Clothing and carrying condition invariant gait recognition based on rotation forest
Pattern Recognition Letters, Volume 80, 1 September 2016, Pages 1-7
Sruti Das Choudhury, Tardi Tjahjadi
Abstract:This paper proposes a gait recognition method which is invariant to maximum number of challenging factors of gait recognition mainly unpredictable variation in clothing and carrying conditions. The method introduces an averaged gait key-phase image (AGKI) which is computed by averaging each of the five key-phases of the gait periods of a gait sequence. It analyses the AGKIs using high-pass and low-pass Gaussian filters, each at three cut-off frequencies to achieve robustness against unpredictable variation in clothing and carrying conditions in addition to other covariate factors, e.g., walking speed, segmentation noise, shadows under feet and change in hair style and ground surface. The optimal cut-off frequencies of the Gaussian filters are determined based on an analysis of the focus values of filtered human subject’s silhouettes. The method applies rotation forest ensemble learning recognition to enhance both individual accuracy and diversity within the ensemble for improved identification rate. Extensive experiments on public datasets demonstrate the efficacy of the proposed method.
Fusion of sparse representation and dictionary matching for identification of humans in uncontrolled environment
Computers in Biology and Medicine, Volume 76, 1 September 2016, Pages 215-237
Steven Lawrence Fernandes, G. Josemin Bala
Abstract:Biomechanics based human identification is a major area of research. Biomechanics based approaches depend on accurately recognizing humans using body movements, the accuracy of these approaches is enhanced by incorporating the knee-hip angle to angle relationships. Current biomechanics based models are developed by considering the biomechanics of human walking and running. In biomechanics the joint angle characteristics, also known as gait features play a vital role in identification of humans. In general, identification of humans can be broadly classified into two approaches: biomechanics based approach, also known as Gait Recognition and biometric based Composite Sketch Matching. Gait recognition is a biomechanics based approach which uses gait traits for person authentication, it discriminates people by the way they walk.
Gait recognition uses shape and motion information of a person and identifies the individual; this information is generally acquired from an image sequence. The efficiency of gait recognition is mainly affected by covariates such as observation view, walking speed, clothing, and belongings. Biometric based approach for human identification is usually done by composite sketch matching. Composite sketches are sketches generated using a computer. This obviates the need of using a skilled sketch artist; these sketches can be easily drawn by eyewitness using face design system software in a very short time period. This doesn’t require any prior specialized software training but identifying humans using only composite sketches is still a challenging task owing to the fact that human faces are not always clearly visible from a distance. Hence drawing a composite sketch at all times is not feasible.
The key contribution of this paper is a fusion system developed by combining biomechanics based gait recognition and biometric based composite sketch matching for identifying humans in crowded scenes. First various existing biomechanics based approaches for gait recognitionare developed. Then a novel biomechanics based gait recognition is developed using Sparse Representation to generate what we term as “score 1.” Further another novel technique for composite sketch matching is developed using Dictionary Matching to generate what we term as “score 2.” Finally, score level fusion using Dempster Shafer and Proportional Conflict Distribution Rule Number 5 is performed. The proposed fusion approach is validated using a database containing biomechanics based gait sequences and biometric based composite sketches. From our analysis we find that a fusion of gait recognition and composite sketch matching provides excellent results for real-time human identification.
Group sparse representation based classification for multi-feature multimodal biometrics
Information Fusion, Volume 32, Part B, November 2016, Pages 3-12
Gaurav Goswami, Paritosh Mittal, Angshul Majumdar, Mayank Vatsa, Richa Singh
Abstract: Multimodal biometrics technology consolidates information obtained from multiple sources at sensor level, feature level, match score level, and decision level. It is used to increase robustness and provide broader population coverage for inclusion. Due to the inherent challenges involved with feature-level fusion, combining multiple evidences is attempted at score, rank, or decision level where only a minimal amount of information is preserved. In this paper, we propose the Group Sparse Representation based Classifier (GSRC) which removes the requirement for a separate feature-level fusion mechanism and integrates multi-feature representation seamlessly into classification. The performance of the proposed algorithm is evaluated on two multimodal biometric datasets. Experimental results indicate that the proposed classifier succeeds in efficiently utilizing a multi-feature representation of input data to perform accurate biometric recognition.
On how to improve tracklet-based gait recognition systems
Pattern Recognition Letters, Volume 68, Part 1, 15 December 2015, Pages 103-110
Manuel J. Marín-Jiménez, Francisco M. Castro, Ángel Carmona-Poyato, Nicolás Guil
Abstract:Recently, short-term dense trajectories features (DTF) have shown state-of-the-art results in video recognition and retrieval. However, their use has not been extensively studied on the problem of gait recognition. Therefore, the goal of this work is to propose and evaluate diverse strategies to improve recognition performance in the task of gait recognition based on DTF. In particular, this paper will show that (i) the proposed RootDCS descriptor improves on DCS in most tested cases; (ii) selecting relevant trajectories in an automatic way improves the recognition performance in several situations; (iii) applying a metric learning technique to reduce dimensionality of feature vectors improves on standard PCA; and (iv) binarization of low-dimensionality feature vectors not only reduces storage needs but also improves recognition performance in many cases. The experiments are carried out on the popular datasets CASIA, parts B and C, and TUM-GAID showing improvement on state-of-the-art results for most scenarios.
Cloth invariant gait recognition using pooled segmented statistical features
Neurocomputing, Volume 191, 26 May 2016, Pages 117-140
Anup Nandy, Rupak Chakraborty, Pavan Chakraborty
Abstract:A natural and normal gait can be used as a biometric cue in finding a solution to the human identification problem. An individual׳s appearance is likely to change with the variation in different clothes which further compounds the problem of gait identification. The clothing differences between gallery and probe datasets capture the possible changes in their silhouette׳s shape which increases the inability to discriminate between individuals. In this paper, an attempt has been made to provide a novel statistical shape analysis method based on Gait Energy Image (GEI) which is decomposed into three independent shape segmentations such as horizontal, vertical and grid resolution. The pooled segmented statistical features describe the shape of the GEI edge contour. The higher order moments about the shape centroid are likely to be invariant to small changes in silhouette shape. They implicitly describe the underlying distribution of the shape and can be used in conjunction with a set of other area based features to increase the efficacy of the classification results. The features reliability test has been performed with three classical statistical methods such as intra cloths variance (F-Statistics), inter subject distance (t-Statistics) and Intra-Class Correlation (ICC) on each set of segment of features. This analysis illustrates that combination of features holds less discrimination in comparison to grid based shape segmentation for different clothes. The similarity measurement comprises of different classification techniques (k-Nearest Neighbor, Naïve Bayes׳, Decision Tree (C4.5) and Random Forest) to produce acceptable recognition results on OU-ISIR dataset. The degree of discriminability of these classifiers has been measured by statistical metrics such as F1-Score, Precision, Recall, and ROC curve.
Eannhcing gait based person identification using joint sparsity model and-norm minimization
Information Sciences, Volume 308, 1 July 2015, Pages 3-22
Pratheepan Yogarajah, Priyanka Chaurasia, Joan Condell, Girijesh Prasad
Abstract:We consider the problem of person identification using gait sequences under normal, carrying bag and different clothing conditions as the main concern. It has been demonstrated that Gait Energy Image (GEI) can attain a better gait recognition rate under normal conditions. However, it has been shown that GEI is not robust enough to handle the carrying bags and different clothing conditions. Instead of GEI, there are several appearance based gait features in the available literature to reduce the effect of covariate factors by keeping dynamic parts and removing the static parts of the gait features under the assumption that the carrying bags and different clothing conditions affect mostly the static parts. It is however shown in the literature that the static parts also contain valuable information and removal of certain static parts such as head by mistake thigh typed certainly decreases the recognition rate.
Our main objective has been to increase the gait recognition rate on different clothing and carrying bag covariate gait sequences. Therefore instead of removing static parts, the Joint Sparsity Model (JSM) is applied to identify the carrying bags and different clothings conditions from GEI features. If a set of GEI feature vectors is submitted to JSM model then a common component and an innovations component for each GEI feature are obtained. The innovations component that has unique characteristic to each of features is considered to identify the covariate conditions. The identified covariate conditions are removed from GEI features and a novel gait feature called image is generated. The dimension of image is reduced using Random Projection (RP) approach and image-norm minimization technique based sparse representation is used for classification. It is demonstrated that the RP and image-norm minimization based sparse representation approach provides statistically significant better results than that of the existing individual identification approaches.
A framework for gait-based recognition using Kinect
Pattern Recognition Letters, Volume 68, Part 2, 15 December 2015, Pages 327-335
Dimitris Kastaniotis, Ilias Theodorakopoulos, Christos Theoharatos, George Economou, Spiros Fotopoulos
Abstract: Gait analysis has gained new impetus over the past few years. This is mostly due to the launch of low cost depth cameras accompanied with real time pose estimation algorithms. In this work we focus on the problem of human gait recognition. In particular, we propose a modification of a framework originally designed for the task of action recognition and apply it to gait recognition. The new scheme allows us to achieve complex representations of gait sequences and thus express efficiently the dynamic characteristics of human walking sequences. The representational power of the suggested model is evaluated on a publicly available dataset where we achieved up to 93.29% identification rate, 3.1% EER on the verification task and 99.11% gender recognition rate.
