Multi-CAMSHIFT應用於多角度人臉追蹤與辨識

Multi-CAMSHIFT for Multi-View Faces Tracking and Recognition

林俊廷(Chun-Ting Lin)

指導教授 ： 黃漢邦

國立臺灣大學/工學院/機械工程學研究所/碩士(2005年)

https://doi.org/10.6342/NTU.2005.10247

摘要

本文的主要目的為發展多物件影像追蹤與多角度人臉偵測與辨識系統。我們提出Multi-CAMSHIFT來實現多物件追蹤，利用所感興趣的機率分布特性，例如：顏色、形狀，快速追蹤出物件輪廓以作為候選區域。整個系統架構於多解析度機制之上，可以有效改善系統效能並且降低龐大的運算量。配合多組主成分分析(PCA)和支持向量機(SVM)，利用不同角度的奇異臉分析，結合成多角度人臉偵測與辨識模組，對於不同人臉姿勢加以分類與身分辨識。
我們的系統可應用於複雜背景以及即時追蹤，並且利用機率模型的更新機制，有效解決緩慢光源的變化。我們將上述的方法以及理論，成功地實現多角度人臉追蹤與辨識，並且應用於監測系統、人形追蹤和人臉辨識門禁等各系統。

關鍵字

人臉 ； 追蹤 ； 偵測 ； 辨識 ； 多角度人臉 ； 主成分分析 ； 支持向量機

並列摘要

This thesis, aims to develop a system for multiple objects tracking and multi-view faces detection and recognition. We propose a novel method (Multi-CAMSHIFT), which is based on the characteristics of color and shape probability distribution, to solve the tracking problems for multiple objects. The tracker is used to get the candidate regions by outlining the interested probability distribution. The system performance is further improved by using multi-resolution framework and computation reduction. The principal component analysis (PCA) and support vector machine (SVM) are integrated to form the multi-view faces detection and recognition module for classifying different face poses and identities. Beside color information, the gray background image is used to locate the human head in the region of tracking pedestrian based on probability distribution rule. The rule can also be used for skin color face tracking to remove background region (non-face region).
Since the proposed Multi-CAMSHIFT (MCAMSHIFT) is computationally efficient, it can work in complex background and track in real-time. The slowly changing lighting condition is effectively resolved using probability model update. From experiments, the proposed MCAMSHIFT was successfully applied to multi-view faces tracking and recognition. It can also be applied to surveillance system, pedestrian tracking and face guard systems.

並列關鍵字

face ； tracking ； detection ； recognition ； multi-view ； PCA ； SVM

參考文獻

[5] B. Castaneda, J. C. Cockkburn, “Reduce Support Vector Machines Applied to Real-Time Face Tracking,” ICASSP’05, Vol. 2, pp. 673-676, 2005.

[6] C. C. Chang, C. J. Lin, “LIBSVM: A Library for Support Vector Machines,” http://www.csie.ntu.edu.tw/~cjlin/libsvm, 2001.

[7] T. C. Chang, T. S. Huang, and C. Novak, “Facial Feature Extraction from Color Image,” Proceedings of the 12th International Conference on Pattern Recognition, Vol. 2, pp. 39-43, 1994.

[8] R. Chellappa, C. L. Wilson, and S. Sirohey. “Human and Machine Recognition of Faces: A Survey,” Proceedings of IEEE, pp. 705-741, 1995.

[9] Y. Cheng, “Mean Shift, Mode Seeking, and Clustering,” IEEE Transactions on Pattern Analysis Machine Intelligence, Vol. 17, pp. 790-799, 1995.