A Comparative Analysis of Texture Methods for Visual Object Categorization

Hayder Ayad; Loay E. George; Mamoun Jasim Mohammed

doi:10.25212/lfu.qzj.2.2.02

Authors

Hayder Ayad Department of Computer Science, University of Baghdad, Iraq
Loay E. George Department of Computer Science, University of Baghdad, Iraq
Mamoun Jasim Mohammed Department of Computer Engineering, The Iraqia University, Iraq

DOI:

https://doi.org/10.25212/lfu.qzj.2.2.02

Keywords:

Texture analysis, Co-occurrence Matrix, Gradient, Edge Histogram, SVM, Caltech 101 Dataset.

Abstract

This paper presents a comparative study to the most common texture features analysis methods. In fact, there are two kinds of approaches have been proposed to extract the texture features for the purpose of object categorization, the former deals with the intensity pixels which derived the intensities texture and the second method dealing with the edge pixels which obtained the edge texture. However, to extract and make a comparative analysis to the texture maps there are several approaches have been presented in this research, i.e., Gradient, Co-occurrence matrix, Contrast and Edge Histogram Descriptor. A real world images dataset denoted by Caltech 101 dataset has been adopted to evaluate the proposed texture analysis methods. Mostly, the first 20 classes with 40 images per-class have been chosen to demonstrate the methods performance. Fundamentally, the objects of these images have almost isolated for the purpose of categorization. The experiment results show that the edge histogram descriptor outperformed the other proposed texture analysis methods with average accuracy 71.175±1.355775 because the edge histogram descriptor is less sensitive to the noise and variation of pixels intensities which most of the objects of Caltech 101 dataset profoundly affected.

Downloads

Download data is not yet available.

References

Avramović, A., Ševo, I. and Reljin I. 2015. “Comparative analysis of texture classification based low and high order local features”. 23rd Telecommunication Forum Telfor (TELFOR). Pp: 799 – 802.

Ayad. H., Abdullah, S.N.H.S. and Abdullah, A. 2012. “Visual Object Categorization Based on Orientation Descriptor.” Sixth Asia international conference on mathematical modeling and computer simulation (ASM 2012). Bali, Indonesia, 29-31.

Ayad, H., Abdulameer, M.H. George, L.E and Hassan, N.F. 2015. “Descriptor Trends in Texture Classification for Material Recognition.” Research Journal of Applied Sciences, Engineering and Technology. Vol. 10, Issue 10, Pp: 1089-1101.

Belsare, A. D., Mushrif, M. M., Pangarkar, M. A. and Meshram, N. 2015. “Classification of Breast Cancer Histopathology Images using Texture Feature Analysis”. IEEE Region 10 Conference (TENCON). Pp: 1-5.

Jabid. T., Mohammadt, T., Ahsan, T., Abdullah-AI-Wadud M. and Chae, O. 2011. “An Edge-Texture based Moving Object Detection for Video Content Based Application”.14th International Conference on Computer and Information Technology. Pp: 112 – 116.

Jain, R., Kasturi, R. and Schunck, B.G. 1995."Machine vision." McGraw-Hill, New York, NY, USA.

Liua, Y., Zhanga,D., Lua, G. and Mab, W-Y. 2007. “A survey of content-based image retrieval with high-level semantics.” Pattern Recognition, Vol. 40, Pp: 262– 282,

Nadernejad, E. 2008. “Edge Detection Techniques: Evaluations and Comparisons.” Applied Mathematical Sciences, Vol. 2, No.31, Pp: 1507 – 1520.

Salam, H.I. A. 2008. “Content-Based Image Retrieval System Using Fuzzy Rule”. Master thesis. Collogue of Science, Al-Nahrain University. Iraq.

Satpathy, A., Jiang, X., and Eng., H-L. 2014. “LBP-Based Edge-Texture Features for Object Recognition”. IEEE TRANSACTIONS ON IMAGE PROCESSING, Vol. 23. Pp: 1953 – 1964.

Won, C.S., Park, D. K. and Park, S-J. 2002. “Efficient Use of MPEG-7 Edge Histogram Descriptor.” ETRI Journal. Vol. 24, Issue 1.