A Methodology for the Integration of Hopfield Network and Genetic Algorithm Schemes for Graph Matching Problems
博士 === 國立中山大學 === 機械與機電工程學系研究所 === 93 === Object recognition is of much interest in recent industrial automation. Although a variety of approaches have been proposed to tackle the recognition problem, some cases such as overlapping objects, articulated objects, and low-resolution images, are still n...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2005
|
Online Access: | http://ndltd.ncl.edu.tw/handle/07832368643089770958 |
id |
ndltd-TW-093NSYS5490003 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-093NSYS54900032015-12-23T04:08:01Z http://ndltd.ncl.edu.tw/handle/07832368643089770958 A Methodology for the Integration of Hopfield Network and Genetic Algorithm Schemes for Graph Matching Problems 整合式霍菲爾類神經網路與遺傳演算法以求解圖形比對問題之方法論 Chin-Chung Huang 黃清忠 博士 國立中山大學 機械與機電工程學系研究所 93 Object recognition is of much interest in recent industrial automation. Although a variety of approaches have been proposed to tackle the recognition problem, some cases such as overlapping objects, articulated objects, and low-resolution images, are still not easy for the existing schemes. Coping with these more complex images has remained a challenging task in the field. This dissertation, aiming to recognize objects from such images, proposes a new integrated method. For images with overlapping or articulated objects, graph matching methods are often used, seeing them as solving a combinatorial optimization problem. Both Hopfield network and the genetic algorithm are decent tools for the combinatorial optimization problems. Unfortunately, they both have intolerable drawbacks. The Hopfield network is sensitive to its initial state and stops at a local minimum if it is not properly given. The GA, on the other hand, only finds a near-global solution, and it is time-consuming for large-scale tasks. This dissertation proposes to combine these two methods, while eliminating their bad and keeping their good, to solve some complex recognition problems. Before the integration, some arrangements are required. For instance, specialized 2-D GA operators are used to accelerate the convergence. Also, the “seeds” of the solution of the GA is extracted as the initial state of the Hopfield network. By doing so the efficiency of the system is greatly improved. Additionally, several fine-tuning post matching algorithms are also needed. In order to solve the homomorphic graph matching problem, i.e., multiple occurrences in a single scene image, the Hopfield network has to repeat itself until the stopping criteria are met. The method can not only be used to obtain the homomorphic mapping between the model and the scene graphs, but it can also be applied to articulated object recognition. Here we do not need to know in advance if the model is really an articulated object. The proposed method has been applied to measure some kinematic properties, such as the positions of the joints, relative linear and angular displacements, of some simple machines. The subject about articulated object recognition has rarely been mentioned in the literature, particularly under affine transformations. Another unique application of the proposed method is also included in the dissertation. It is about using low-resolution images, where the contour of an object is easily affected by noise. To increase the performance, we use the hexagonal grid in dealing with such low-resolution images. A hexagonal FFT simulation is first presented to pre-process the hexagonal images for recognition. A feature vector matching scheme and a similarity matching scheme are also devised to recognize simpler images with only isolated objects. For complex low-resolution images with occluded objects, the integrated method has to be tailored to go with the hexagonal grid. The low-resolution, hexagonal version of the integrated scheme has also been shown to be suitable and robust. Innchyn Her 何應勤 2005 學位論文 ; thesis 174 en_US |
collection |
NDLTD |
language |
en_US |
format |
Others
|
sources |
NDLTD |
description |
博士 === 國立中山大學 === 機械與機電工程學系研究所 === 93 === Object recognition is of much interest in recent industrial automation. Although a variety of approaches have been proposed to tackle the recognition problem, some cases such as overlapping objects, articulated objects, and low-resolution images, are still not easy for the existing schemes. Coping with these more complex images has remained a challenging task in the field.
This dissertation, aiming to recognize objects from such images, proposes a new integrated method. For images with overlapping or articulated objects, graph matching methods are often used, seeing them as solving a combinatorial optimization problem. Both Hopfield network and the genetic algorithm are decent tools for the combinatorial optimization problems. Unfortunately, they both have intolerable drawbacks. The Hopfield network is sensitive to its initial state and stops at a local minimum if it is not properly given. The GA, on the other hand, only finds a near-global solution, and it is time-consuming for large-scale tasks. This dissertation proposes to combine these two methods, while eliminating their bad and keeping their good, to solve some complex recognition problems. Before the integration, some arrangements are required. For instance, specialized 2-D GA operators are used to accelerate the convergence. Also, the “seeds” of the solution of the GA is extracted as the initial state of the Hopfield network. By doing so the efficiency of the system is greatly improved. Additionally, several fine-tuning post matching algorithms are also needed.
In order to solve the homomorphic graph matching problem, i.e., multiple occurrences in a single scene image, the Hopfield network has to repeat itself until the stopping criteria are met. The method can not only be used to obtain the homomorphic mapping between the model and the scene graphs, but it can also be applied to articulated object recognition. Here we do not need to know in advance if the model is really an articulated object. The proposed method has been applied to measure some kinematic properties, such as the positions of the joints, relative linear and angular displacements, of some simple machines. The subject about articulated object recognition has rarely been mentioned in the literature, particularly under affine transformations.
Another unique application of the proposed method is also included in the dissertation. It is about using low-resolution images, where the contour of an object is easily affected by noise. To increase the performance, we use the hexagonal grid in dealing with such low-resolution images. A hexagonal FFT simulation is first presented to pre-process the hexagonal images for recognition. A feature vector matching scheme and a similarity matching scheme are also devised to recognize simpler images with only isolated objects. For complex low-resolution images with occluded objects, the integrated method has to be tailored to go with the hexagonal grid. The low-resolution, hexagonal version of the integrated scheme has also been shown to be suitable and robust.
|
author2 |
Innchyn Her |
author_facet |
Innchyn Her Chin-Chung Huang 黃清忠 |
author |
Chin-Chung Huang 黃清忠 |
spellingShingle |
Chin-Chung Huang 黃清忠 A Methodology for the Integration of Hopfield Network and Genetic Algorithm Schemes for Graph Matching Problems |
author_sort |
Chin-Chung Huang |
title |
A Methodology for the Integration of Hopfield Network and Genetic Algorithm Schemes for Graph Matching Problems |
title_short |
A Methodology for the Integration of Hopfield Network and Genetic Algorithm Schemes for Graph Matching Problems |
title_full |
A Methodology for the Integration of Hopfield Network and Genetic Algorithm Schemes for Graph Matching Problems |
title_fullStr |
A Methodology for the Integration of Hopfield Network and Genetic Algorithm Schemes for Graph Matching Problems |
title_full_unstemmed |
A Methodology for the Integration of Hopfield Network and Genetic Algorithm Schemes for Graph Matching Problems |
title_sort |
methodology for the integration of hopfield network and genetic algorithm schemes for graph matching problems |
publishDate |
2005 |
url |
http://ndltd.ncl.edu.tw/handle/07832368643089770958 |
work_keys_str_mv |
AT chinchunghuang amethodologyfortheintegrationofhopfieldnetworkandgeneticalgorithmschemesforgraphmatchingproblems AT huángqīngzhōng amethodologyfortheintegrationofhopfieldnetworkandgeneticalgorithmschemesforgraphmatchingproblems AT chinchunghuang zhěnghéshìhuòfēiěrlèishénjīngwǎnglùyǔyíchuányǎnsuànfǎyǐqiújiětúxíngbǐduìwèntízhīfāngfǎlùn AT huángqīngzhōng zhěnghéshìhuòfēiěrlèishénjīngwǎnglùyǔyíchuányǎnsuànfǎyǐqiújiětúxíngbǐduìwèntízhīfāngfǎlùn AT chinchunghuang methodologyfortheintegrationofhopfieldnetworkandgeneticalgorithmschemesforgraphmatchingproblems AT huángqīngzhōng methodologyfortheintegrationofhopfieldnetworkandgeneticalgorithmschemesforgraphmatchingproblems |
_version_ |
1718156117899476992 |