Boosting-Based Face Detection and Adaptation (Paperback)
暫譯: 基於增強的臉部偵測與適應
Cha Zhang, Zhengyou Zhang
- 出版商: Morgan & Claypool
- 出版日期: 2010-10-22
- 售價: $1,620
- 貴賓價: 9.5 折 $1,539
- 語言: 英文
- 頁數: 140
- 裝訂: Paperback
- ISBN: 160845133X
- ISBN-13: 9781608451333
海外代購書籍(需單獨結帳)
買這商品的人也買了...
-
$1,400$1,330 -
$990Android Apps with App Inventor: The Fast and Easy Way to Build Android Apps (Paperback)
-
$420$378 -
$520$442 -
$480$432 -
$403Unity AR 增強現實完全自學教程 (全彩)
-
$594$564 -
$449Adobe Audition 聲音後期處理實戰手冊, 2/e
-
$383中文版Adobe Audition CC 2020從入門到精通
-
$407統計學入門:文科生也能看得懂的統計學, 5/e
-
$620$490 -
$480$379 -
$540$486 -
$550$434 -
$600$474 -
$480$336 -
$3,468The R Book, 3/e (Hardcover)
-
$500$395 -
$580$493 -
$450$383 -
$980$774 -
$560$442 -
$780$608 -
$680$537 -
$680$537
商品描述
Face detection, because of its vast array of applications, is one of the most active research areas in computer vision. In this book, we review various approaches to face detection developed in the past decade, with more emphasis on boosting-based learning algorithms. We then present a series of algorithms that are empowered by the statistical view of boosting and the concept of multiple instance learning. We start by describing a boosting learning framework that is capable to handle billions of training examples. It differs from traditional bootstrapping schemes in that no intermediate thresholds need to be set during training, yet the total number of negative examples used for feature selection remains constant and focused (on the poor performing ones). A multiple instance pruning scheme is then adopted to set the intermediate thresholds after boosting learning. This algorithm generates detectors that are both fast and accurate. Table of Contents: A Brief Survey of the Face Detection Literature / Cascade-based Real-Time Face Detection / Multiple Instance Learning for Face Detection / Detector Adaptation / Other Applications / Conclusions and Future Work
商品描述(中文翻譯)
人臉檢測因其廣泛的應用而成為計算機視覺中最活躍的研究領域之一。在本書中,我們回顧了過去十年中開發的各種人臉檢測方法,並更強調基於提升(boosting)的學習算法。我們接著介紹了一系列受統計提升觀點和多實例學習概念驅動的算法。我們首先描述了一個能夠處理數十億訓練範例的提升學習框架。它與傳統的自助抽樣(bootstrapping)方案不同,因為在訓練過程中不需要設置中間閾值,但用於特徵選擇的負範例總數保持不變且集中(在表現不佳的範例上)。然後採用多實例修剪方案在提升學習後設置中間閾值。這個算法生成的檢測器既快速又準確。
目錄:
- 人臉檢測文獻簡要調查
- 基於級聯的實時人臉檢測
- 用於人臉檢測的多實例學習
- 檢測器適應
- 其他應用
- 結論與未來工作