Graph matching for object recognition and recovery

2004 ◽  
Vol 37 (7) ◽  
pp. 1557-1560 ◽  
Author(s):  
Lei He ◽  
Chia Y. Han ◽  
Bryan Everding ◽  
William G. Wee
Keyword(s):  
Object Recognition ◽  
Graph Matching

THE ROLE OF RELATIONAL CONSTRAINTS IN REGION MATCHING

2004 ◽  
Vol 18 (03) ◽  
pp. 443-454 ◽  
Author(s):  
ALIREZA AHMADYFARD ◽  
JOSEF KITTLER
Keyword(s):  
Object Recognition ◽  
Graph Matching ◽  
Original Method ◽  
Misclassification Rate ◽  
Shape Descriptors ◽  
Recognition Method ◽  
Region Matching ◽  
Matching Technique ◽  
Elliptic Region

We propose a graph-based representation for the elliptic region shape descriptors introduced by Tuytelaars et al.13 In this representation we use image profiles to describe the relation between a pair of image regions. This new representation and a graph matching technique proposed in Ref. 1 are the basis of an object recognition method. An experimental comparative study between the original method and the new graph-based method is carried out. The results show that the graph-based method is more robust to scaling than the original method. Moreover, the misclassification rate using the graph-based method is considerably lower than that yielded by the original method.

Combining Feature- and Correspondence-Based Methods for Visual Object Recognition

2009 ◽  
Vol 21 (7) ◽  
pp. 1952-1989 ◽  
Author(s):  
Günter Westphal ◽  
Rolf P. Würtz
Keyword(s):  
Object Recognition ◽  
Graph Matching ◽  
Single Layer ◽  
Recognition System ◽  
Input Image ◽  
Visual Object ◽  
Visual Object Recognition ◽  
Elastic Graph Matching ◽  
Feature Based ◽  
Arbitrary Objects

We present an object recognition system built on a combination of feature- and correspondence-based pattern recognizers. The feature-based part, called preselection network, is a single-layer feedforward network weighted with the amount of information contributed by each feature to the decision at hand. For processing arbitrary objects, we employ small, regular graphs whose nodes are attributed with Gabor amplitudes, termed parquet graphs. The preselection network can quickly rule out most irrelevant matches and leaves only the ambiguous cases, so-called model candidates, to be verified by a rudimentary version of elastic graph matching, a standard correspondence-based technique for face and object recognition. According to the model, graphs are constructed that describe the object in the input image well. We report the results of experiments on standard databases for object recognition. The method achieved high recognition rates on identity and pose. Unlike many other models, it can also cope with varying background, multiple objects, and partial occlusion.

Sign in / Sign up

Export Citation Format

Share Document