指紋辨識系統之研究

A Study on the Fingerprint Recognition System.

翁上景(Shang-Ching Weng)

指導教授 ： 涂世雄

中原大學/工學院/電機工程研究所/碩士(2011年)

https://doi.org/10.6840/cycu201100089

摘要

摘要
隨著人工智慧和自動化科學的快速發展，更實現了指紋識別多的研究興趣。隨著幾十年的發展，指紋自動識別系統建立了相應的計算機上從宏觀到微觀電腦，甚至到嵌入式處理器。中的應用指紋也發展到從軍事上的應用日常生活。
為了解決這個問題，指紋識別，指紋識別算法進行了詳細的在這個文件，該文件是從指紋採集範圍，指紋的預處理，指紋識別真正的指紋算法，識別系統。首先，指紋識別的原則，研究了細節，和指紋識別系統績效評估進行了討論。然後預其中包括指紋分割加工，指紋圖像增強，指紋二值化，並指紋細化指紋識別探索。指紋特徵提取 前處理指紋圖像，為以後的使用指紋識別程序。阿全等三角形匹配的快速指紋識別算法探索。通過運用全等三角形的匹配，它加速了初步匹配的過程，可以放棄聯合國匹配的樣品很快。此外，保持了較高的識別精度。實驗表明，該新的算法進行了驗證，可應用於實際指紋應用。

關鍵字

指紋特徵提取 ； 全等三角形 ； 生物識別 ； 指紋識別

並列摘要

Abstract
With the fast development of artificial intelligence and automation science, fingerprint recognition achieves more and more research interests. With several decades’ development, automatic fingerprint recognition system has been established base on from macro computer to micro computer, even to embedded processor. The applications of fingerprint also developed from military applications to daily life.
To address the problems in fingerprint recognition, the fingerprint recognition algorithm is discussed in detail in this paper, which is range from fingerprint collection, fingerprint pre-processing, and fingerprint recognition algorithm to real fingerprint recognition system. First, the principle of fingerprint identification is studied in detail, and the fingerprint identification system’s performance measurement is discussed. Then the pre-processing which includes fingerprint segmentation, fingerprint enhancement, fingerprint binarization, and fingerprint thinning for fingerprint recognition is explored. The fingerprint features are extracted from the pre-processed fingerprint images and used for the later fingerprint recognition procedure. A congruent triangle matching based fast fingerprint recognition algorithm is explored. Through using the congruent triangle matching, it accelerates the preliminary matching process and can discard the un-matched samples quickly. Furthermore, it keeps the high recognition accuracy. Experiment shows this new algorithms is validated and can be applied to the real fingerprint applications.

並列關鍵字

fingerprint feature extraction ； congruent triangle ； biometric ； fingerprint recognition

參考文獻

1. Jain A. K., Ross A., Prabhakar S. An introduction to biometric recognition, IEEE Transactions on circuits and systems for video technology, vol. 14, no. 1, pp. 4-20, 2004.

4. R. Chellappa, C. Wilson, and A. sirohey. “human and machine recognition of faces: a survey”, proceedings IEEE, vol. 83, no. 5, pp. 705-740, 1995

6. V. Nalwa. “automatic on line signature verification”, proceedings of IEEE, vol. 85, no.2 pp. 213-239, 2005

9. Hong L, Wan Y. F. and Jain A. “Fingerprint image enhancement: algorithm and performance evaluation”, IEEE transaction on pattern analysis and machine intelligence, vol. 20, no. 8, 1998

10. W. Wang, J. W. Li, F. F. Huang, H. L. Feng, “Design and Implementation of log gabor filter in Fingerprint image enhancement.” Pattern recognition letters, vol 29, no. 3, 2008