PROJECT TITLE :
Multi-signature based person re-identification
A unique look-primarily based technique for person re-identification is proposed. The approach exploits three native features to extract the shape and therefore the chromatic appearance of an individual. Robustness against low resolution images, viewpoint and illumination changes, occlusions and create variations is achieved by a unique signature. A body half division is used to propose a unique distance measure. The method has been compared to state-of-the-art methods employing a re-identification benchmark dataset. Results show that the proposed resolution outperforms state-of-the-art ways used for comparison.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here