查詢結果分析
來源資料
頁籤選單縮合
| 題 名 | 複雜背景中人臉偵測快速演算法則=An Efficient Region-Based Algorithm for Detecting Human Faces in Complex Background |
|---|---|
| 作 者 | 何信瑩; 施東和; | 書刊名 | 逢甲學報 |
| 卷 期 | 33 1998.06[民87.06] |
| 頁 次 | 頁135-155 |
| 分類號 | 312.1 |
| 關鍵詞 | 人臉偵測; 人臉識別; 邊緣偵測; 圖形識別; Face detection; Face recognition; Edge detection; Pattern recognition; |
| 語 文 | 中文(Chinese) |
| 中文摘要 | 本文提出一個複雜背景中人臉偵測快速演算法則。此演算法則是一個以事先學習 知識為基底而以邊緣偵測之邊線所形成之區域特徵為導向的階層式架構。在第一階層中,找 尋經由邊緣偵測後影像之局部最大空白區域來推論可能的人臉臉頰所在。第二階層主要採用 經由自動學習人臉特徵所得的加權遮罩作為人臉之整體性特徵來快速找出人臉的候選者。第 三階層是根據人臉之眼、鼻、口和臉頰等局部特徵所建立的臉部特徵向量對人臉之候選者做 精確判別。實驗結果證明所提方法能快速在複雜影像中偵測出不同大小之人臉並定位。 |
| 英文摘要 | In this paper an efficient region-based algorithm to locate human faces in a complex background in which both the location and the size of a face are unknown is proposed. A hierarchical knowledge-based approach using region features formed by edge features of the human face is utilized in our algorithm which consists of three levels. At level 1, after edge detection process the local maximum rectangulat blanks in an unknown image, regarded as the necessary portions of the possible human faces are found. At level 2, the candidate human faces are selected using the weighting mask as the global features of a face obtained from the machine learning using a lot of human face samples. At level 3, a face feature vector representing the local features of the eyes, nose, mouth and eyebrows is used for the fine matching with each candidate human face. Experimental results show that the proposed algorithm for detecting and locating human faces in a complex background is fast and robust. |
本系統中英文摘要資訊取自各篇刊載內容。