Multiple Resolution Image Classification

Binary image classification is a problem that has received much attention in recent years. In this paper we evaluate a selection of popular techniques in an effort to find a feature set/classifier combination which generalizes well to full resolution image data. We then apply that system to images at one-half through onesixteenth resolution, and consider the corresponding error rates. In addition, we further observe generalization performance as it depends on the number of training images, and lastly, compare the system’s best error rates to that of a human performing an identical classification task given the same set of test images.

[1]  H. Sebastian Seung,et al.  Learning the parts of objects by non-negative matrix factorization , 1999, Nature.

[2]  Bernhard Schölkopf,et al.  Comparing support vector machines with Gaussian kernels to radial basis function classifiers , 1997, IEEE Trans. Signal Process..

[3]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[4]  Michael J. Swain,et al.  Indexing via color histograms , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[5]  Rosalind W. Picard,et al.  Texture orientation for sorting photos "at a glance" , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[6]  Vapnik,et al.  SVMs for Histogram Based Image Classification , 1999 .

[7]  Anil K. Jain,et al.  Shape-Based Retrieval: A Case Study With Trademark Image Databases , 1998, Pattern Recognit..

[8]  Tomaso Poggio,et al.  Multiclass Classification of SRBCTs , 2001 .

[9]  Martin Szummer,et al.  Indoor-outdoor image classification , 1998, Proceedings 1998 IEEE International Workshop on Content-Based Access of Image and Video Database.

[10]  Daphne Koller,et al.  Toward Optimal Feature Selection , 1996, ICML.