Recognition and Reconstruction of Partially Occluded Objects

A new automatic system for the recognition and re¬construction of resealed and/or rotated partially occluded objects is presented. The objects to be recognized are described by 2D views and each view is occluded by several half-planes. The whole object views and their visible parts (linear cuts) are then stored in a database. To establish if a region R of an input image represents an object possibly occluded, the system generates a set of linear cuts of R and compare them with the elements in the database. Each linear cut of R is associated to the most similar database linear cut. R is recognized as an instance of the object 0 if the majority of the linear cuts of R are associated to a linear cut of views of 0. In the case of recognition, the system reconstructs the occluded part of R and determines the scale factor and the orientation in the image plane of the recognized object view. The system has been tested on two different datasets of objects, showing good performance both in terms of recognition and reconstruction accuracy.

• Michela Lecca
• Stefano Messelodi

• Occluded Object Recognition
• Shape Reconstruction
• Automatic Self-Adaptive Systems
• Linear Cut.

[1] S. A. Nene, S. K. Nayar, H. Murase, Columbia object image library
(COIL-100). In Technical Report CUCS-006-96, Columbia University,
1996.
[2] http://www.ikea.com/ms/it IT/our products.html
[3] R. Brunelli, O. Mich, Image retrieval by examples. In IEEE Transactions
on Multimedia N. 2(3), 2000.
[4] C. Andreatta, CBIR techniques for object recognition. Technical Report
ITC-irst T04-12-01, December 2004.
[5] M. Lecca, MEMORI - Version 1.0. Technical Report ITC-irst T05-10-01,
October 2005
[6] M. Reinhold, M. Grzegorzek, J. Denzler, H. Niemann, Appearance-
Based Recognition of 3-D Objects by Cluttered Background and Occlusions.
In Pattern Recognition Vol. 38, N. 5, 2005
[7] A. Shokoufandeh, I. Marsic, S. J. Dickinson, View-based object
recognition using saliency maps. In Image and Computing N. 17, 1999
[8] V. Vilaplana, X. Giro, P.Salembier, F. Marques, Region-based extraction
and analysis of visual object information. In Proc. of Int. Workshop on
Content-Based Multimedia Indexing CBMI 2005, pp. SSI.3.1-SSI.3.9,
SBN: 952-15-1364-0, 2005
[9] V. Ferrari, T. Tuytelaars, L. Van Gool, Simultaneous Object Recognition
and Segmentation by Image Exploration. In International Journal of
Computer Vision (IJCV), April 2006
[10] E. Rivlin and S. J. Dickinson and A. Rosenfeld, Recognition by
Functional Parts. In Computer Vision and Image Understanding: CVIU,
Vol. 62, N. 2, 1995
[11] L. Wiskott, and C. von der Malsburg, A Neural System for the Recognition
of Partially Occluded Objects in Cluttered Scenes. In Advances in
Pattern Recognition Systems using Neural Networks Technologies, Vol.
7 in series Machine Perception and Artificial Intelligence, 1994
[12] F. Krolupper, Recognition of Occluded Objects Using Curvature. In
Proc. of The 12th International Conference in Central Europe on
Computer Graphics, Visualization and Computer Vision: WSCG 2004,
2004
[13] T. Deselaers, D. Keysers, R. Paredes, E. Vidal, H. Ney, Local
Representation for multi-object recognition. In Proc. of Deutsche
Arbeitsgemeinschaft f ¨ur Mustererkennung: DAGM 2003, 2003
[14] S. Obdrzlek, J. Matas, Object Recognition using Local Affi ne Frames on
Distinguished Regions. In Proc. of British Machine Vision Conference,
2002
[15] R. Basri, D. Jacobs, Recognition Using Region Correspondences In
Proc. of International Conference on Computer Vision: ICCV, 1995
[16] G. Dorko, C. Schmid, Object class recognition using discriminative
local features. In Research Report 5497, INRIA Rhone Alpes, 2004
[17] G. Fritz, L. Paletta, H. Bischof, Object representation and recognition
from informative local appearances. In Proc. of Digital Imaging in
Media and Education, 28th AAPR Workshop, 2004
[18] S. Agarwal, A. Awan, D. Roth, Learning to Detect Objects in Images
via a Sparse, Part-Based Representation. In IEEE, Pattern Analysis and
Machine Intelligence, Vol. 26, No. 11, 2004
[19] S. Berretti, A. Del Bimbo, E. Vicario, Effi cient matching and indexing
of Graph Models in Content-Based Retrieval. In IEEE Transaction on
Pattern Analysis and Machine Intelligence, Vol. 23, No. 10, 2001
[20] M. Lecca, Recognition and Reconstruction of partially Occluded
Objects. Technical Report, ITC-irst T06-04-01, April 2006.
[21] M. Lecca, Object Recognition in Color Images by the Self Confi guring
System MEMORI. In International Journal of Signal Processing, Vol.
3, No. 3, 2006
TRANSACTIONS ON ENGINEERING, COMPUTING AND TECHNOLOGY VOLUME 16 NOVEMBER 2006 ISSN 1305-5313
ENFORMATIKA V16 2006 ISSN 1305-5313 238 © 2006 WORLD ENFORMATIKA SOCIETY