A New Algorithm for Pattern Recognition Based on Ring Approach

碩士 === 亞洲大學 === 生物資訊學系碩士班 === 96 === Template matching is one of the most active research areas in pattern recognition. It is also a critical step of image analysis. Traditional methods for template matching have encountered many problems and limitations. Among them, rotation-invariance is the most...

Full description

Bibliographic Details
Main Authors: Ching-Ling Lai, 賴慶霖
Other Authors: Cheng-Yu Lee
Format: Others
Language:zh-TW
Published: 2008
Online Access:http://ndltd.ncl.edu.tw/handle/91429178110555648960
id ndltd-TW-096THMU8112007
record_format oai_dc
spelling ndltd-TW-096THMU81120072015-10-13T14:49:20Z http://ndltd.ncl.edu.tw/handle/91429178110555648960 A New Algorithm for Pattern Recognition Based on Ring Approach 基於環形原理的一種新式比對技術 Ching-Ling Lai 賴慶霖 碩士 亞洲大學 生物資訊學系碩士班 96 Template matching is one of the most active research areas in pattern recognition. It is also a critical step of image analysis. Traditional methods for template matching have encountered many problems and limitations. Among them, rotation-invariance is the most challenging one. Ring approach inherently bears low computational complexity and is easy to overcome the rotation-invariance problem while matching. This research is based upon the concept of ring approach to develop a new template matching algorithm --‘Eight-way Sampling’. It efficiently improves the robustness of the ring approach algorithm when template matching circular-like objects. Considering simpler sampling strategy, rotation-invariance, and robustness for incomplete and overlapping patterns, the algorithm proposed can be a promising solution for circular-like object template matching. Cheng-Yu Lee 李正宇 2008 學位論文 ; thesis 73 zh-TW
collection NDLTD
language zh-TW
format Others
sources NDLTD
description 碩士 === 亞洲大學 === 生物資訊學系碩士班 === 96 === Template matching is one of the most active research areas in pattern recognition. It is also a critical step of image analysis. Traditional methods for template matching have encountered many problems and limitations. Among them, rotation-invariance is the most challenging one. Ring approach inherently bears low computational complexity and is easy to overcome the rotation-invariance problem while matching. This research is based upon the concept of ring approach to develop a new template matching algorithm --‘Eight-way Sampling’. It efficiently improves the robustness of the ring approach algorithm when template matching circular-like objects. Considering simpler sampling strategy, rotation-invariance, and robustness for incomplete and overlapping patterns, the algorithm proposed can be a promising solution for circular-like object template matching.
author2 Cheng-Yu Lee
author_facet Cheng-Yu Lee
Ching-Ling Lai
賴慶霖
author Ching-Ling Lai
賴慶霖
spellingShingle Ching-Ling Lai
賴慶霖
A New Algorithm for Pattern Recognition Based on Ring Approach
author_sort Ching-Ling Lai
title A New Algorithm for Pattern Recognition Based on Ring Approach
title_short A New Algorithm for Pattern Recognition Based on Ring Approach
title_full A New Algorithm for Pattern Recognition Based on Ring Approach
title_fullStr A New Algorithm for Pattern Recognition Based on Ring Approach
title_full_unstemmed A New Algorithm for Pattern Recognition Based on Ring Approach
title_sort new algorithm for pattern recognition based on ring approach
publishDate 2008
url http://ndltd.ncl.edu.tw/handle/91429178110555648960
work_keys_str_mv AT chinglinglai anewalgorithmforpatternrecognitionbasedonringapproach
AT làiqìnglín anewalgorithmforpatternrecognitionbasedonringapproach
AT chinglinglai jīyúhuánxíngyuánlǐdeyīzhǒngxīnshìbǐduìjìshù
AT làiqìnglín jīyúhuánxíngyuánlǐdeyīzhǒngxīnshìbǐduìjìshù
AT chinglinglai newalgorithmforpatternrecognitionbasedonringapproach
AT làiqìnglín newalgorithmforpatternrecognitionbasedonringapproach
_version_ 1717757665617117184