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

An improved saliency mechanism for c...

Emami, Mohsen.

FindBook

Google Book

Amazon

博客來

An improved saliency mechanism for computer vision.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	An improved saliency mechanism for computer vision./
作者:	Emami, Mohsen.
面頁冊數:	134 p.
附註:	Source: Dissertation Abstracts International, Volume: 75-02(E), Section: B.
Contained By:	Dissertation Abstracts International75-02B(E).
標題:	Engineering, Mechanical. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3598899
ISBN:	9781303478581

An improved saliency mechanism for computer vision.
Emami, Mohsen.

An improved saliency mechanism for computer vision. - 134 p.

Source: Dissertation Abstracts International, Volume: 75-02(E), Section: B.

Thesis (Ph.D.)--Oklahoma State University, 2013.

The objective of this project is to find an efficient biologically plausible model for the bottom-up saliency mechanism of the human vision system (HVS) and employ it in computer vision applications. In practice, analyzing or storing all information entering the human eye at every moment is beyond the capabilities of the human neural system. The saliency mechanism controls the process of selecting and allocating attention to the most "prominent" locations in the scene, which are mostly referred to as "salient points" or "interesting points" in the literature. The same problem of information overload exists in most of the computer vision applications and an efficient visual saliency model can help reducing time consumption of the algorithm. These applications comprise, but are not limited to, automatic target detection, robotics and image and video compression.

ISBN: 9781303478581Subjects--Topical Terms:

783786
Engineering, Mechanical.

An improved saliency mechanism for computer vision.
LDR:03018nam a2200301 4500 001 1964272
005 20141015113824.5
008 150210s2013 ||||||||||||||||| ||eng d
020 $a 9781303478581
035 $a (MiAaPQ)AAI3598899
035 $a AAI3598899
040 $a MiAaPQ $c MiAaPQ
100 1 $a Emami, Mohsen. $3 2100687
245 1 3 $a An improved saliency mechanism for computer vision.
300 $a 134 p.
500 $a Source: Dissertation Abstracts International, Volume: 75-02(E), Section: B.
500 $a Adviser: Larry L. Hoberock.
502 $a Thesis (Ph.D.)--Oklahoma State University, 2013.
520 $a The objective of this project is to find an efficient biologically plausible model for the bottom-up saliency mechanism of the human vision system (HVS) and employ it in computer vision applications. In practice, analyzing or storing all information entering the human eye at every moment is beyond the capabilities of the human neural system. The saliency mechanism controls the process of selecting and allocating attention to the most "prominent" locations in the scene, which are mostly referred to as "salient points" or "interesting points" in the literature. The same problem of information overload exists in most of the computer vision applications and an efficient visual saliency model can help reducing time consumption of the algorithm. These applications comprise, but are not limited to, automatic target detection, robotics and image and video compression.
520 $a In the report herein, the general architecture of models of the HVS saliency mechanism is presented and some of the well-known models are illustrated. There are several metrics to compare saliency models; however, results from different metrics vary widely in evaluating models. Since it is important to know which models perform the best in mimicking the saliency mechanism of the human visual system, first a procedure is proposed for evaluating metrics for comparing saliency maps using a database of human fixations on approximately 1000 images. This procedure is then employed to identify the best metric. This best metric is then used to evaluate nine published bottom-up saliency models on two databases, one containing natural images and the other synthetic ones. Furthermore, a new method for normalizing feature saliency maps in the saliency detection mechanisms is introduced. Also, the best visual saliency model in the literature is modified to overcome some deficiencies by automatically selecting different parameters for different regions of the image. As an application of the models of the saliency mechanisms, a saliency mechanism with the new normalization method is then applied to dishware inspection that shows interesting results.
590 $a School code: 0664.
650 4 $a Engineering, Mechanical. $3 783786
650 4 $a Engineering, Robotics. $3 1018454
650 4 $a Engineering, Computer. $3 1669061
690 $a 0548
690 $a 0771
690 $a 0464
710 2 $a Oklahoma State University. $b Mechanical Engineering. $3 1043227
773 0 $t Dissertation Abstracts International $g 75-02B(E).
790 $a 0664
791 $a Ph.D.
792 $a 2013
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3598899