Object Recognition from Color Images by Fuzzy Classification of Gabor Wavelet Features

This paper introduces a novel object recognition approach based on the Gabor Wavelet representation of the binarized image that makes use of fuzzy logic for determining the 'soft' class label of the color test images with respect to the gray training templates. The fuzzy membership function used is a Generalized Gaussian function whose exponent value is determined empirically. The use of simple computations for assigning the class label to the query image makes the technique computationally effective. The experimental results on 494 color test images from ten object categories from the Caltech database show a high percentage of classification accuracy with only fifteen gray images from each category used for training. The efficiency of our method is established by comparing our results with that of different classifiers and also with Qiu's Content based Image retrieval (CBIR) system for color images.

[1]  Yi-Ping Hung,et al.  Viewpoint-Independent Object Detection Based on Two-Dimensional Contours and Three-Dimensional Sizes , 2011, IEEE Transactions on Intelligent Transportation Systems.

[2]  Joachim M. Buhmann,et al.  Distortion Invariant Object Recognition in the Dynamic Link Architecture , 1993, IEEE Trans. Computers.

[3]  Rangaraj M. Rangayyan,et al.  Directional analysis of images with Gabor wavelets , 2000, Proceedings 13th Brazilian Symposium on Computer Graphics and Image Processing (Cat. No.PR00878).

[4]  Hong Zhang,et al.  Object detection by parts using appearance, structural and shape features , 2011, 2011 IEEE International Conference on Mechatronics and Automation.

[6]  Robin N. Strickland,et al.  Wavelet transform methods for object detection and recovery , 1997, IEEE Trans. Image Process..

[7]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[8]  R. Neil Braithwaite,et al.  Hierarchical Gabor filters for object detection in infrared images , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[9]  R. Kana,et al.  Specialization and integration of brain responses to object recognition and location detection , 2012, Brain and behavior.

[10]  Cordelia Schmid,et al.  Accurate Object Recognition with Shape Masks , 2012, International Journal of Computer Vision.

[11]  Cemal Kose,et al.  Comparing 2D matched filter response and Gabor filter methods for vessel segmentation in retinal images , 2010, National Conference on Electrical, Electronics and Computer Engineering.

[12]  G. Qiu.  Indexing chromatic and achromatic patterns for content-based colour image retrieval , 2002, Pattern Recognit..

[13]  Jake K. Aggarwal,et al.  Computer Tracking of Objects Moving in Space , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Fadi Dornaika,et al.  Efficient Object Detection and Matching Using Feature Classification , 2010, 2010 20th International Conference on Pattern Recognition.

[15]  Antonio Torralba,et al.  A Tree-Based Context Model for Object Recognition , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Bir Bhanu,et al.  Gabor wavelet representation for 3-D object recognition , 1997, IEEE Trans. Image Process..

[17]  Yan Huang,et al.  Parallel Gabor Wavelet Transform for Edge Detection , 2010, 2010 International Conference on Internet Technology and Applications.