Mussarat Yasmin

Papers

Total Citations

H-Index

About

Dr. Mussarat Yasmin is a leading researcher in artificial intelligence and computer vision, with a primary focus on deep learning for biometric and pedestrian analysis. Her most-cited work, "Appearance based pedestrians’ gender recognition by employing stacked auto encoders in deep learning" (2018, 99 citations), represents a landmark contribution to automated gender classification from visual data. In this study, she pioneered the use of stacked autoencoders—a deep learning architecture—to extract robust, appearance-based features from pedestrian images, significantly improving recognition accuracy over traditional handcrafted methods. This work has been widely adopted in surveillance, human-computer interaction, and demographic analytics, demonstrating her ability to bridge theoretical deep learning with practical, real-world applications. Beyond this flagship paper, Dr. Yasmin’s research spans feature selection, image classification, and medical imaging, where she has developed algorithms that enhance computational efficiency and predictive performance. Her contributions are recognized through a growing citation impact, reflecting the utility of her methods in both academic and industrial settings. Dr. Yasmin’s work continues to inspire advances in automated visual understanding, making her a key figure in the evolution of intelligent systems for gender recognition and beyond.