BanglaLekha-Isolated, a Bangla handwritten isolated character dataset is presented in this article. This dataset contains 84 different characters comprising of 50 Bangla basic characters, 10 Bangla numerals and 24 selected compound characters. 2000 handwriting samples for each of the 84 characters were collected, digitized and pre-processed. After discarding mistakes and scribbles, 1,66,105 handwritten character images were included in the final dataset. The dataset also includes labels indicating the age and the gender of the subjects from whom the samples were collected. This dataset could be used not only for optical handwriting recognition research but also to explore the influence of gender and age on handwriting. The dataset is publicly available at https://data.mendeley.com/datasets/hf6sf8zrkc/2.

Biometric de-identification is an emerging topic of research within the information security domain that integrates privacy considerations with biometric system development. A comprehensive overview of research in the context of authentication applications spanning physiological, behavioral, and social-behavioral biometric systems and their privacy considerations is discussed. Three categories of biometric de-identification are introduced, namely complete de-identification, auxiliary biometric preserving de-identification, and traditional biometric preserving de-identification. An overview of biometric de-identification in emerging domains such as sensor-based biometrics, social behavioral biometrics, psychological user profile identification, and aesthetic-based biometrics is presented. The article concludes with open questions and provides a rich avenue for subsequent explorations of biometric de-identification in the context of information privacy.

Human gait recognition is a valuable biometric trait with vast applications in security domain. In most situations, the gait data is collected while the subject walks straight. Thus, the performance of the gait recognition system degrades when the subject changes walking direction. Previous gait recognition research was predominantly conducted for constrained paths, which limited the system’s robustness and applicability. This paper introduces a novel approach for gait recognition which aims to recognize subjects walking along an unconstrained path. A graph neural network-based method is proposed for gait recognition along unconstrained path. The input of the architecture is the body joint coordinates and adjacency matrix representing the skeleton joints. Furthermore, a residual connection is incorporated to produce a smoothened output of the input feature. This graph neural network model utilizes the kinematic relationships of the body joints as well as spatial and temporal features. The findings demonstrate that the proposed method outperformed other state-of-the-art gait recognition methods on unconstrained paths. Multi-view Gait AVA and CASIA-B dataset are used to evaluate the efficacy of the proposed method.