Improved HOG Descriptors

we study the feature set for object recognition problem, and use human detection as a test case. We propose two improvements based on HOG model which are Spatial Selective Method and Multi-level Method. In Spatial Selective One, we use HOG descriptor to extract feature vector from image window, but we shorten the feature vector size by eliminating less informative region. We get the same performance as Dalal's method, while reducing the extraction running time by 40%. In the Multi-level Method, we enhance the performance of HOG descriptor by 3% by adding more information to feature vector set through using concatenating multi-level on extraction process. All the experiments of this work are evaluated on INRIA pedestrian dataset 2009.

[1]  Daniel P. Huttenlocher,et al.  Efficient matching of pictorial structures , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[2]  Shu Liao,et al.  Dominant Local Binary Patterns for Texture Classification , 2009, IEEE Transactions on Image Processing.

[3]  Shuicheng Yan,et al.  An HOG-LBP human detector with partial occlusion handling , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[4]  Dariu Gavrila,et al.  Real-time object detection for "smart" vehicles , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[5]  Cordelia Schmid,et al.  Human Detection Based on a Probabilistic Assembly of Robust Part Detectors , 2004, ECCV.

[6]  Cordelia Schmid,et al.  Learning to Parse Pictures of People , 2002, ECCV.

[7]  Navneet Dalal,et al.  Finding People in Images and Videos , 2006 .

[8]  David A. Forsyth,et al.  Probabilistic Methods for Finding People , 2001, International Journal of Computer Vision.

[9]  Raj Gupta,et al.  Robust order-based methods for feature description , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[10]  David A. McAllester,et al.  A discriminatively trained, multiscale, deformable part model , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[12]  Sébastien Marcel,et al.  Local binary patterns as an image preprocessing for face authentication , 2006, 7th International Conference on Automatic Face and Gesture Recognition (FGR06).

[13]  Lin Yang,et al.  Robust segmentation and object classification in natural and medical images , 2009 .