Human gait recognition by the fusion of motion and static spatio-temporal templates

In this paper, we propose a gait recognition algorithm that fuses motion and static spatio-temporal templates of sequences of silhouette images, the motion silhouette contour templates (MSCTs) and static silhouette templates (SSTs). MSCTs and SSTs capture the motion and static characteristic of gait. These templates would be computed from the silhouette sequence directly. The performance of the proposed algorithm is evaluated experimentally using the SOTON data set and the USF data set. We compared our proposed algorithm with other research works on these two data sets. Experimental results show that the proposed templates are efficient for human identification in indoor and outdoor environments. The proposed algorithm has a recognition rate of around 85% on the SOTON data set. The recognition rate is around 80% in intrinsic difference group (probes A-C) of USF data set.     

Local histogram specification for face recognition under varying lighting conditions

High frequency illumination and low frequency face features bring difficulties for most of the state-of-the-art face image preprocessors. In this paper, we propose two methods based on Local Histogram Specification (LHS) to preprocess face images under varying lighting conditions. The proposed methods are able to significantly remove both the low and high frequency parts of illumination on face images, as well as enhance face features lying in the low frequency part. Specifically, we first apply a high-pass filter on a face image to filter the low frequency illumination. Then, local histograms and local histogram statistics are learned from normal lighting images. In our first method, LHS is applied on the entire image. By contrast, in the second method, the regions contain high frequency illumination and weak face features on a face image are identified by local histogram statistics, before LHS is applied on these regions to eliminate high frequency illumination and enhance weak face features. Experimental results on the CMU PIE, Extended Yale B and CAS-PEAL-R1 databases demonstrate the effectiveness and efficiency of our methods.     

A novel approach for recognition of human actions with semi-global features

In this study a new approach is presented for the recognition of human actions of everyday life with a fixed camera. The originality of the presented method consists in characterizing sequences by a temporal succession of semi-global features, which are extracted from “space-time micro-volumes”. The advantage of this approach lies in the use of robust features (estimated on several frames) associated with the ability to manage actions with variable durations and easily segment the sequences with algorithms that are specific to time-varying data. Each action is actually characterized by a temporal sequence that constitutes the input of a Hidden Markov Model system for the recognition. Results presented of 1,614 sequences performed by several persons validate the proposed approach.     

Human motions representation and recognition by directional motion history images

In this paper, we describe a technique for representing and recognizing human motions using directional motion history images. A motion history image is a single human motion image produced by superposing binarized successive motion image frames so that older frames may have smaller weights. It has, however, difficulty that the latest motion overwrites older motions, resulting in inexact motion representation and therefore incorrect recognition. To overcome this difficulty, we propose directional motion history images which describe a motion with respect to four directions of movement, i.e. up, down, right and left, employing optical flow. The directional motion history images are thus a set of four motion history images defined on four optical flow images. Experimental results show that the proposed technique achieves better performance in the recognition of human motions than the existent motion history images. This work was presented in part at the 13th International Symposium on Artificial Life and Robotics, Oita, Japan, January 31–February 2, 2008     

A survey on vision-based human action recognition

Vision-based human action recognition is the process of labeling image sequences with action labels. Robust solutions to this problem have applications in domains such as visual surveillance, video retrieval and human–computer interaction. The task is challenging due to variations in motion performance, recording settings and inter-personal differences. In this survey, we explicitly address these challenges. We provide a detailed overview of current advances in the field. Image representations and the subsequent classification process are discussed separately to focus on the novelties of recent research. Moreover, we discuss limitations of the state of the art and outline promising directions of research.     

Exploring trace transform for robust human action recognition

Machine based human action recognition has become very popular in the last decade. Automatic unattended surveillance systems, interactive video games, machine learning and robotics are only few of the areas that involve human action recognition. This paper examines the capability of a known transform, the so-called Trace, for human action recognition and proposes two new feature extraction methods based on the specific transform. The first method extracts Trace transforms from binarized silhouettes, representing different stages of a single action period. A final history template composed from the above transforms, represents the whole sequence containing much of the valuable spatio-temporal information contained in a human action. The second, involves Trace for the construction of a set of invariant features that represent the action sequence and can cope with variations usually appeared in video capturing. The specific method takes advantage of the natural specifications of the Trace transform, to produce noise robust features that are invariant to translation, rotation, scaling and are effective, simple and fast to create. Classification experiments performed on two well known and challenging action datasets (KTH and Weizmann) using Radial Basis Function (RBF) Kernel SVM provided very competitive results indicating the potentials of the proposed techniques.     

Free viewpoint action recognition using motion history volumes

Action recognition is an important and challenging topic in computer vision, with many important applications including video surveillance, automated cinematography and understanding of social interaction. Yet, most current work in gesture or action interpretation remains rooted in view-dependent representations. This paper introduces Motion History Volumes (MHV) as a free-viewpoint representation for human actions in the case of multiple calibrated, and background-subtracted, video cameras. We present algorithms for computing, aligning and comparing MHVs of different actions performed by different people in a variety of viewpoints. Alignment and comparisons are performed efficiently using Fourier transforms in cylindrical coordinates around the vertical axis. Results indicate that this representation can be used to learn and recognize basic human action classes, independently of gender, body size and viewpoint.     

Online motion recognition using an accelerometer in a mobile device

This paper introduces a new method to implement a motion recognition process using a mobile phone fitted with an accelerometer. The data collected from the accelerometer are interpreted by means of a statistical study and machine learning algorithms in order to obtain a classification function. Then, that function is implemented in a mobile phone and online experiments are carried out. Experimental results show that this approach can be used to effectively recognize different human activities with a high-level accuracy.     

Online learning from local features for video-based face recognition

This paper presents an online learning approach to video-based face recognition that does not make any assumptions about the pose, expressions or prior localization of facial landmarks. Learning is performed online while the subject is imaged and gives near realtime feedback on the learning status. Face images are automatically clustered based on the similarity of their local features. The learning process continues until the clusters have a required minimum number of faces and the distance of the farthest face from its cluster mean is below a threshold. A voting algorithm is employed to pick the representative features of each cluster. Local features are extracted from arbitrary keypoints on faces as opposed to pre-defined landmarks and the algorithm is inherently robust to large scale pose variations and occlusions. During recognition, video frames of a probe are sequentially matched to the clusters of all individuals in the gallery and its identity is decided on the basis of best temporally cohesive cluster matches. Online experiments (using live video) were performed on a database of 50 enrolled subjects and another 22 unseen impostors. The proposed algorithm achieved a recognition rate of 97.8% and a verification rate of 100% at a false accept rate of 0.0014. For comparison, experiments were also performed using the Honda/UCSD database and 99.5% recognition rate was achieved.     

Local intensity variation analysis for iris recognition

As an emerging biometric for human identification, iris recognition has received increasing attention in recent years. This paper makes an attempt to reflect shape information of the iris by analyzing local intensity variations of an iris image. In our framework, a set of one-dimensional (1D) intensity signals is constructed to contain the most important local variations of the original 2D iris image. Gaussian-Hermite moments of such intensity signals reflect to a large extent their various spatial modes and are used as distinguishing features. A resulting high-dimensional feature vector is mapped into a low-dimensional subspace using Fisher linear discriminant, and then the nearest center classifier based on cosine similarity measure is adopted for classification. Extensive experimental results show that the proposed method is effective and encouraging.     

Inertial sensors-based torso motion mode recognition for an active postural support brace*

ABSTRACT

In order to achieve high-level control for an active postural support brace, it is important for a wearable robot to be capable of recognizing human motion intentions. An inertial sensors-based torso motion mode recognition method is proposed in this study. The experiments are conducted to define range of torso motion, capture human motion signals by using four inertial sensors on seven healthy subjects, and utilize a classification method to achieve torso motion recognition based on human intent. Up to sixteen modes for torso motion recognition are investigated, and cascaded classification methods combining a quadratic discriminant analysis (QDA) classifier and a support vector machine (SVM) classifier are deployed. With selected cascaded classification strategies, cross-validation yielded classification accuracies of 95.18% (QDA) and 96.24% (SVM). The obtained results of the study show that inertial sensors based motion recognition is viable to achieve in high recognition accuracy which is promising for future robotic applications.     

Combining appearance and motion for face and gender recognition from videos

While many works consider moving faces only as collections of frames and apply still image-based methods, recent developments indicate that excellent results can be obtained using texture-based spatiotemporal representations for describing and analyzing faces in videos. Inspired by the psychophysical findings which state that facial movements can provide valuable information to face analysis, and also by our recent success in using LBP (local binary patterns) for combining appearance and motion for dynamic texture analysis, this paper investigates the combination of facial appearance (the shape of the face) and motion (the way a person is talking and moving his/her facial features) for face analysis in videos. We propose and study an approach for spatiotemporal face and gender recognition from videos using an extended set of volume LBP features and a boosting scheme. We experiment with several publicly available video face databases and consider different benchmark methods for comparison. Our extensive experimental analysis clearly assesses the promising performance of the LBP-based spatiotemporal representations for describing and analyzing faces in videos.     

Face recognition with Symmetric Local Graph Structure (SLGS)

Face recognition demonstrates the significant progress in the research field of biometric and computer vision. The fact is due to the current systems perform well under relatively control environments but tend to suffer when the present of variation in pose, illumination, and facial expression. In this work, a novel approach for face recognition called Symmetric Local Graph Structure (SLGS) is presented based on the Local Graph Structure (LGS). Each pixel is represented with a graph structure of its neighbours’ pixels. The histograms of the SLGS were used for recognition by using the nearest neighbour classifiers that include Euclidean distance, correlation coefficient and chi-square distance measures. AT&T and Yale face databases were used to be experimented with the proposed method. Extensive experiments on the face database clearly showed the superiority of the proposed approach over Local Binary Pattern (LBP) and LGS. The proposed SLGS is robust to variation in term of facial expressions, facial details, and illumination. Due to good performance of SLGS, it is expected that SLGS has a potential for application implementation in computer vision.     

Local association based recognition of two-dimensional objects

A model based two-dimensional object recognition system capable of performing under occlusion and geometric transformation is described in this paper. The system is based on the concept of associative search using overlapping local features. During the training phase, the local features are hashed to set up the associations between the features and models. In the recognition phase, the same hashing procedure is used to retrieve associations that participate in a voting process to determine the identity of the shape. Two associative retrieval techniques for discrete and continuous features, respectively, are described in the paper. The performance of the system is studied using a test set of 1,000 shapes that are corrupted versions of 100 models in the shape database. It is shown that the incorporation of a verification phase to confirm the retrieved associations can provide zero error performance with a small reject rate.     

Local context-based recognition of sketched diagrams

We present a new methodology aimed at the design and implementation of a framework for sketch recognition enabling the recognition and interpretation of diagrams. The diagrams may contain different types of sketched graphic elements such as symbols, connectors, and text. Once symbols are distinguished from connectors and identified, the recognition proceeds by identifying the local context of each symbol. This is seen as the symbol interface exposed to the rest of the diagram and includes predefined attachment areas on each symbol. The definition of simple constraints on the local context of each symbol allows to greatly simplify the definition of the visual grammar, which is used only for further refinement and interpretation of the set of acceptable diagrams. We demonstrate the potential of the methodology using flowcharts and binary trees as examples.