标题: 低解析度印刷数字之辨识
Recognition of Printed Digits of Low Resolution
作者: 林泓宏
Horng-Horng Lin
庄仁辉
Jen-Hui Chuang
资讯科学与工程研究所
关键字: 数字辨识;低解析度;检测系统;Digits Recognition;Low Recolution;Inspecting System
公开日期: 1998
摘要: 尽管数字影像辨识已经算是一个成熟的技术了,但对于低解析度数字影像的处理,却仍是一个较少人研究和讨论的方向。在这篇论文里头,我们发展了一个高速发票印刷检测系统,并针对印刷中之发票号码作自动辨识。其中,我们探讨了几个具有挑战性的问题,如:高速印刷检测系统的设计、发票影像中数字区块的切割与背景网点的消除,低解析度数字影像的辨识等。为了解决这些问题,我们提出了最小灰阶值分析法(Minimal Gray-level Analysis),来处理发票影像中,数字区块的切割、网点消除和影像强化等前处理的部分。另外,对于每个只有 8 x 8 的低解析度数字影像,我们应用所提出的列处理法(Row-based Method)来撷取其特征,然后,再以树状辨识器来做辨识。依据我们在实验室中雏形系统的测试结果,可以达到 95% 以上的辨识率。
In this paper, we develop an on-line inspecting system for invoice printing and introduce some techniques to automatically recognize the printed digits on the invoices. The poor quality of an invoice image, the textured background, and the low resolution of each printed digit make the research challenging. To overcome these problems, a robust method based on a minimal gray-level analysis is proposed to preprocess the invoice images. The preprocessing includes the number block extraction, textured background removal, and digit image enhancement. For each digit image of 8(8 pixels, a row-based method is developed to extract the features of the digit, which is then applied to a tree classifier for recognition. For the prototype system developed in the laboratory, a recognition rate of 95% can be achieved.
URI: http://140.113.39.130/cdrfb3/record/nctu/#NT870394049
http://hdl.handle.net/11536/64189
显示于类别:Thesis