本文選題：字符識別　切入點(diǎn)：隨機(jī)圓檢測　出處：《江南大學(xué)》2012年碩士論文　論文類型：學(xué)位論文

【摘要】：隨著工業(yè)生產(chǎn)的自動(dòng)化程度越來越高,許多場合下需要對生產(chǎn)線上產(chǎn)品的標(biāo)號或編碼通過機(jī)器進(jìn)行自動(dòng)識別。然而工業(yè)現(xiàn)場的復(fù)雜環(huán)境,如光照不均勻、噪聲等因素,給字符的準(zhǔn)確識別帶來較大的困難,對字符識別系統(tǒng)的硬件和軟件的性能也提出了更高的要求。本文研究基于嵌入式智能相機(jī)硬件平臺,以軸承壓印字符為識別對象,在總結(jié)前人經(jīng)驗(yàn)和成果基礎(chǔ)上,提出了自己的解決方法,實(shí)現(xiàn)軸承壓印字符的自動(dòng)識別。論文所涉及的內(nèi)容包括以下幾個(gè)方面: 1)軸承圖像的采集和預(yù)處理。在分析軸承壓印字符的成像特點(diǎn)的基礎(chǔ)上,設(shè)計(jì)了適用于軸承的圖像采集系統(tǒng)。該系統(tǒng)基于嵌入式智能相機(jī)圖像采集平臺,并選用低角度LCD環(huán)形光源作為輔助光源,通過對軸承進(jìn)行圖像采集證實(shí)該系統(tǒng)能夠獲取質(zhì)量較高的軸承圖片。在圖像預(yù)處理階段,由于軸承是圓形結(jié)構(gòu)且字符區(qū)域在圖像中的位置不固定,因此需要對軸承字符區(qū)域進(jìn)行定位和矯正,以便后續(xù)的處理和識別。為此,在使用大津法得到軸承的二值圖像后,首先要對軸承圓心進(jìn)行定位。針對隨機(jī)Hough變換圓檢測算法的不足,使用一種改進(jìn)的隨機(jī)圓檢測算法用于軸承的圓心定位,在候選圓選取的過程中通過簡單的判斷降低了運(yùn)算量,實(shí)驗(yàn)證實(shí)該圓心定位算法能夠快速而準(zhǔn)確定位出軸承圓心。隨后,以定位出的圓心為極坐標(biāo)原點(diǎn),采用投影法確定軸承字符區(qū)域。最后,對軸承字符扇形區(qū)域進(jìn)行矯正,若采用極坐標(biāo)變換所得圖像毛刺較多,因此本文采用基于仿射變換的字符矯正方法,實(shí)驗(yàn)表明該方法能使變換后的圖像毛刺較少且速度上也能滿足要求。 2)軸承字符的特征提取和分類器。本文詳細(xì)描述了兩種常用的特征提取方法:方向線素特征和輪廓層次特征,并在理論分析和實(shí)驗(yàn)的基礎(chǔ)上,針對他們的不足分別提出了基于彈性網(wǎng)格的方向線素特征和基于小波變換的輪廓層次特征兩種改進(jìn)的特征提取方法�；趶椥跃W(wǎng)格的方向線素特征有效地彌補(bǔ)了均勻網(wǎng)格劃分對字符形變的敏感性,特征的魯棒性更強(qiáng)�；谛〔ㄗ儞Q的輪廓層次特征充分利用了小波多分辨率分析的特性,特征抗噪性更好且維數(shù)更低。關(guān)于軸承字符識別的分類器,本文討論了BP神經(jīng)網(wǎng)絡(luò)和支持向量機(jī)分類器的原理,并分別設(shè)計(jì)了基于動(dòng)量項(xiàng)與自適應(yīng)學(xué)習(xí)速率的BP神經(jīng)網(wǎng)絡(luò)和基于LIBSVM的支持向量機(jī)網(wǎng)絡(luò)。軸承字符中識別系統(tǒng)具體采用的特征提取方法和分類器方案是通過最后的識別實(shí)驗(yàn)確定的。 通過對實(shí)際拍攝的圖片進(jìn)行識別實(shí)驗(yàn),驗(yàn)證了本文所述方法的有效性,并確定特征提取方法和分類器的選取。實(shí)驗(yàn)表明:本文采用的圖像采集方案能夠獲取質(zhì)量較高的軸承圖像,預(yù)處理方法效果較好,根據(jù)試驗(yàn)結(jié)果最終選取改進(jìn)的輪廓層次特征作為特征,使用支持向量機(jī)作為分類器。字符識別的準(zhǔn)確率在96%以上,速度上也能滿足實(shí)際需求。本文方法能夠快速而準(zhǔn)確地對軸承壓印字符進(jìn)行自動(dòng)識別。
[Abstract]:With the industrial production of increasingly high degree of automation, many applications need to automatically identify the product line or label encoding through the machine. However the complicatedindustrial environments, such as uneven illumination, noise and other factors, difficult to accurately identify the characters, performance of character recognition system of hardware and software also put forward higher requirements. This paper is based on the embedded hardware platform with intelligent camera, bearing the pressed characters to recognize the object in the previous experience and on the basis of the results, proposed own solution, realize the automatic recognition of the pressed characters. Bearing the related contents include the following aspects:
1) bearing image capture and preprocessing. Based on the analysis of imaging characteristics of bearing characters pressed on the design of the image acquisition system. The system is suitable for bearing the embedded image acquisition platform based on smart camera, and the low angle LCD ring light source as auxiliary light source, through collecting image bearing pictures of the system can be confirmed to obtain high quality bearings. In the image preprocessing stage, because the bearing is a circle structure and character region in the image of the location is not fixed, so the need for positioning and correction of bearing character area, so that the subsequent processing and recognition. Therefore, the Otsu method is used in bearing two value image, first of all to the localization of the bearing circle. For lack of randomized Hough transform circle detection algorithm, using random circle detection algorithm is improved for the bearing center localization, in the selection of candidate circle In the process of judgment by simply reduces the amount of computation and experiments prove that the location algorithm can quickly and accurately locate the bearing circle. Then, in order to locate the center as the origin of polar coordinates, bearing character area is determined by projection method. Finally, the bearing character of sector correction, if using the polar coordinate transform the image of burr more, this paper uses character correction method based on affine transformation. The experimental results show that the method can transform the image of burr less and speed can meet the requirements.
2) bearing character feature extraction and classifier. This paper describes the extraction methods of two kinds of features: directional line element feature and contour feature, and on the basis of theoretical analysis and experiments, for their shortcomings are proposed based on elastic mesh directional line element feature extraction and contour level feature of wavelet transform two kinds of improved methods. Based on the characteristics of elastic mesh directional line element features effectively compensate for the sensitivity of uniform mesh deformation character based on robust feature. Characteristics of wavelet transform contour level features full use of the wavelet multi-resolution analysis based on the characteristics of better noise resistance and lower dimension on the bearing. Character recognition classifier, this paper discusses the principle of BP neural network and support vector machine classifier, and we design the momentum and adaptive learning rate based on BP The network and support vector machine network based on LIBSVM. The feature extraction method and classifier scheme adopted in bearing character recognition system are determined through the final recognition experiment.
Through experiments on real images, verify the validity of the method, and determine the selection of feature extraction and classifier. Experimental results show that the bearing image acquisition scheme used in this paper can obtain high quality, pretreatment method is better, according to the results of selected contour level features improved as features, support vector machine is used as classifier. Character recognition accuracy is above 96%, the speed can meet the practical demands. This method can quickly and accurately on the bearing characters pressed automatic identification.

【學(xué)位授予單位】：江南大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2012
【分類號】：TP368.1;TP391.43

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 李倩;;文檔圖像的二值化算法綜述[J];中國傳媒大學(xué)學(xué)報(bào)(自然科學(xué)版);2008年04期

2 陳愛軍;李金宗;李東東;;一種改進(jìn)的隨機(jī)圓檢測算法[J];光電工程;2006年12期

3 楊基春;黃戰(zhàn)華;朱猛;楊鶴猛;;高噪聲輪胎圖像規(guī)格號提取方法研究[J];光電工程;2010年03期

4 楊基春;黃戰(zhàn)華;蔡懷宇;張尹馨;;大噪聲圖像的輪胎規(guī)格號識別技術(shù)[J];光電工程;2010年09期

5 曹建海,路長厚;基于小波變換和DCT的字符圖像特征抽取新方法[J];光電子·激光;2004年04期

6 曹建海;李龍;路長厚;;基于RBF-NN的壓印凹凸字符質(zhì)量檢測研究[J];光電子·激光;2006年08期

7 李學(xué)勇;路長厚;李建美;;融合輪廓矩和Fourier描述子特征的壓印字符識別[J];光電子.激光;2007年10期

8 李建美;路長厚;李學(xué)勇;;一種基于圖像分層的標(biāo)牌壓印字符分割方法[J];光電子.激光;2008年06期

9 葉薌蕓,戚飛虎,吳健淵,許磊;文本圖像的快速二值化方法[J];紅外與毫米波學(xué)報(bào);1997年05期

10 李牧;閆繼宏;朱延河;趙杰;;一種改進(jìn)的大津法在機(jī)器視覺中的應(yīng)用[J];吉林大學(xué)學(xué)報(bào)(工學(xué)版);2008年04期

相關(guān)博士學(xué)位論文 前1條

1 李建美;標(biāo)牌壓印字符圖像獲取與處理中的關(guān)鍵技術(shù)研究[D];山東大學(xué);2008年

相關(guān)碩士學(xué)位論文 前10條

1 李杜;字符識別技術(shù)研究及其在機(jī)器視覺測控中的應(yīng)用[D];江南大學(xué);2011年

2 李了了;工業(yè)現(xiàn)場字符識別方法的研究[D];合肥工業(yè)大學(xué);2003年

3 肖進(jìn);多神經(jīng)網(wǎng)絡(luò)在車牌字符識別中的應(yīng)用[D];東南大學(xué);2004年

4 高偉;車牌字符識別技術(shù)的研究[D];山西大學(xué);2005年

5 丁勝;基于支持向量機(jī)的手寫體字符識別[D];青島大學(xué);2006年

6 鄔文俊;基于機(jī)器視覺技術(shù)的啤酒瓶字符自動(dòng)識別系統(tǒng)的研究[D];湖北工業(yè)大學(xué);2005年

7 朱峰;車牌漢字識別技術(shù)的研究與實(shí)現(xiàn)[D];江蘇大學(xué);2006年

8 邊威;小波基的選取與構(gòu)造方法討論[D];東北師范大學(xué);2007年

9 何浩智;字符識別中筆段及特征提取方法的研究[D];湖南大學(xué);2007年

10 徐銘杰;基于支持向量機(jī)的字符識別系統(tǒng)的研究與實(shí)現(xiàn)[D];浙江工業(yè)大學(xué);2007年

，

本文編號：1644445