Language:
繁體中文
English
日文
說明(常見問題)
南開科技大學
圖書館首頁
編目中圖書申請
登入
回首頁
切換:
標籤
|
MARC模式
|
ISBD
Contributions to real time shape det...
~
The University of Texas at Dallas.
Contributions to real time shape detection with applications to face detection.
紀錄類型:
書目-電子資源 : 單行本
正題名/作者:
Contributions to real time shape detection with applications to face detection./
作者:
Wu, Feng.
面頁冊數:
120 p.
附註:
Source: Dissertation Abstracts International, Volume: 67-10, Section: B, page: 5867.
Contained By:
Dissertation Abstracts International67-10B.
標題:
Computer Science. -
電子資源:
Download PDF (下載PDF全文)
ISBN:
9780542932892
Contributions to real time shape detection with applications to face detection.
Wu, Feng.
Contributions to real time shape detection with applications to face detection.
- 120 p.
Source: Dissertation Abstracts International, Volume: 67-10, Section: B, page: 5867.
Thesis (Ph.D.)--The University of Texas at Dallas, 2006.
Shape-detection is a critical component in many computer vision systems. Large variety of shapes, lighting conditions, and the high dimensionality of image data make shape-detection a challenging problem. Our research is focused on developing techniques for improving both the accuracy and the speed of shape and object detection. We first describe contributions to the classic normalized template-matching technique. Based on the concept of integral images, we have developed an approximate normalized template-matching method, which can be much faster (100 times faster in typical applications) than the classic normalized template-matching method. In typical template-matching based shape-detection, matching needs to be performed at every possible template location in the image and at multiple image resolutions. We introduce the idea of local maxima and describe a selective template matching method. In this approach, matching values are computed only at selective locations, resulting in additional speed-up of the run time.
ISBN: 9780542932892Subjects--Topical Terms:
1000005419
Computer Science.
Contributions to real time shape detection with applications to face detection.
LDR
:03525nmm 2200289 4500
001
1000004936
005
20070601084737.5
008
070601s2006 eng d
020
$a
9780542932892
035
$a
(UnM)AAI3238615
035
$a
AAI3238615
040
$a
UnM
$c
UnM{me_controlnum}
100
1
$a
Wu, Feng.
$3
1000006093
245
1 0
$a
Contributions to real time shape detection with applications to face detection.
300
$a
120 p.
500
$a
Source: Dissertation Abstracts International, Volume: 67-10, Section: B, page: 5867.
500
$a
Adviser: Haim Schweitzer.
502
$a
Thesis (Ph.D.)--The University of Texas at Dallas, 2006.
520
$a
Shape-detection is a critical component in many computer vision systems. Large variety of shapes, lighting conditions, and the high dimensionality of image data make shape-detection a challenging problem. Our research is focused on developing techniques for improving both the accuracy and the speed of shape and object detection. We first describe contributions to the classic normalized template-matching technique. Based on the concept of integral images, we have developed an approximate normalized template-matching method, which can be much faster (100 times faster in typical applications) than the classic normalized template-matching method. In typical template-matching based shape-detection, matching needs to be performed at every possible template location in the image and at multiple image resolutions. We introduce the idea of local maxima and describe a selective template matching method. In this approach, matching values are computed only at selective locations, resulting in additional speed-up of the run time.
520
$a
The detection and the recognition of shapes is typically performed on a small number of useful features. The selection of good features requires processing large amounts of data and is very time consuming. The standard approach to feature-selection is to compute many features from training data, and then select among them a subset that is useful for the task at hand. We have developed a fast selection method that works for linear features. Our approach is based on Principal Components dimensionality reduction on the training data. We show that it is not necessary to compute features for all the training data; instead, one needs only compute features for the principal components. Specifically, redundant features are identified using the classic QR Factorization algorithm, applied in the reduced space.
520
$a
AdaBoosting is a recently developed powerful method for selecting a small set of features and constructing a classifier that uses these features. The standard AdaBoosting technique is symmetric in its treatment of the positive and the negative training examples. However, when AdaBoosting is applied in object-detection, the positive examples are significantly more important than the negative examples. For example, when AdaBoosting is applied to face detection, the positive examples are examples of human faces. It is less clear what are good examples of non-faces. We have developed an asymmetric formulation of AdaBoosting that allows a specified bias toward the positive examples that behaves better in such cases.
590
$a
School code: 0382.
650
4
$a
Computer Science.
$3
1000005419
690
$a
0984
710
2 0
$a
The University of Texas at Dallas.
$3
1000006094
773
0
$t
Dissertation Abstracts International
$g
67-10B.
790
1 0
$a
Schweitzer, Haim,
$e
advisor
790
$a
0382
791
$a
Ph.D.
792
$a
2006
856
4 0
$u
http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3238615
$z
Download PDF (下載PDF全文)
0 筆讀者評論
館藏地:
全部
線上資料庫
出版年:
卷號:
館藏
1 筆 • 頁數 1 •
1
條碼號
典藏地名稱
館藏流通類別
資料類型
索書號
使用類型
借閱狀態
預約人數
備註欄
附件
OE0000911
線上資料庫
線上資源
線上電子書
OE
一般(Normal)
在架
0
1 筆 • 頁數 1 •
1
多媒體
評論
新增評論
分享你的心得
建立或儲存個人書籤
書目轉出
取書館別
處理中
...
變更密碼
登入