Image representation and image similarity computation for images with multiple and partially occluded objects

This paper proposes an approach to object-based image retrieval for images contain multiple and partially occluded objects. In this approach, contours of objects are used to distinguish different classes of objects in images. We decompose all the contours in an image into segments and compute features from the segments. The C4.5 decision-tree learning algorithm is used to classify each segment in the images. Each image is represented in a k-dimensional space, where k is the number of classes of objects in all the images. Each dimension represents information about one of the classes. Euclidean distance between images in the k- dimensional space is adopted to compute similarities between images based on probabilities of segment classes. Experimental results show that this approach is effective.

[1]  Leslie J. Kitchen,et al.  A Framework for Object-Based Image Retrieval at the Semantic Level , 1999, VISUAL.

[2]  R. Bolles,et al.  Recognizing and Locating Partially Visible Objects: The Local-Feature-Focus Method , 1982 .

[3]  N. M. Nasrabadi,et al.  Object recognition based on graph matching implemented by a Hopfield-style neural network , 1989, International 1989 Joint Conference on Neural Networks.

[4]  Richard A. Volz,et al.  Recognizing Partially Occluded Parts , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Nirwan Ansari,et al.  Landmark-based shape recognition by a modified Hopfield neural network , 1993, Pattern Recognit..

[6]  Ingemar J. Cox,et al.  Psychophysical studies of the performance of an image database retrieval system , 1998, Electronic Imaging.

[7]  Charles A. Bouman,et al.  Perceptual image similarity experiments , 1998, Electronic Imaging.

[8]  Olivier D. Faugeras,et al.  Shape Matching of Two-Dimensional Objects , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Keith E. Price.  Hierarchical matching using relaxation , 1986, Comput. Vis. Graph. Image Process..

[10]  Edward J. Delp,et al.  Partial Shape Recognition: A Landmark-Based Approach , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Leslie J. Kitchen,et al.  Object-based image similarity computation using inductive learning of contour-segment relations , 2000, IEEE Trans. Image Process..

[12]  Rangasami L. Kashyap,et al.  Using Polygons to Recognize and Locate Partially Occluded Objects , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Leslie J. Kitchen,et al.  Classification-driven object-based image retrieval , 1999, Proceedings IEEE International Conference on Multimedia Computing and Systems.

[14]  Gérard G. Medioni,et al.  Structural Indexing: Efficient 3-D Object Recognition , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Bir Bhanu,et al.  Recognition of occluded objects: A cluster-structure algorithm , 1987, Pattern Recognit..