Paper Title:
Object Classification Based on Fractional HoG Features
  Abstract

The purpose of this paper is to classify objects contained in images by the object categories. A new object feature in computer vision is introduced, that is fractional histograms of oriented gradients (fHoG). Due to the characteristics of fractional calculus, it is a descriptor that represents not only the object shape information but also the object texture details information. Together with pyramid decomposition, the fHoG features could be used to classify objects with similar shape but in different categories. For fHoG feature is some kind of local features, pyramid decomposition is designed to capture the hiding corresponding information between pixels. The two pyramid, spatial pyramid and Laplace pyramid, are both introduced. The former one is easy to compute while the calculation cost increasing fast as the pyramid level increasing. The latter one could save the calculation cost and get a better classification effect. Both of them could significantly improves the classification performance.

  Info
Periodical
Edited by
Zhenyu Du and Bin Liu
Pages
491-496
DOI
10.4028/www.scientific.net/AMM.65.491
Citation
Y. Liu, X. D. Shen, "Object Classification Based on Fractional HoG Features", Applied Mechanics and Materials, Vol. 65, pp. 491-496, 2011
Online since
June 2011
Export
Price
$32.00
Share

In order to see related information, you need to Login.

In order to see related information, you need to Login.

Authors: De Cheng Gao, Bin Liu, Jian Guo Wang
Abstract:In this paper, we have investigated an approach based on log-polar transform and support vector machine (SVM) for texture classification....
226
Authors: Xiao Liang Shi, Ying Li, Rong Xin Deng
Chapter 2: Microwaves Optics and Image
Abstract:It has become an important means of shelterbelts surveying using high resolution remote sensing image to access the distribution of farmland...
500
Authors: Ling Ling Zhang, Ge Ying Lai, Xiang Gui Zeng, Fa Zhao Yi
Chapter 18: Geographic Information and Remote Sensing Science
Abstract:According to the problem that the classification result of shrub and forest land was easy to confuse when used spectrum of Advanced Land...
3606
Authors: De Kun Hu, Jie Lin
Chapter 6: Intelligent System
Abstract:A multi-feature bio-inspired model for scene image classification (MFBIM) is presented in this work; it extends the hierarchical feedforward...
1569
Authors: Abdul Kadir, K.A.A. Aziz, Irianto
Chapter 3: Design for Automation and Intelligent Systems
Abstract:This paper reports a new approach for recognizing objects by using combination of texture, color and shape features. Texture features were...
111