Gabor filter based image representation for object classification

Data representation plays an important role in a classifier's accuracy. A given dataset may lead to better results by simply applying a change of basis while keeping the original number of parameters. In this paper, Gabor Filter based image representation has been exploited for object classification. First, Gabor filter based convolution is computed for features extraction, then down-sampling is performed and features are normalized to zero mean and unit variance. This image representation having discriminative visual patterns is used for training of object classifier in Matlab Neural Toolbox. Performance of this proposed image representation is examined on two real world image datasets CIFAR and MNIST and results show that data representation using Gabor can provide good classification without increasing the number of trainable parameters. Finally, this approach is compared to different configurations of Convolutional Neural Network having trainable parameters to verify the validity of proposed image representation.

[1]  Fei Su,et al.  Histogram of Log-Gabor Magnitude Patterns for face recognition , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[2]  Yong Haur Tay,et al.  A Comparative Study for Texture Classification Techniques on Wood Species Recognition Problem , 2009, 2009 Fifth International Conference on Natural Computation.

[3]  Renu Dhir,et al.  Recognition of Handwritten Gurmukhi Numeral using Gabor Filters , 2012 .

[4]  Saman A. Zonouz,et al.  CloudID: Trustworthy cloud-based and cross-enterprise biometric identification , 2015, Expert Syst. Appl..

[5]  Patrice Collen,et al.  Deep learning of split temporal context for automatic speech recognition , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[6]  Ebru Arisoy,et al.  Low-rank matrix factorization for Deep Neural Network training with high-dimensional output targets , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[7]  Chong Wang,et al.  Simultaneous image classification and annotation , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Jae-Hong Min,et al.  Object classification based on visual and extended features for video surveillance application , 2011, 2011 8th Asian Control Conference (ASCC).

[9]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[10]  Dharminder Kumar,et al.  Comparing gradient based learning methods for optimizing predictive neural networks , 2014, 2014 Recent Advances in Engineering and Computational Sciences (RAECS).

[11]  Qi Tian,et al.  Multiple instance learning using visual phrases for object classification , 2010, 2010 IEEE International Conference on Multimedia and Expo.

[12]  Haiying Guan,et al.  A New Metric for Latent Fingerprint Image Preprocessing , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[13]  Changsong Liu,et al.  Optimized Gabor filter based feature extraction for character recognition , 2002, Object recognition supported by user interaction for service robots.

[14]  Yingli Tian,et al.  Text Detection in Natural Scene Images by Stroke Gabor Words , 2011, 2011 International Conference on Document Analysis and Recognition.

[15]  Qiang Hao,et al.  A study on the use of Gabor features for Chinese OCR , 2001, Proceedings of 2001 International Symposium on Intelligent Multimedia, Video and Speech Processing. ISIMP 2001 (IEEE Cat. No.01EX489).