虹膜病灶特徵辨識方法

A Method For Identifying Nidus In The Iridology

陳國宏(Kuo-Hung Chen)

指導教授 ： 劉 啟 東

朝陽科技大學/資訊學院/資訊工程系/碩士(2010年)

摘要

虹膜學發展已經超過100 年，虹膜可反應出個人的身體的健康狀
況與疾病，本篇論文運用影像處理的演算法，來鑑定與辨別虹膜影像
的標記資訊，使用Canny 邊緣偵測運算子來定位病灶上局部的邊緣，
並運用曲線擬合的方法來確認橢圓形的病灶，實驗的結果顯示出能夠
有效的確認出虹膜上的樣本，經過測試的影像共14 張，5 張具有病
灶特徵、另外9 張則不具有病灶特徵，正確辨識率為85.2%、錯誤辨
識率為29.4%，本論文主要目的在於偵測出虹膜上的開放與封閉式病
灶。

關鍵字

橢圓擬合 ； 邊緣偵測 ； 虹膜學

並列摘要

Iridology has developed more than 100 years, the iris can reflect a
person''s state of health and systemic disease. In this paper we present a
method to identify and discriminate the signature information in iris
images. We use Canny edge detector to locate the partial edge of lacuna.
We then use curve fitting method to identify the elliptic lacuna. The
experimental results show that we can identify iris pattern automatically
and efficiently. The proposed method had tested on 14 images, 5 of them
contain lacuna area and 9 contain false lacuna area. We had achieved
identification rate 85.2% and miss identification rate 29.4%. The goal of
this paper is to detect the location of open or closed patterns in iris.

並列關鍵字

Ellipse fitting ； Edge detection ； Iridology

參考文獻

[1] A.D.Wibawa and M.H.Purnomo, ”Early Detection on the Condition of Pancreas Organ as the Cause of Diabetes Mellitus by Real Time Iris Image Processing,” IEEE Asia Pacific Conference on Circuits and Systems, 2006.

[5] B. Jensen, Iridology Simplificated. fifth edition, 1980.

[7] Rafael C. Gonzalez, Richard E. Woods, Digital Image Processing Prentice-Hall, Second Edition, 2002.

[8] J. Canny, “A computational approach to edge detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, Vol. 8, No.6, pp. 679-698.

[11] L. Xu, E. Oja, and P. Kultanan, “A new curve detection method: randomized Hough transform (RHT),” Pattern Recognition Letters, 1990,Vol. 11, No. 5, pp. 331-338.