Relevance Feedback Based on Feature Discreteness for Image Content Retrieval
碩士 === 國立臺南大學 === 數位學習科技學系碩士班 === 97 === We propose a new relevance feedback approach to achieving high system accuracy for image content retrieval and high flexibility in selecting features of interest. Our system is divided into two major phases, namely index map construction and query comparison....
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Online Access: | http://ndltd.ncl.edu.tw/handle/98308150758227987982 |
id |
ndltd-TW-097NTNT5395032 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-097NTNT53950322016-05-02T04:11:51Z http://ndltd.ncl.edu.tw/handle/98308150758227987982 Relevance Feedback Based on Feature Discreteness for Image Content Retrieval 以特徵離散性為基礎的影像內容檢索相關回饋機制 Ya-ting Gu 辜雅婷 碩士 國立臺南大學 數位學習科技學系碩士班 97 We propose a new relevance feedback approach to achieving high system accuracy for image content retrieval and high flexibility in selecting features of interest. Our system is divided into two major phases, namely index map construction and query comparison. In the phase of index map construction, ten MPEG-7 descriptors and six Tamura features are extracted from each database image. For each color or texture feature, database images are clustered by a self-organizing map and then an index map is constructed. In the phase of query comparison, a user can submit a query image and select features of interest. To search similar images from the database, we propose an image voting scheme. In each index map, database images that belong to the same cluster with the query are cast a vote. For each database image, its vote in each map is accumulated and the sum is regarded as the similarity to the query. If the retrieval result is not satisfied, the user can select relevant images as a new query. To improve the retrieval result, we propose a vote re-weighting scheme based on feature discreteness of relevant images. The database images that most similar to relevant images can be retrieved. Experimental results reveal the effectiveness of our approach. Hsin-Chih Lin 林信志 學位論文 ; thesis 58 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立臺南大學 === 數位學習科技學系碩士班 === 97 === We propose a new relevance feedback approach to achieving high system accuracy for image content retrieval and high flexibility in selecting features of interest. Our system is divided into two major phases, namely index map construction and query comparison. In the phase of index map construction, ten MPEG-7 descriptors and six Tamura features are extracted from each database image. For each color or texture feature, database images are clustered by a self-organizing map and then an index map is constructed. In the phase of query comparison, a user can submit a query image and select features of interest. To search similar images from the database, we propose an image voting scheme. In each index map, database images that belong to the same cluster with the query are cast a vote. For each database image, its vote in each map is accumulated and the sum is regarded as the similarity to the query. If the retrieval result is not satisfied, the user can select relevant images as a new query. To improve the retrieval result, we propose a vote re-weighting scheme based on feature discreteness of relevant images. The database images that most similar to relevant images can be retrieved. Experimental results reveal the effectiveness of our approach.
|
author2 |
Hsin-Chih Lin |
author_facet |
Hsin-Chih Lin Ya-ting Gu 辜雅婷 |
author |
Ya-ting Gu 辜雅婷 |
spellingShingle |
Ya-ting Gu 辜雅婷 Relevance Feedback Based on Feature Discreteness for Image Content Retrieval |
author_sort |
Ya-ting Gu |
title |
Relevance Feedback Based on Feature Discreteness for Image Content Retrieval |
title_short |
Relevance Feedback Based on Feature Discreteness for Image Content Retrieval |
title_full |
Relevance Feedback Based on Feature Discreteness for Image Content Retrieval |
title_fullStr |
Relevance Feedback Based on Feature Discreteness for Image Content Retrieval |
title_full_unstemmed |
Relevance Feedback Based on Feature Discreteness for Image Content Retrieval |
title_sort |
relevance feedback based on feature discreteness for image content retrieval |
url |
http://ndltd.ncl.edu.tw/handle/98308150758227987982 |
work_keys_str_mv |
AT yatinggu relevancefeedbackbasedonfeaturediscretenessforimagecontentretrieval AT gūyǎtíng relevancefeedbackbasedonfeaturediscretenessforimagecontentretrieval AT yatinggu yǐtèzhēnglísànxìngwèijīchǔdeyǐngxiàngnèiróngjiǎnsuǒxiāngguānhuíkuìjīzhì AT gūyǎtíng yǐtèzhēnglísànxìngwèijīchǔdeyǐngxiàngnèiróngjiǎnsuǒxiāngguānhuíkuìjīzhì |
_version_ |
1718254784211845120 |