東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Adaptive mean shift-based image segm...

St. Francis Xavier University (Canada).

FindBook

Google Book

Amazon

博客來

Adaptive mean shift-based image segmentation using multiple instance learning.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Adaptive mean shift-based image segmentation using multiple instance learning./
作者:	Xu, Tao.
面頁冊數:	117 p.
附註:	Source: Masters Abstracts International, Volume: 47-06, page: .
Contained By:	Masters Abstracts International47-06.
標題:	Artificial Intelligence. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=MR50501
ISBN:	9780494505014

Adaptive mean shift-based image segmentation using multiple instance learning.
Xu, Tao.

Adaptive mean shift-based image segmentation using multiple instance learning. - 117 p.

Source: Masters Abstracts International, Volume: 47-06, page: .

Thesis (M.Sc.)--St. Francis Xavier University (Canada), 2009.

Image segmentation plays a key role in a range of subfields of computer vision, including content-based image retrieval, object recognition, mobile object tracking, medical imaging, etc. However, strong segmentation, which corresponds to the process of partitioning an image into meaningful regions, remains a difficult and as yet unsolved problem. Bottom-up approaches utilize color, texture and other low-level visual features to partition images into homogeneous regions. However, regions that are homogeneous in low-level visual content do not necessarily (and usually do not) correspond to meaningful objects. This is mainly due to the lack of correspondence between low-level visual features and high-level semantics, which is known as the semantic gap. Hence, in recent years, much research interest on this topic has been focused on top-down designs that introduce high-level cues into the segmentation process.

ISBN: 9780494505014Subjects--Topical Terms:

769149
Artificial Intelligence.

Adaptive mean shift-based image segmentation using multiple instance learning.
LDR:03317nmm 2200265 a 45 001 887307
005 20101020
008 101020s2009 ||||||||||||||||| ||eng d
020 $a 9780494505014
035 $a (UMI)AAIMR50501
035 $a AAIMR50501
040 $a UMI $c UMI
100 1 $a Xu, Tao. $3 1059048
245 1 0 $a Adaptive mean shift-based image segmentation using multiple instance learning.
300 $a 117 p.
500 $a Source: Masters Abstracts International, Volume: 47-06, page: .
502 $a Thesis (M.Sc.)--St. Francis Xavier University (Canada), 2009.
520 $a Image segmentation plays a key role in a range of subfields of computer vision, including content-based image retrieval, object recognition, mobile object tracking, medical imaging, etc. However, strong segmentation, which corresponds to the process of partitioning an image into meaningful regions, remains a difficult and as yet unsolved problem. Bottom-up approaches utilize color, texture and other low-level visual features to partition images into homogeneous regions. However, regions that are homogeneous in low-level visual content do not necessarily (and usually do not) correspond to meaningful objects. This is mainly due to the lack of correspondence between low-level visual features and high-level semantics, which is known as the semantic gap. Hence, in recent years, much research interest on this topic has been focused on top-down designs that introduce high-level cues into the segmentation process.
520 $a In the context of content-based image retrieval, relevance feedback learning has been successfully used in the past as a means of reducing the semantic gap. Inspired by this, we developed in this thesis an adaptive image segmentation framework that achieves a task-dependent top-down adaption of the scale parameters of the mean shift-based segmentation algorithm. Different from previous learning-based segmentation schemes, the proposed method requires neither manual segmentations as training samples nor prior object-specific knowledge for parameter learning. This is made possible based on the assumption that the visual appearance of a particular object model has a Unique distribution in the feature space. Thus, once a quantized representation of this distribution is obtained through a learning-based means, an improved segmentation for images of the same object model can be conducted. More specifically, under the context of a content-based image retrieval system, each image in the retrieval set is labeled either positive or negative depending on the presence of an object of interest. Extracted features of labeled images constitute the training samples for multiple instance learning, which in turn induces a mapping from the object of interest to the scale parameters of the mean shift-based segmentation algorithm. Once the mapping is established, it is incorporated into the segmentation procedure so as to improve the performance for images of the same object model. Experimental results indicate both the capability and flexibility of our proposed method for practical usage.
590 $a School code: 1367.
650 4 $a Artificial Intelligence. $3 769149
650 4 $a Computer Science. $3 626642
690 $a 0800
690 $a 0984
710 2 $a St. Francis Xavier University (Canada). $3 1020611
773 0 $t Masters Abstracts International $g 47-06.
790 $a 1367
791 $a M.Sc.
792 $a 2009
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=MR50501