Object Localization Based on Mutual Information in Global Structure Constraint Model

In this paper, a kind of object representation model global structure constraint is presented, in which objects are described as constellations of points satisfied with their intrinsic specific global structure constraints. The spatial relations among all the patches of small color variations are extracted as shape model and the representative color information of patches are encoded and clustered as color model with color cluster information. Then, in the searching phase, mutual information is used as measurement with optimal algorithm to locate target objects in images by finding out the exactly matched position. In the experiment, we tested the approach on a collection of human face images and the results demonstrated the approach is simple, effective and efficient.

[1]  Daphna Weinshall,et al.  Efficient Learning of Relational Object Class Models , 2005, ICCV.

[2]  Pietro Perona,et al.  Object class recognition by unsupervised scale-invariant learning , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[3]  Daphna Weinshall,et al.  Efficient Learning of Relational Object Class Models , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[4]  Timothy F. Cootes,et al.  Active Appearance Models , 1998, ECCV.

[5]  Harry Wechsler,et al.  The FERET database and evaluation procedure for face-recognition algorithms , 1998, Image Vis. Comput..

[6]  Daniel P. Huttenlocher,et al.  Pictorial Structures for Object Recognition , 2004, International Journal of Computer Vision.

[7]  Colin R. Reeves,et al.  Evolutionary computation: a unified approach , 2007, Genetic Programming and Evolvable Machines.

[8]  Timothy F. Cootes,et al.  A mixture model for representing shape variation , 1999, Image Vis. Comput..

[9]  Kin-Man Lam,et al.  Elastic shape-texture matching for human face recognition , 2008, Pattern Recognit..

[10]  Timothy F. Cootes,et al.  Active shape models , 1998 .

[11]  Pietro Perona,et al.  Towards automatic discovery of object categories , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[12]  Richard Bowden,et al.  Simultaneous modeling and tracking (SMAT) of feature sets , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).