Human Gait Recognition Using Deep Learning and Improved Ant Colony Optimization

Human gait recognition (HGR) has received a lot of attention in the last decade as an alternative biometric technique. The main challenges are change in-person view angle and covariant factors. major factors walking while carrying bag wearing coat. Deep learning is new machine technique that gaining popularity. Many techniques for HGR based on deep presented literature. requirement efficient framework always required correct quick recognition. We proposed fully automated improved ant colony optimization (IACO) using video sequences this work. consists four primary steps. In first step, database normalized frame. second two pre-trained models named ResNet101 InceptionV3 selected modified according to dataset's nature. After that, we trained both transfer extracted features. IACO algorithm used improve select best features, which then passed Cubic SVM final classification. cubic employs multiclass method. experiment was carried out three angles (0, 18, 180) CASIA B dataset, accuracy 95.2, 93.9, 98.2 percent, respectively. A comparison with existing also performed, method outperforms terms computational time.