運用影像處理技術之鈔票防拷系統

A Bill-Counterfeit Prevention System using Digital Image Processing Techniques

王佑禎(Yo-Chen Wang)

指導教授 ： 張元翔

中原大學/工學院/資訊工程研究所/碩士(2006年)

https://doi.org/10.6840/cycu200600391

摘要

偽鈔是金融市場中最主要的犯罪問題之一。本論文主要的目的為發展一套鈔票防拷系統 (Bill-Counterfeit Prevention或BCP) ，目的是希望可以用來自動偵測多功能事務機所擷取之影像中是否含有鈔票，以防止一般民眾自行拷貝美金鈔票。本系統主要演算法包括: (1) 複雜背景的移除；(2) 鈔票位置的辨別；(3) 角度的修正；(4) 鈔票面積大小的判別；及(5) 鈔票正反面的判別；(6) 政府註記的分析；(7) 上下顛倒的判別；(8) 簽名分析；(9) 鈔票幣值的分析等九大步驟來完成。在本論文中共使用了132張內含鈔票的影像(包括了美金1元、5元、10元、20元、50元、100元等六種幣值)作系統測試。研究結果顯示，利用本防拷系統演算法以辨識美金鈔票，平均辨識率為78.3％。總結而言，本系統未來可以植基於硬體上，如多功能事物機、掃描器、印表機上，將偵測為鈔票的地方，採取一些額外的措施，如：直接跳過鈔票的地方不印出或掃描出來，或在鈔票上加上額外的註記等方式，以達到防止拷貝鈔票的目的。

關鍵字

多功能事務機 ； 偽鈔 ； 影像處理 ； 圖形辨識

並列摘要

Counterfeit is one of the major crimes in financial market. The objective of this project was to develop a bill-counterfeit prevention (BCP) algorithm used in multi-function peripherals (MFPs) that automatically detects reproduction of U.S. banknotes. Our BCP algorithm includes: (1) complex background removal; (2) banknote location identification; (3) orientation correction; (4) area measurement; (5) front/back identification; (6) treasury seal analysis; (7) upside/down correction; (8) signature analysis; and (9) currency value analysis. To test our BCP algorithm, a database of 132 digital images with various amounts, i.e., $1, $5, $10, $20, $50, and $100, of U.S. banknotes were collected. In this preliminary study, our technique has achieved a detection rate of 78.3% in U.S. banknotes. In summary, our technique can be potentially used in detecting banknote reproduction such that extra enforcement measures (e.g., no scanning or printing, watermark & tracing system, etc.) can be achieved. Future investigation will also include hardware implementation adopting the BCP algorithm used in MFP copiers, scanners and/or printers.

並列關鍵字

Multi-Function Peripheral (MFP) ； Image Processing ； Pattern Recognition ； Counterfeit

參考文獻

[9] http://www.treas.gov/usss/money_illustrations.shtml, Counterfeit Awareness, June 15, 2006.

[10] A. Frosini, M. Gori and P. Priami, ”A neural network-based model for paper currency recognition and verification,” IEEE Trans. Neural Networks, vol. 7, Issue 6, pp. 1482-1490, Nov 1996.

[14] J. K. Lee and I. H. Kim, “New recognition algorithm for various kinds of Euro banknotes,” The 29th Annual IEEE International Conference on Industrial Electronics Society, 2003(IECON '03), vol. 3, pp. 2266-2270, Nov. 2-6, 2003.

[15] C. Herley, P. Vora and S. Yang, “Detection and deterrence of counterfeiting of valuable documents,” IEEE International Conference, Image Processing (ICIP‘04), vol. 4, pp. 2423-2426, Oct. 24-27, 2004.

[16] http://www.rulesforuse.org , CBCDG, June 15, 2006.