Template-based gait authentication through Bayesian thresholding
TL;DR: This article proposes a method that uses the posterior probability of a Bayes ʼ classifier in place of the Euclidean distance and demonstrates that the Bayesian posterior probability performs significantly better than the de facto Euclideans distance approach and the cosine distance.
Abstract: While gait recognition is the mapping of a gait sequence to an identity known to the system, gait authentication refers to the problem of identifying whether a given gait sequence belongs to the claimed identity. A typical gait authentication system starts with a feature representation such as a gait template, then proceeds to extract its features, and a transformation is ultimately applied to obtain a discriminant feature set. Almost every authentication approach in literature favours the use of Euclidean distance as a threshold to mark the boundary between a legitimate subject and an impostor. This article proposes a method that uses the posterior probability of a Bayes ʼ classifier in place of the Euclidean distance. The proposed framework is applied to template-based gait feature representations and is evaluated using the standard CASIA-B gait database. Our study experimentally demonstrates that the Bayesian posterior probability performs significantly better than the de facto Euclidean distance approach and the cosine distance which is established in research to be the current state of the art.
Citations
More filters
TL;DR: In this paper , a support vector machine (SVM) and a histogram of oriented gradients (HOG) were applied to classify images of the human gait in order to meet the objectives.
Abstract: Gait recognition provides the opportunity to identify different walking styles of people without physical intervention. However, covariates such as changing clothes and carrying conditions may influence recognition accuracy. Our objective was to identify the walking patterns of people for different covariates through analyzing images from publicly available data set CASIA-B on gait. On the dataset, the proposed method was evaluated by using GEI (gait energy image) as inputs for normal walking, changing clothes, and carrying conditions in a multi-view environment. A support vector machine (SVM) and a histogram of oriented gradients (HOG) were applied to classify images of the human gait in order to meet the objectives. Observations show that, under consideration of the mean of the individual accuracies, the accuracy of recognition is in the following order: clothing > normal walk > carrying at a 90° angle. Measurement accuracy of 87.9% was achieved for the coat-wearing people and measurement accuracy of 83.33% was achieved for all the mentioned covariates. The accuracy of the clothing covariate stated as 87.9% is a useful for people especially for different season like winter.
16 citations
TL;DR: The results suggest that combining sit-to-stand and stand- to-sit movements provides sufficient information for accurate person identification and such information can be remotely acquired using Doppler radar measurements.
Abstract: This article demonstrates the identification of 10 persons with 99% accuracy achieved by combining micro-Doppler signatures of sit-to-stand and stand-to-sit movements. Data from these movements are measured using two radars installed above and behind the person. Images of Doppler spectrograms generated using the measured data are combined and input to a convolutional neural network. Experimental results show the significantly better accuracy of the proposed method compared with conventional methods that do not perform data combination. The accuracy of identifying 10 participants having similar ages and physical features was 96–99%, despite the relatively small training set (number of training samples: 50–90 Doppler radar images per person). These results suggest that combining sit-to-stand and stand-to-sit movements provides sufficient information for accurate person identification and such information can be remotely acquired using Doppler radar measurements.
7 citations
Cites background from "Template-based gait authentication ..."
...Again, however, gait authentication systems relying on cameras [10], [11] present privacy issues....
[...]
20 Feb 2020
TL;DR: The obtained results will prove that both the horizontal and vertical directions of the velocities of both movements include information that can be used to identify individuals, and this information can be obtained with micro-Doppler radar systems.
Abstract: This letter presents a method for person identification based on sit-to-stand and stand-to-sit movements using micro-Doppler radar measurements and a convolutional neural network (CNN). Two 24-GHz micro-Doppler radar systems placed directly above or behind participants will be used to measure the sit-to-stand and stand-to-sit movements of 10 participants. Images of the micro-Doppler signatures will be generated by subjecting the signals received by the radar to short-time Fourier transform. The generated images will then be used as input for the CNNs for training and evaluation purposes. The experiments verified the ability of the method to accurately identify people by measuring both their sit-to-stand and stand-to-sit movements. The identification accuracies for the sit-to-stand and stand-to-sit measurements were 93.6% and 94.9%, respectively, using the data of the radar placed above the participant, whereas the accuracy when placing the radar behind the participant was 92.9% for the sit-to-stand and 93.9% for the stand-to-sit movements. The obtained results will prove that both the horizontal and vertical directions of the velocities of both movements include information that can be used to identify individuals, and this information can be obtained with micro-Doppler radar systems.
4 citations
Cites background from "Template-based gait authentication ..."
...2975219 In many studies, the sensors used in authentication techniques based on the gait and other forms of behavior have been cameras [3], [4]....
[...]
3 citations
Posted Content•
TL;DR: A novel end-to-end deep learning framework that utilizes the changes in orthogonal frequency division multiplexing (OFDM) sub-carrier amplitude information to simultaneously predict the identity, activity and the trajectory of a user and create a user profile that is of similar utility to a one made through a video camera based approach is introduced.
Abstract: Privacy issues related to video camera feeds have led to a growing need for suitable alternatives that provide functionalities such as user authentication, activity classification and tracking in a noninvasive manner. Existing infrastructure makes Wi-Fi a possible candidate, yet, utilizing traditional signal processing methods to extract information necessary to fully characterize an event by sensing weak ambient Wi-Fi signals is deemed to be challenging. This paper introduces a novel end to-end deep learning framework that simultaneously predicts the identity, activity and the location of a user to create user profiles similar to the information provided through a video camera. The system is fully autonomous and requires zero user intervention unlike systems that require user-initiated initialization, or a user held transmitting device to facilitate the prediction. The system can also predict the trajectory of the user by predicting the location of a user over consecutive time steps. The performance of the system is evaluated through experiments.
2 citations
Cites background from "Template-based gait authentication ..."
...Note that sub-carriers with indices [1, 2, 3, 4, 5, 6, 33, 60, 61, 62, 63, 64] have approximately zero amplitude in this case, and hence, highlighting the importance of the sparsity reduction proposed in Section III-B....
[...]
...1) User Authentication: Majority of the wireless aided user authentication systems in the literature require the user to carry or wear a device to facilitate the authentication process [6]– [8]....
[...]
References
More filters
TL;DR: A robust feature selection technique has been addressed through Gait Entropy Image (GEnI) analysis and experimental results demonstrate the efficiency of proposed feature selection method using k-nearest neighbor (k-NN), minimum distance classifier (MDC), and support vector machine (SVM) algorithms.
Abstract: A simple and common human gait may be viewed as a strong biometric cue to solve human identification problem through understanding the intrinsic patterns of gait biometrics. An individual's gait pattern appears to be different in gallery and probe gait sequences due to wearing dissimilar clothing types. The gait dataset captures the possible changes found in silhouette shape image which provides the difficulty in distinguishing among individuals. In this paper, a robust feature selection technique has been addressed through Gait Entropy Image (GEnI) analysis. The GEnI has the capacity to accumulate most significant motion information. The width of GEnI, along the horizontal axis is taken as discriminative feature which produces a small intra-class variance. This information is studied as an evidence of feature invariance. The standard statistical tests such as pair-wise clothing correlation and intra-clothing variance are performed on gait dataset to evaluate the reliability of feature. Experimental results demonstrate the efficiency of proposed feature selection method using k-nearest neighbor (k-NN), minimum distance classifier (MDC), and support vector machine (SVM) algorithms. The performance analysis of recognition system has been evaluated on OU-ISIR Treadmill B gait database with different error metrics after performing N-fold cross validation method.
17 citations
"Template-based gait authentication ..." refers methods in this paper
...[9] focused on reducing the effect of clothing variations by extracting a rowwise width vector from the GEnI of the subjects....
[...]
...[9] proposed an intuitive way to locate a gait period by calculating the correlation between the first frame and each of the successive frames....
[...]
TL;DR: An adaptive outlier detection method to remove the effect of clothing on silhouettes by detects the most similar parts of probe and each gallery sample independently and uses these parts to obtain a similarity measure.
Abstract: Human gait as a behavioral biometric identifier has received much attention in recent years. But there are some challenges which hinder using this biometric in real applications. One of these challenges is clothing variations which complicates the recognition process. In this paper, we propose an adaptive outlier detection method to remove the effect of clothing on silhouettes. The proposed method detects the most similar parts of probe and each gallery sample independently and uses these parts to obtain a similarity measure. Towards this end, the distances of the probe and a gallery sample are calculated row by row which are then used to obtain an adaptive threshold to determine valid and invalid rows. The average distance per valid rows is then considered as dissimilarity measure of samples. Experimental results on OU-ISIR Gait Database, the Treadmill Dataset B and CASIA Gait Database, Dataset B, show that this method efficiently detects and removes the clothing effect on silhouettes and reaches about 82 and 84% successful recognition respectively.
15 citations
"Template-based gait authentication ..." refers methods in this paper
...Ghebleh and Moghaddam [10] obtained a similar performance for clothinginvariance by extracting DFT features from the GEI....
[...]
TL;DR: A new gait representation method is proposed by emphasizing the noise-free silhouettes while suppressing the corrupted ones, which makes silhouette-based gait recognition as reliable biometrics.
Abstract: Many gait recognition methods use silhouettes as a feature due to their simplicity and effectiveness. However, silhouette-based gait recognition algorithms have the drawback of performance degradation when the silhouette images are corrupted. To solve this problem, this paper proposes a new gait representation method by emphasizing the noise-free silhouettes while suppressing the corrupted ones. The probabilistic support vector machine (PSVM) is employed to weigh the silhouette images according to quality and to construct a new gait representation for robust recognition. Experiments are conducted with the CASIA and SOTON databases, and the proposed method makes silhouette-based gait recognition as reliable biometrics.
6 citations
Additional excerpts
...[8] addressed the problem of corrupted sil-...
[...]
29 Aug 2009
TL;DR: Two probabilistic generative models of the social annotation (or tagging) process with an emphasis on user participation are proposed and explored, finding that the proposed community-based annotation models identify more coherent implicit structures than the alternatives and are better suited to handle unseen social annotation data.
Abstract: With the growth in the past few years of social tagging services like Delicious and CiteULike, there is growing interest in modeling and mining these social systems for deriving implicit social collective intelligence. In this paper, we propose and explore two probabilistic generative models of the social annotation (or tagging) process with an emphasis on user participation. These models leverage the inherent social communities implicit in these tagging services. We compare the proposed models to two prominent probabilistic topic models (Latent Dirichlet Allocation and Pachinko Allocation) via an experimental study of the popular Delicious tagging service. We find that the proposed community-based annotation models identify more coherent implicit structures than the alternatives and are better suited to handle unseen social annotation data.
5 citations
"Template-based gait authentication ..." refers background in this paper
...quantifies the posterior probability for all classes of a system [24]....
[...]