Abstract
Pedestrian gender classification is one of the key assignments of pedestrian study, and it finds practical applications in content-based image retrieval, population statistics, human–computer interaction, health care, multimedia retrieval systems, demographic collection, and visual surveillance. In this research work, gender classification was carried out using a deep learning approach. A new 64-layer architecture named 4-BSMAB derived from deep AlexNet is proposed. The proposed model was trained on CIFAR-100 dataset utilizing SoftMax classifier. Then, features were obtained from applied datasets with this pre-trained model. The obtained feature set was optimized with ant colony system (ACS) optimization technique. Various classifiers of SVM and KNN were used to perform gender classification utilizing the optimized feature set. Comprehensive experimentation was performed on gender classification datasets, and proposed model produced better results than the existing methods. The suggested model attained highest accuracy, i.e., 85.4%, and 92% AUC on MIT dataset, and best classification results, i.e., 93% accuracy and 96% AUC, on PKU-Reid dataset. The outcomes of extensive experiments carried out on existing standard pedestrian datasets demonstrate that the proposed framework outperformed existing pedestrian gender classification methods, and acceptable results prove the proposed model as a robust model.
Highlights
In recent years, researchers’ interest in visual surveillance applications has been growing due to the availability of low-cost optical and infrared cameras and advanced computing machines
Since gender is a key attribute of a pedestrian and plays a role in social communication and human classification, gender prediction can be useful for various applications related to content-based image retrieval (CBIR), population statistics, human–computer interaction (HCI), health care, multimedia retrieval systems, demographic collection [15], and visual surveillance
Extensive experiments were performed by adopting different classifiers such as support vector machine (SVM), discriminant classification, and k-nearest neighbor (KNN) to observe sufficient low-level (HOG and LOMO features) and deep feature-based contributions for the design of a joint feature representation (JFR), and in this way, the proposed approach achieved 96% area under the curve (AUC) and 89.3% accuracy on pedestrian attribute (PETA) dataset, and
Summary
Researchers’ interest in visual surveillance applications has been growing due to the availability of low-cost optical and infrared cameras and advanced computing machines. Pedestrian images are captured under a specific field of view (FoV) in controlled environments [1] These days, object recognition from images and videos captured by digital cameras is being preferred by people for automated tasks related to security monitoring, public safety [2], pedestrian behavior analysis, etc. Low-level information includes hand-crafted features such as shape, color, and texture, while high-level information includes deep features of images [16,17,18,19,20] These information types usually use pedestrians’ voices, gait, skin color, and facial expression for gender prediction [21]. These approaches have faced issues related to different camera settings, pedestrians’ complex full-body appearances, and variations in their poses. Environmental effects which include changes in brightness, viewpoint disparities, blur, occlusion, and background cluttering, and images having a low resolution have affected results while classifying pedestrian gender
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
