Square patch feature: faster weak-classifier for robust object detection

Mohd Mustafah, Yasir and Bigdeli, Abbas and Azman, Amelia Wong and Dadgostar, Farhad and Lovell, Brian (2010) Square patch feature: faster weak-classifier for robust object detection. In: 11th International Conference on Control Automation Robotics & Vision (ICARCV), 2010, 7-10th December 2010, Singapore.

PDF - Published Version Restricted to Registered users only Download (384kB) | Request a copy

Abstract

This paper presents a novel generic weak classifier for object detection called “Square Patch Feature”. The speed and overall performance of a detector utilising Square Patch features in comparison to other weak classifiers shows improvement. Each weak classifier is based on the difference between two or four fixed size square patches in an image. A pre-calculated representation of the image called “patch image” is required to accelerate the weak classifiers computation. The computation requires fewer arithmetic operations and fewer accesses to the main memory in comparison to the well known Viola-Jones Haar-like classifier. In addition to the faster computation, the weak classifier can be extended for in-plane rotation, where each square patch can be rotated to detect in-plane rotated objects. The results of the experiments on the MIT CBCL Face dataset show that a Square Patch Feature classifier is as accurate as the Viola-Jones Haarlike classifier, and when implemented on hardware (i.e. FPGA), it is almost 2 times faster.

Item Type:	Conference or Workshop Item (Full Paper)
Additional Information:	5107/99
Uncontrolled Keywords:	weak classifier, rotation invariance, object detection.
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Engineering
Depositing User:	Dr Yasir Mohd Mustafah
Date Deposited:	28 Apr 2011 10:10
Last Modified:	11 Jul 2011 14:45
URI:	http://irep.iium.edu.my/id/eprint/99

Actions (login required)

View Item