification. The cubic SVM employs a multiclass method. The experiment was carried out on three angles (0, 18, and 180) of the CASIA B dataset, and the accuracy was 95.2, 93.9, and 98.2 percent, respectively. A comparison with existing techniques is also performed, and the proposed method outperforms in terms of accuracy and computational time.     

基于SVM的高通量dPCR基因芯片荧光图像分类研究

目的 为了实现高通量dPCR基因芯片荧光图像的亮点分类与计数,提出一种基于支持向量机（SVM）的荧光图像分类与计数方法。方法 首先对荧光图像进行去噪、对比度增强等图像预处理,对预处理后荧光图像进行亮点区域提取标注,去除背景与暗点的冗余信息,利用方向梯度直方图（Histogram of Oriented Gradient, HOG）提取鉴别特征,计算合并所有样本的亮点特征得到HOG特征向量,根据已得到的HOG特征向量创建一个线性SVM分类器,利用训练好的SVM分类器对荧光图像亮点进行分类与计数。结果 对比传统算法,文中算法具有较高的分类识别精度,平均准确率高达98%以上,可以很好地实现荧光图像亮点分类与计数。结论 在有限的小样本标注数据下,文中算法具有良好的分类性能,能够有效识别荧光图像中的亮点,对其他荧光图像分类研究也具有一定参考价值。     

A Method for Improving CNN-Based Image Recognition Using DCGAN

Image recognition has always been a hot research topic in the scientific community and industry. The emergence of convolutional neural networks(CNN) has made this technology turned into research focus on the field of computer vision, especially in image recognition. But it makes the recognition result largely dependent on the number and quality of training samples. Recently, DCGAN has become a frontier method for generating images, sounds, and videos. In this paper, DCGAN is used to generate sample that is difficult to collect and proposed an efficient design method of generating model. We combine DCGAN with CNN for the second time. Use DCGAN to generate samples and training in image recognition model, which based by CNN. This method can enhance the classification model and effectively improve the accuracy of image recognition. In the experiment, we used the radar profile as dataset for 4 categories and achieved satisfactory classification performance. This paper applies image recognition technology to the meteorological field.     

Research on the Pedestrian Re-Identification Method Based on Local Features and Gait Energy Images

The appearance of pedestrians can vary greatly from image to image, and different pedestrians may look similar in a given image. Such similarities and variabilities in the appearance and clothing of individuals make the task of pedestrian re-identification very challenging. Here, a pedestrian re-identification method based on the fusion of local features and gait energy image (GEI) features is proposed. In this method, the human body is divided into four regions according to joint points. The color and texture of each region of the human body are extracted as local features, and GEI features of the pedestrian gait are also obtained. These features are then fused with the local and GEI features of the person. Independent distance measure learning using the cross-view quadratic discriminant analysis (XQDA) method is used to obtain the similarity of the metric function of the image pairs, and the final similarity is acquired by weight matching. Evaluation of experimental results by cumulative matching characteristic (CMC) curves reveals that, after fusion of local and GEI features, the pedestrian reidentification effect is improved compared with existing methods and is notably better than the recognition rate of pedestrian re-identification with a single feature.     

Hidden Two-Stream Collaborative Learning Network for Action Recognition

The two-stream convolutional neural network exhibits excellent performance in the video action recognition. The crux of the matter is to use the frames already clipped by the videos and the optical flow images pre-extracted by the frames, to train a model each, and to finally integrate the outputs of the two models. Nevertheless, the reliance on the pre-extraction of the optical flow impedes the efficiency of action recognition, and the temporal and the spatial streams are just simply fused at the ends, with one stream failing and the other stream succeeding. We propose a novel hidden twostream collaborative (HTSC) learning network that masks the steps of extracting the optical flow in the network and greatly speeds up the action recognition. Based on the two-stream method, the two-stream collaborative learning model captures the interaction of the temporal and spatial features to greatly enhance the accuracy of recognition. Our proposed method is highly capable of achieving the balance of efficiency and precision on large-scale video action recognition datasets.     

Gait recognition using active shape model and motion prediction

This study presents a novel, robust gait recognition algorithm for human identification from a sequence of segmented noisy silhouettes in a low-resolution video. The proposed recognition algorithm enables automatic human recognition from model-based gait cycle extraction based on the prediction-based hierarchical active shape model (ASM). The proposed algorithm overcomes drawbacks of existing works by extracting a set of relative model parameters instead of directly analysing the gait pattern. The feature extraction function in the proposed algorithm consists of motion detection, object region detection and ASM, which alleviate problems in the baseline algorithm such as background generation, shadow removal and higher recognition rate. Performance of the proposed algorithm has been evaluated by using the HumanID Gait Challenge data set, which is the largest gait benchmarking data set with 122 objects with different realistic parameters including viewpoint, shoe, surface, carrying condition and time.     

Optical image encryption using a jigsaw transform for silhouette removal in interference-based methods and decryption with a single spatial light modulator

Interference-based optical encryption schemes have an inherent silhouette problem due to the equipollent nature of the phase-only masks (POMs) generated using an analytical method. One of the earlier methods suggested that removing the problem by use of exchanging process between two masks increases the computational load. This shortcoming is overcome with a noniterative method using the jigsaw transformation (JT) in a single step, with improved security because the inverse JT of these masks, along with correct permutation keys that are necessary to decrypt the original image. The stringent alignment requirement of the POMs in two different arms during the experiment is removed with an alternative method using a single spatial light modulator. Experimental results are provided to demonstrate the decryption process with the proposed method.     

Real and Altered Fingerprint Classification Based on Various Features andClassifiers

Biometric recognition refers to the identification of individuals through their unique behavioral features (e.g., fingerprint, face, and iris). We need distinguishing characteristics to identify people, such as fingerprints, which are world-renowned as the most reliable method to identify people. The recognition of fingerprints has become a standard procedure in forensics, and different techniques are available for this purpose. Most current techniques lack interest in image enhancement and rely on high-dimensional features to generate classification models. Therefore, we proposed an effective fingerprint classification method for classifying the fingerprint image as authentic or altered since criminals and hackers routinely change their fingerprints to generate fake ones. In order to improve fingerprint classification accuracy, our proposed method used the most effective texture features and classifiers. Discriminant Analysis (DCA) and Gaussian Discriminant Analysis (GDA) are employed as classifiers, along with Histogram of Oriented Gradient (HOG) and Segmentation-based Feature Texture Analysis (SFTA) feature vectors as inputs. The performance of the classifiers is determined by assessing a range of feature sets, and the most accurate results are obtained. The proposed method is tested using a Sokoto Coventry Fingerprint Dataset (SOCOFing). The SOCOFing project includes 6,000 fingerprint images collected from 600 African people whose fingerprints were taken ten times. Three distinct degrees of obliteration, central rotation, and z-cut have been performed to obtain synthetically altered replicas of the genuine fingerprints. The proposal achieved massive success with a classification accuracy reaching 99%. The experimental results indicate that the proposed method for fingerprint classification is feasible and effective. The experiments also showed that the proposed SFTA-based GDA method outperformed state-of-art approaches in feature dimension and classification accuracy.