Using Local Invariant in Occluded Object Recognition by Hopfield Neural Network
碩士 === 國立中山大學 === 機械與機電工程學系研究所 === 91 === In our research, we proposed a novel invariant in 2-D image contour recognition based on Hopfield-Tank neural network. At first, we searched the feature points, the position of feature points where are included high curvature and corner on the contour. We us...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2003
|
Online Access: | http://ndltd.ncl.edu.tw/handle/61679627653397484929 |
id |
ndltd-TW-091NSYS5490038 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-091NSYS54900382016-06-22T04:20:47Z http://ndltd.ncl.edu.tw/handle/61679627653397484929 Using Local Invariant in Occluded Object Recognition by Hopfield Neural Network 利用局部特徵不變量與Hopfield網路辨識重疊物件 Chih-Hung Tzeng 曾智宏 碩士 國立中山大學 機械與機電工程學系研究所 91 In our research, we proposed a novel invariant in 2-D image contour recognition based on Hopfield-Tank neural network. At first, we searched the feature points, the position of feature points where are included high curvature and corner on the contour. We used polygonal approximation to describe the image contour. There have two patterns we set, one is model pattern another is test pattern. The Hopfield-Tank network was employed to perform feature matching. In our results show that we can overcome the test pattern which consists of translation, rotation, scaling transformation and no matter single or occlusion pattern. Innchyn Her 何應勤 2003 學位論文 ; thesis 78 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立中山大學 === 機械與機電工程學系研究所 === 91 === In our research, we proposed a novel invariant in 2-D image contour recognition based on Hopfield-Tank neural network. At first, we searched the feature points, the position of feature points where are included high curvature and corner on the contour. We used polygonal approximation to describe the image contour. There have two patterns we set, one is model pattern another is test pattern. The Hopfield-Tank network was employed to perform feature matching. In our results show that we can overcome the test pattern which consists of translation, rotation, scaling transformation and no matter single or occlusion pattern.
|
author2 |
Innchyn Her |
author_facet |
Innchyn Her Chih-Hung Tzeng 曾智宏 |
author |
Chih-Hung Tzeng 曾智宏 |
spellingShingle |
Chih-Hung Tzeng 曾智宏 Using Local Invariant in Occluded Object Recognition by Hopfield Neural Network |
author_sort |
Chih-Hung Tzeng |
title |
Using Local Invariant in Occluded Object Recognition by Hopfield Neural Network |
title_short |
Using Local Invariant in Occluded Object Recognition by Hopfield Neural Network |
title_full |
Using Local Invariant in Occluded Object Recognition by Hopfield Neural Network |
title_fullStr |
Using Local Invariant in Occluded Object Recognition by Hopfield Neural Network |
title_full_unstemmed |
Using Local Invariant in Occluded Object Recognition by Hopfield Neural Network |
title_sort |
using local invariant in occluded object recognition by hopfield neural network |
publishDate |
2003 |
url |
http://ndltd.ncl.edu.tw/handle/61679627653397484929 |
work_keys_str_mv |
AT chihhungtzeng usinglocalinvariantinoccludedobjectrecognitionbyhopfieldneuralnetwork AT céngzhìhóng usinglocalinvariantinoccludedobjectrecognitionbyhopfieldneuralnetwork AT chihhungtzeng lìyòngjúbùtèzhēngbùbiànliàngyǔhopfieldwǎnglùbiànshízhòngdiéwùjiàn AT céngzhìhóng lìyòngjúbùtèzhēngbùbiànliàngyǔhopfieldwǎnglùbiànshízhòngdiéwùjiàn |
_version_ |
1718318625661648896 |