2-D Invariant Pattern Recognition Using a Backpropogation Network Improved by Distributed Associative Memory

碩士 === 國立成功大學 === 電機工程研究所 === 82 === In this paper, a system included image preprocessing and neural networks is proposed. The various function units of the image processing are used to obtain an invariant image representation in the beginn...

Full description

Bibliographic Details
Main Authors: Jau-Ling Shih, 石昭玲
Other Authors: Pau-Choo Chung
Format: Others
Language:en_US
Published: 1994
Online Access:http://ndltd.ncl.edu.tw/handle/47410554866730966852
id ndltd-TW-082NCKU0442089
record_format oai_dc
spelling ndltd-TW-082NCKU04420892015-10-13T15:36:51Z http://ndltd.ncl.edu.tw/handle/47410554866730966852 2-D Invariant Pattern Recognition Using a Backpropogation Network Improved by Distributed Associative Memory 加強式反向傳播網路之二維圖形辨識系統 Jau-Ling Shih 石昭玲 碩士 國立成功大學 電機工程研究所 82 In this paper, a system included image preprocessing and neural networks is proposed. The various function units of the image processing are used to obtain an invariant image representation in the beginning of the system. The space of the neural networks weights can be reduced by using the reduction of the feature dimension before the preprocessed feature applied to the networks.Then, several kinds of the neural models are proposed for pattern recognition : (1) distributed associative memory (DAM), (2) backpropagation network(BPN), (3)DAM combined with BPN, and(4)BPN with the associative memory as initial weights. In the case of (3), this hierarchical networks consist of two levels of neural networks. In the low level, a DAM receives the output vectors of image preprocessing functions to create a system which recognizes pattern regardless of changes in scale or rotation. The higher level is a two- layers BPN which recives the recalled information from the memorized database of the lower level. This neural networks use a BPN after the DAM can raise the recognition ratio in comparison with a DAM, and be faster than a BPN.In the case of (4), the training of the BPN speeds up much because this neural networks use a associative memory of a DAM as initial weights of the first layer of te BPN. Experiment results show that the system can recognize all the patterns correctly when the percentage of the white noises is under under 20% for the case (3) and (4). Pau-Choo Chung 詹寶珠 1994 學位論文 ; thesis 60 en_US
collection NDLTD
language en_US
format Others
sources NDLTD
description 碩士 === 國立成功大學 === 電機工程研究所 === 82 === In this paper, a system included image preprocessing and neural networks is proposed. The various function units of the image processing are used to obtain an invariant image representation in the beginning of the system. The space of the neural networks weights can be reduced by using the reduction of the feature dimension before the preprocessed feature applied to the networks.Then, several kinds of the neural models are proposed for pattern recognition : (1) distributed associative memory (DAM), (2) backpropagation network(BPN), (3)DAM combined with BPN, and(4)BPN with the associative memory as initial weights. In the case of (3), this hierarchical networks consist of two levels of neural networks. In the low level, a DAM receives the output vectors of image preprocessing functions to create a system which recognizes pattern regardless of changes in scale or rotation. The higher level is a two- layers BPN which recives the recalled information from the memorized database of the lower level. This neural networks use a BPN after the DAM can raise the recognition ratio in comparison with a DAM, and be faster than a BPN.In the case of (4), the training of the BPN speeds up much because this neural networks use a associative memory of a DAM as initial weights of the first layer of te BPN. Experiment results show that the system can recognize all the patterns correctly when the percentage of the white noises is under under 20% for the case (3) and (4).
author2 Pau-Choo Chung
author_facet Pau-Choo Chung
Jau-Ling Shih
石昭玲
author Jau-Ling Shih
石昭玲
spellingShingle Jau-Ling Shih
石昭玲
2-D Invariant Pattern Recognition Using a Backpropogation Network Improved by Distributed Associative Memory
author_sort Jau-Ling Shih
title 2-D Invariant Pattern Recognition Using a Backpropogation Network Improved by Distributed Associative Memory
title_short 2-D Invariant Pattern Recognition Using a Backpropogation Network Improved by Distributed Associative Memory
title_full 2-D Invariant Pattern Recognition Using a Backpropogation Network Improved by Distributed Associative Memory
title_fullStr 2-D Invariant Pattern Recognition Using a Backpropogation Network Improved by Distributed Associative Memory
title_full_unstemmed 2-D Invariant Pattern Recognition Using a Backpropogation Network Improved by Distributed Associative Memory
title_sort 2-d invariant pattern recognition using a backpropogation network improved by distributed associative memory
publishDate 1994
url http://ndltd.ncl.edu.tw/handle/47410554866730966852
work_keys_str_mv AT jaulingshih 2dinvariantpatternrecognitionusingabackpropogationnetworkimprovedbydistributedassociativememory
AT shízhāolíng 2dinvariantpatternrecognitionusingabackpropogationnetworkimprovedbydistributedassociativememory
AT jaulingshih jiāqiángshìfǎnxiàngchuánbōwǎnglùzhīèrwéitúxíngbiànshíxìtǒng
AT shízhāolíng jiāqiángshìfǎnxiàngchuánbōwǎnglùzhīèrwéitúxíngbiànshíxìtǒng
_version_ 1717767126152904704