Object Recognition using Full Pixel Matching

We consider the optimization problem of object recognition for real world images. Although several approaches have been proposed, this paper aims to improve the recognition rate with our novel method. In this paper, a full pixel matching based object recognition method in which no advance segmentation procedure is occurred during matching procedure is proposed. Our method compares the similarity of two images with pixels rather than the previous works with regions, shapes, et. al, so that the recognition rate can be improved. Furthermore, in order to implement our method, we present and analyze two algorithms which are Decision Space based Algorithm (DSA) and Direction Pattern based Algorithm (DPA). In the experiment, the performance of recognition of our two algorithms is evaluated on caltech 101 dataset. We compare our algorithms to several conventional works, such that our method improve the performance of object recognition in recognition rate, robustness of recognition among the variation of appearance and deformation in the images, and segmentation free.

[1]  Hiroshi Murase,et al.  A Multimodal Constellation Model for Object Category Recognition , 2009, MMM.

[2]  Marc Berthod,et al.  Subpixel contour matching using continuous dynamic programming , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Jamie Shotton,et al.  The Layout Consistent Random Field for Recognizing and Segmenting Partially Occluded Objects , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[4]  Frédéric Jurie,et al.  Groups of Adjacent Contour Segments for Object Detection , 2008, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Seiichi Uchida,et al.  An Efficient Two-Dimensional Warping Algorithm , 1999 .

[6]  Kazuhiro Hotta,et al.  Object Categorization Based on Kernel Principal Component Analysis of Visual Words , 2008, 2008 IEEE Workshop on Applications of Computer Vision.

[7]  Jitendra Malik,et al.  Shape matching and object recognition using low distortion correspondences , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[8]  Ramesh C. Jain,et al.  Using Dynamic Programming for Solving Variational Problems in Vision , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  G. Griffin,et al.  Caltech-256 Object Category Dataset , 2007 .

[10]  Jitendra Malik,et al.  Image Retrieval and Classification Using Local Distance Functions , 2006, NIPS.

[11]  Jitendra Malik,et al.  Recognition using regions , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Pietro Perona,et al.  Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[13]  Yuichi Yaguchi,et al.  Segmentation-Free Object Recognition Using Full Pixel Matching , 2009, 2009 Ninth IEEE International Conference on Computer and Information Technology.

[14]  Daphne Koller,et al.  Shape-Based Object Localization for Descriptive Classification , 2008, International Journal of Computer Vision.

[15]  Jitendra Malik,et al.  SVM-KNN: Discriminative Nearest Neighbor Classification for Visual Category Recognition , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[16]  Ryuichi Oka.  Spotting Method for Classification of Real World Data , 1998, Comput. J..

[17]  Yaguchi Yuichi,et al.  3D Shape Reconstruction Using Optimal Pixel Matching Between Images , 2008 .

[18]  David G. Lowe,et al.  Multiclass Object Recognition with Sparse, Localized Features , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[19]  Aaron E. Rosenberg,et al.  Performance tradeoffs in dynamic time warping algorithms for isolated word recognition , 1980 .