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

Adapting learning techniques for vis...

University of California, Berkeley.

FindBook

Google Book

Amazon

博客來

Adapting learning techniques for visual recognition.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Adapting learning techniques for visual recognition./
作者:	Zhang, Hao.
面頁冊數:	107 p.
附註:	Adviser: Jitendra Malik.
Contained By:	Dissertation Abstracts International69-05B.
標題:	Artificial Intelligence. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3311694
ISBN:	9780549611974

Adapting learning techniques for visual recognition.
Zhang, Hao.

Adapting learning techniques for visual recognition. - 107 p.

Adviser: Jitendra Malik.

Thesis (Ph.D.)--University of California, Berkeley, 2007.

This thesis builds on previous work on shape matching techniques in computer vision, and classification techniques in machine learning. It tries to model the visual recognition task as one based on comparison to prototypes. Careful attention is paid to insights from perception and neuroscience on the nature of human visual similarity.

ISBN: 9780549611974Subjects--Topical Terms:

769149
Artificial Intelligence.

Adapting learning techniques for visual recognition.
LDR:03241nam 2200337 a 45 001 852991
005 20100701
008 100701s2007 ||||||||||||||||| ||eng d
020 $a 9780549611974
035 $a (UMI)AAI3311694
035 $a AAI3311694
040 $a UMI $c UMI
100 1 $a Zhang, Hao. $3 1019140
245 1 0 $a Adapting learning techniques for visual recognition.
300 $a 107 p.
500 $a Adviser: Jitendra Malik.
500 $a Source: Dissertation Abstracts International, Volume: 69-05, Section: B, page: 3080.
502 $a Thesis (Ph.D.)--University of California, Berkeley, 2007.
520 $a This thesis builds on previous work on shape matching techniques in computer vision, and classification techniques in machine learning. It tries to model the visual recognition task as one based on comparison to prototypes. Careful attention is paid to insights from perception and neuroscience on the nature of human visual similarity.
520 $a Classifying hand written digits has been heavily researched, and serves as a clearly-defined shape matching problem. One contribution of this thesis is a prototype-based classifier that drastically reduces the number of prototypes needed for the nearest neighbor technique.
520 $a A second contribution of this thesis is a technique for determining what parts of the shape are most informative for classification. This notion can be formalized in the framework of "feature selection" as in machine learning. The study of discriminative power from feature selection yields insight on (1) the usefulness of individual parts of the shape (2) the classification process of a general linear model classifier on shape data.
520 $a The most significant contribution of this thesis is a new learning technique for visual categorization, "SVM-KNN", which draws on aspects of two well known techniques: support vector machines (SVM) and K-nearest neighbor. The basic idea is to find close neighbors to a query sample and train a local support vector machine that preserves the distance function on the collection of neighbors. This technique is a good match to the unique challenges of general visual recognition: hugely multi-class, few training examples per class, and high variation within class. This approach is quite flexible, and permits recognition based on color, texture, and particularly shape, in a homogeneous framework.
520 $a Our hybrid method has reasonable computational complexity both in training and at run time, and yields excellent results in practice. A wide variety of distance functions can be used and experiments show state-of-the-art performance on a number of benchmark data sets of shape and texture classification (MNIST, USPS, CUReT) and object recognition (Caltech-101). On Caltech-101, the technique achieved a correct classification rate of 62.42%(+/-0.41%) using only fifteen training examples, outperforming other published approaches at the time.
590 $a School code: 0028.
650 4 $a Artificial Intelligence. $3 769149
650 4 $a Biology, Neuroscience. $3 1017680
650 4 $a Computer Science. $3 626642
690 $a 0317
690 $a 0800
690 $a 0984
710 2 $a University of California, Berkeley. $3 687832
773 0 $t Dissertation Abstracts International $g 69-05B.
790 $a 0028
790 1 0 $a Malik, Jitendra, $e advisor
791 $a Ph.D.
792 $a 2007
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3311694