A Vision Based Method for Object Recognition

Recognizing objects in images is a very important research task in the field of computer vision and pattern recognition. We introduce an effective method for object recognition. In order to characterize the appearance of the objects, the SFIT features are extracted from the images. Then, these features are sent to train four classifiers i.e. KNN classifier, Naive Bayes classifier, Decision tree classifier and SVM classifier which are used to predict objects. Out method performs well on the Caltech image data in the experiments.

[1]  Bernd Girod,et al.  Compressed Histogram of Gradients: A Low-Bitrate Descriptor , 2011, International Journal of Computer Vision.

[2]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[3]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

[4]  Ulrich Eckhardt,et al.  Shape descriptors for non-rigid shapes with a single closed contour , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[5]  Zdenek Kalal,et al.  Tracking-Learning-Detection , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Jitendra Malik,et al.  Shape matching and object recognition using shape contexts , 2010, 2010 3rd International Conference on Computer Science and Information Technology.

[7]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

[8]  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).

[9]  Su Yang,et al.  Image matching based on orientation-magnitude histograms and global consistency , 2012, Pattern Recognit..

[10]  Alex Pentland,et al.  Face recognition using eigenfaces , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[11]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .