多重物體凸形輪廓定位之研究

RESEARCH ON LOCATING THE CONVEX HULL OF MULTIPLE OBJECTS

張嘉元(Chia-Yuan Chang)

指導教授 ： 陳永盛

元智大學/工程學院/電機與資訊工程研究所/碩士(1998年)

摘要

基於人類視覺而言，若想從一幅影像中區分出各個獨立的物件，簡直是一件易如反掌的事。
但直至今日，科學家們尚未發展出一套完全模擬人類視覺的系統。
不過令人欣慰的是如今電腦科技的突飛猛進，也使得各方面的數位影像處理技術跟隨著提升，
一些過去不易處理的問題也都可被輕鬆地解決。
物件輪廓萃取在許多影像處理與圖形辨識領域中是不可或缺的技術。
因此我們本著主動輪廓模型與動態規劃的精神提出一種可適用於多重物件輪廓分離的演算法則。
其中也衍生與使用許多技術，諸如：區塊產生、邊界產生、物件萃取、凸形輪廓等等，
在本篇論文中將有詳細介紹，並有實驗結果來佐證。

關鍵字

物件輪廓萃取 ； 凸形輪廓 ； 主動輪廓模型 ； 動態規劃

並列摘要

The object contour extracted from an image by human vision is a piece of cake action.
Up to date, scientist has not yet found a successful system to explain and match human vision in present-day world.
Whatever, the computational technique has lot of progress today that many problems of image processing can be solved more easily.
The contour extraction of objects is of great importance in many fields of image processing and pattern recognition.
In this thesis, we present an approach to locating multiple objects in an image based on the principle criterion of active contour model
and dynamic programming. Many fundamental techniques will be adopted to realize the function of multi-object location,
they are the computations on a histogram, gradient distribution, thresholding, labeling, convex hull, etc.
The region planes and boundary planes are operated with these fundamental techniques as well as an iteration procedure
to extract the object contours processing convexity. The experimental results show the feasibility of the proposed approach.

並列關鍵字

Object Contour Extraction ； Convex Hull ； Active Contour Model ； Dynamic Programming

參考文獻

[1] J. F. Canny, "A Computational Approach to Edge Detection," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 8, No. 6, pp. 679-698, 1986.

[2] J. B. Burns, and A. R. Hanson, "Extraction Straight Lines," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 8, No. 1, pp. 11-15, 1986.

[3] V. Venkateswar and R. Chellappa, "Extraction of Straight Lines in Aerial Images," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 14, No. 11, pp. 1111-1114, 1992.

[5] G. Sperling, "Binocular vision: a physical and neural," AM. J. PSYCHOLOGY, Vol. 83, pp. 461-534, 1970.

[6] Y. He and A. Kundu, Ŗ-D Shape Classification Using Hidden Markov Model," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 13, No. 11, pp. 1172-1184, 1991.