Multistage object recognition using dynamical-link graph matching

1991 ◽  
Author(s):  
Kenneth A. Flaton
Keyword(s):  
Object Recognition ◽  
Graph Matching

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.

Organic Computing Methods for Face Recognition (Methoden des Organic Computing zur Gesichtserkennung)

2005 ◽  
Vol 47 (4) ◽  
Author(s):  
Rolf P. Würtz
Keyword(s):  
Face Recognition ◽  
Object Recognition ◽  
Graph Matching ◽  
Biological Systems ◽  
Computing Methods ◽  
High Expectations ◽  
Recognition Systems ◽  
Image Pixels ◽  
General Object ◽  
Organic Computing

SummuryAutomatic face recognition is a slowly maturing and economically highly important technology, which still falls short of the high expectations set on it. The variation in images taken from the same person makes face recognition systems difficult to design — it is impossible to explicitly code all variability. Successful systems have relied heavily on the principle of self-organizing many fragile cues to arrive at a robust decision and have been built by learning from biological systems. The paper describes the techniques of elastic bunch graph matching as a hierarchical integration of image pixels into Gabor responses, jets, graphs, and bunch graphs. Beside face recognition, these concepts are used for face classification learned from examples. It is attempted to develop them further to reach a complete parameterization of all faces. Methods for more general object recognition using the same Organic Computing principles are outlined and include the concept of end-stopped cells as corner detectors.

Sign in / Sign up

Export Citation Format

Share Document