本文選題：機(jī)器視覺 + 壓印字符�。� 參考：《廣東工業(yè)大學(xué)》2017年碩士論文

【摘要】：輪胎壓印字符是在工業(yè)中廣泛被應(yīng)用的一類標(biāo)識(shí)字符,它是利用模具使物體表面產(chǎn)生凹凸形變壓印而成。壓印字符與其背景區(qū)域顏色相同,且為立體字符。隨著現(xiàn)代制造業(yè)科技水平及生產(chǎn)效率要求的提高,對(duì)凹凸壓印字符的自動(dòng)化識(shí)別已成為工業(yè)產(chǎn)品生產(chǎn)管理智能化的一個(gè)必然要求。由于無色差這個(gè)特點(diǎn)使得工業(yè)相機(jī)采集的壓印字符圖像不易辨認(rèn),所以直接借用已有的光學(xué)字符識(shí)別研究成果較為困難。本文正是針對(duì)凹凸壓印字符難以穩(wěn)定識(shí)別這一問題,開展了以下的相關(guān)研究工作。設(shè)計(jì)了針對(duì)輪胎壓印字符的圖像采集硬件系統(tǒng)。本文首先簡(jiǎn)述了機(jī)器視覺系統(tǒng)的組成,分析了相關(guān)硬件的性能參數(shù)和選型方法,并根據(jù)本課題視覺系統(tǒng)的具體要求選取了合適硬件。分析了光照對(duì)壓印字符圖像的影響,并根據(jù)輪胎壓印字符特點(diǎn)選擇高角度環(huán)形LED光源前置照明的照明方案作為識(shí)別系統(tǒng)的最佳照明方案,為后續(xù)的算法處理的奠定了良好的基礎(chǔ)。設(shè)計(jì)了針對(duì)輪胎字符信息環(huán)形排列結(jié)構(gòu)的模板匹配定位方法及邊緣檢測(cè)分割方法。本文首先介紹了常用的字符定位算法,然后利用壓印字符的特點(diǎn)和已知字符信息研究了基于歸一化積相關(guān)(NCC)的壓印字符定位問題,進(jìn)而提出基于已知信息粗略定位,扇形掃描定位輪胎字符區(qū)域的方法,定位效果比較理想,能夠準(zhǔn)確地確定輪胎字符所在區(qū)域的邊界。通過多種分割方法的實(shí)驗(yàn)效果對(duì)比,采用邊緣檢測(cè)對(duì)已定位并轉(zhuǎn)換為水平排列的字符圖像進(jìn)行單個(gè)字符分割。采用了基于最小二乘支持向量機(jī)的字符識(shí)別方法,該方法很好地解決了壓印字符在識(shí)別過程中出現(xiàn)的訓(xùn)練時(shí)間長(zhǎng),識(shí)別正確率不穩(wěn)定的問題。從最終的軟件實(shí)現(xiàn)效果來看,本文設(shè)計(jì)的壓印字符識(shí)別系統(tǒng)的識(shí)別正確率及穩(wěn)定性符合系統(tǒng)的設(shè)計(jì)要求,達(dá)到了很好的識(shí)別效果。
[Abstract]:Tyre embossing character is a kind of mark character widely used in industry. The embossing character is the same color as its background area and is a stereoscopic character. With the improvement of technology level and production efficiency of modern manufacturing industry, automatic recognition of embossed characters has become an inevitable requirement for intelligent production management of industrial products. Because of the characteristic of no color difference, it is difficult to identify the imprint character image collected by industrial camera, so it is difficult to directly borrow the existing research results of optical character recognition. Aiming at the problem that the embossing characters are difficult to recognize stably, the following research work is carried out in this paper. A hardware system of image acquisition for tire embossing characters is designed. In this paper, the composition of the machine vision system is briefly introduced, and the performance parameters and selection methods of the related hardware are analyzed, and the appropriate hardware is selected according to the specific requirements of the vision system in this paper. The influence of illumination on imprint character image is analyzed, and the lighting scheme of high angle ring LED light source preillumination is selected as the best lighting scheme of recognition system according to the character characteristics of tire embossing character. It lays a good foundation for the subsequent algorithm processing. A template matching location method and edge detection segmentation method are designed for the ring arrangement of tire character information. This paper first introduces common character localization algorithms, then studies the imprint character location problem based on normalized product correlation (NCC) using the characteristics of imprint characters and known character information, and then proposes rough location based on known information. The method of sector scanning and locating tire character region is ideal, and it can accurately determine the boundary of tire character region. By comparing the experimental results of many segmentation methods, the single character segmentation of the character image which has been located and converted to horizontal arrangement is carried out by edge detection. The method of character recognition based on least squares support vector machine (LS-SVM) is used to solve the problems of long training time and unstable recognition accuracy of imprint characters. From the final effect of software implementation, the recognition accuracy and stability of the imprint character recognition system designed in this paper accord with the design requirements of the system, and achieve a very good recognition effect.
【學(xué)位授予單位】：廣東工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41;TQ330.493

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 王勇;郭慧;邢金鵬;;基于輪胎標(biāo)識(shí)點(diǎn)的輪胎分類系統(tǒng)研究[J];橡膠工業(yè);2015年12期

2 關(guān)學(xué)忠;張璐;;基于改進(jìn)的BP神經(jīng)網(wǎng)絡(luò)車牌識(shí)別的研究[J];自動(dòng)化技術(shù)與應(yīng)用;2015年07期

3 吳曉軍;鄒廣華;;基于邊緣幾何特征的高性能模板匹配算法[J];儀器儀表學(xué)報(bào);2013年07期

4 張倩;楊耀權(quán);;基于支持向量機(jī)核函數(shù)的研究[J];電力科學(xué)與工程;2012年05期

5 顧燕萍;趙文杰;吳占松;;最小二乘支持向量機(jī)的算法研究[J];清華大學(xué)學(xué)報(bào)(自然科學(xué)版);2010年07期

6 張釗;費(fèi)一楠;宋麟;王鎖柱;;基于模糊支持向量機(jī)的多分類算法研究[J];計(jì)算機(jī)應(yīng)用;2008年07期

7 孫卜郊;周東華;;基于NCC的存在旋轉(zhuǎn)的圖像匹配方法[J];傳感器與微系統(tǒng);2008年05期

8 范俐捷;王巖飛;高鑫;;一種新的基于灰度的圖像匹配方法[J];微計(jì)算機(jī)信息;2007年30期

9 羅婷婷;范太華;;支持向量機(jī)核函數(shù)及優(yōu)化研究[J];兵工自動(dòng)化;2007年10期

10 孫卜郊;周東華;;基于NCC的快速匹配算法[J];傳感器與微系統(tǒng);2007年09期

，

本文編號(hào)：1907423