金融票據(jù)中印刷號碼識別算法的研究
發(fā)布時間：2019-07-01 09:31
【摘要】：我國彩色發(fā)票版面特別復(fù)雜、多樣,其上一些字符很小。而且用過的發(fā)票是由針式打印機打印而成,很多發(fā)票版面不清晰、已歪斜、已扭曲。在很多發(fā)票上還有不規(guī)范蓋章、簽字,因此如何正確確定發(fā)票圖像上各種字符的位置、如何正確分割出不同字號字符、如何確定小字符的較高維有效特征、如何設(shè)計對應(yīng)的高效的分類器、如何設(shè)計有效訓(xùn)練樣本庫等問題,都是到目前為止沒有很好解決的難題。本文針對發(fā)票編號識別難題,以圖像處理和模式識別等理論為基礎(chǔ),結(jié)合改進的版面分析和識別技術(shù),提出了一種較為有效的發(fā)票號碼識別算法。預(yù)處理階段,首先采用了中值濾波技術(shù)等多種濾波技術(shù)相結(jié)合方式濾波,去除掉發(fā)票圖像上的椒鹽噪聲。對于傾斜的發(fā)票圖像,本文采用的是改進的方向白游程圖像的傾斜校正方法。然后利用迭代閾值法對圖像二值化,根據(jù)發(fā)票特征和灰度直方圖的分析,設(shè)計發(fā)票號碼的定位方法。最后采用水平垂直投影法對單個號碼進行分割,采用模板法對字符進行歸一化。特征提取階段,對印刷體號碼提取了40維有效特征,確保了小字號號碼也能有足夠的區(qū)別其它號碼的特征。對號碼的識別階段,提出了改進的排序?qū)W習(xí)前向掩蔽模式分類器,優(yōu)化了王守覺院士的排序?qū)W習(xí)前向掩蔽模型,使其分類效果更好。此外,論文在發(fā)票編號訓(xùn)練樣本庫和測試庫的建立方面做了一定工作,建立了有400張發(fā)票編號訓(xùn)練樣本庫和300張發(fā)票編號測試庫。它們是由40張發(fā)票編號訓(xùn)練樣本初始庫和30張發(fā)票編號測試初始庫經(jīng)加不同噪聲、旋轉(zhuǎn)不同角度和縮放不同比率而產(chǎn)生�；谠摪l(fā)票編號訓(xùn)練樣本庫而設(shè)計的排序?qū)W習(xí)前向掩蔽模式分類器有較高的識別率和良好的抗噪性能。實驗表明,利用該模式分類器對號碼的識別率明顯高于傳統(tǒng)的BP網(wǎng)絡(luò)的識別率,抗噪性也優(yōu)于BP網(wǎng)絡(luò),識別速度也有提高。
[Abstract]:The layout of color invoice in China is very complex and diverse, and some characters on it are very small. And the used invoice is printed by needle printer, many invoice layout is not clear, has been skewed, distorted. In many invoices, there are still some problems, such as how to correctly determine the position of various characters on the invoice image, how to correctly segment the characters of different font sizes, how to determine the higher dimensional effective features of small characters, how to design the corresponding efficient classifiers, how to design the effective training sample database, and so on, which have not been solved so far. In order to solve the problem of invoice number recognition, based on the theory of image processing and pattern recognition, combined with the improved layout analysis and recognition technology, a more effective invoice number recognition algorithm is proposed in this paper. In the preprocessing stage, the median filtering technology and other filtering techniques are used to remove the salt and pepper noise from the invoice image. For tilted invoice images, this paper adopts an improved tilting correction method for directional white run distance images. Then the iterative threshold method is used to binarize the image. According to the analysis of invoice characteristics and gray histogram, the location method of invoice number is designed. Finally, the horizontal vertical projection method is used to segment a single number, and the template method is used to normalize the characters. In the feature extraction stage, the 40-dimensional effective features are extracted from the printed number, which ensures that the small size number can also have enough features to distinguish other numbers. For the recognition stage of numbers, an improved sorting learning forward masking pattern classifier is proposed, and the ranking learning forward masking model of academician Wang Shoujue is optimized to make the classification effect better. In addition, the paper has done some work in the establishment of invoice number training sample database and test database, and established 400 invoice number training sample database and 300 invoice number test database. They are produced by 40 invoice number training sample initial library and 30 invoice number test initial library by adding different noise, rotating different angles and scaling different ratios. The sorting learning forward masking pattern classifier based on the invoice number training sample database has high recognition rate and good anti-noise performance. The experimental results show that the recognition rate of the number is obviously higher than that of the traditional BP network, the anti-noise is also better than that of the BP network, and the recognition speed is also improved.
【學(xué)位授予單位】：青島大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.41
本文編號：2508369
[Abstract]:The layout of color invoice in China is very complex and diverse, and some characters on it are very small. And the used invoice is printed by needle printer, many invoice layout is not clear, has been skewed, distorted. In many invoices, there are still some problems, such as how to correctly determine the position of various characters on the invoice image, how to correctly segment the characters of different font sizes, how to determine the higher dimensional effective features of small characters, how to design the corresponding efficient classifiers, how to design the effective training sample database, and so on, which have not been solved so far. In order to solve the problem of invoice number recognition, based on the theory of image processing and pattern recognition, combined with the improved layout analysis and recognition technology, a more effective invoice number recognition algorithm is proposed in this paper. In the preprocessing stage, the median filtering technology and other filtering techniques are used to remove the salt and pepper noise from the invoice image. For tilted invoice images, this paper adopts an improved tilting correction method for directional white run distance images. Then the iterative threshold method is used to binarize the image. According to the analysis of invoice characteristics and gray histogram, the location method of invoice number is designed. Finally, the horizontal vertical projection method is used to segment a single number, and the template method is used to normalize the characters. In the feature extraction stage, the 40-dimensional effective features are extracted from the printed number, which ensures that the small size number can also have enough features to distinguish other numbers. For the recognition stage of numbers, an improved sorting learning forward masking pattern classifier is proposed, and the ranking learning forward masking model of academician Wang Shoujue is optimized to make the classification effect better. In addition, the paper has done some work in the establishment of invoice number training sample database and test database, and established 400 invoice number training sample database and 300 invoice number test database. They are produced by 40 invoice number training sample initial library and 30 invoice number test initial library by adding different noise, rotating different angles and scaling different ratios. The sorting learning forward masking pattern classifier based on the invoice number training sample database has high recognition rate and good anti-noise performance. The experimental results show that the recognition rate of the number is obviously higher than that of the traditional BP network, the anti-noise is also better than that of the BP network, and the recognition speed is also improved.
【學(xué)位授予單位】：青島大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.41
【參考文獻】
相關(guān)期刊論文 前10條
1 苑瑋琦;金燦;;基于結(jié)構(gòu)特征的紙幣號碼識別方法[J];計算機工程與應(yīng)用;2014年08期
2 朱顥東;李紅嬋;;基于特征加權(quán)模糊模板匹配的字符識別[J];蘭州理工大學(xué)學(xué)報;2013年01期
3 王威;劉百華;韓宇菲;孫洪慶;孟凡清;;一種通過方向白游程校正文本圖像傾斜的方法[J];科學(xué)技術(shù)與工程;2012年22期
4 趙高長;張磊;武風(fēng)波;;改進的中值濾波算法在圖像去噪中的應(yīng)用[J];應(yīng)用光學(xué);2011年04期
5 吳銳;黃劍華;唐降龍;劉家鋒;;基于灰度直方圖和譜聚類的文本圖像二值化方法[J];電子與信息學(xué)報;2009年10期
6 史玉林;李飛飛;孫益頂;;基于均值濾波和小波分析的圖像去噪[J];電子測量技術(shù);2008年08期
7 段敬紅;欒丹;;人民幣號碼自動識別方法研究[J];計算機工程與科學(xué);2008年01期
8 胡旺;李志蜀;黃奇;;基于雙窗口和極值壓縮的自適應(yīng)中值濾波[J];中國圖象圖形學(xué)報;2007年01期
9 魯娟娟;陳紅;;BP神經(jīng)網(wǎng)絡(luò)的研究進展[J];控制工程;2006年05期
10 遲曉君;孟慶春;;基于投影特征值的車牌字符分割算法[J];計算機應(yīng)用研究;2006年07期
相關(guān)碩士學(xué)位論文 前2條
1 賈彥金;票據(jù)印刷號碼自動識別技術(shù)研究[D];西安理工大學(xué);2008年
2 錢剛;基于ARM的紙幣號碼圖像采集及預(yù)處理系統(tǒng)的研究[D];南京航空航天大學(xué);2007年
，本文編號：2508369
本文鏈接：http://sikaile.net/kejilunwen/ruanjiangongchenglunwen/2508369.html
最近更新
教材專著
