Internet-vision based vehicle model query system using eigenfaces and pyramid of histogram of oriented gradients

• Main Authors: Thitiphat Anakavej, Aram Kawewong, Karn Patanukhom
• Format: Conference Proceeding
• Published: 2018
• Online Access: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84894203596&origin=inward; http://cmuir.cmu.ac.th/jspui/handle/6653943832/47377
• Institution: Chiang Mai University

This paper presents a new framework and feature set for vehicle model query system. By giving model names or manufacturer names as keywords, the desired vehicle images can be queried from target videos or vehicle image databases using internet-vision approach. In this framework, sample images are automatically retrieved from internet via search engine or car related website. Logos and frontal masks are segmented and are used for recognizing the manufacturer name and model of the vehicles, respectively. Eigenfaces and Pyramid Histogram of Oriented Gradients (PHOG) are proposed as features for recognition process. The experiments show that the proposed method can provide recognition rate of 98.2 % for manufacturer logo recognition process, and 94.00% for vehicle model recognition process. The performance of the entire framework of our proposed query system is also evaluated via precision and recall which are obtained as 87.67% and 80.00%, respectively. © 2013 IEEE.