本文選題：檢測(cè)技術(shù)與自動(dòng)化裝置 + 機(jī)器視覺　； 參考：《石家莊鐵道大學(xué)》2014年碩士論文

【摘要】：藥品的包裝是流水線上的一道重要工序，但是過程中常常會(huì)出現(xiàn)藥品漏裝、破碎、缺損、有污染物等包裝缺陷問題。自動(dòng)視覺缺陷檢測(cè)AVI (Automated VisualInspection)已經(jīng)成為現(xiàn)代制藥行業(yè)質(zhì)量控制的一個(gè)重要組成部分。我國的AVI發(fā)展起步比較晚，目前國內(nèi)企業(yè)應(yīng)用的AVI系統(tǒng)仍以國外產(chǎn)品為主。發(fā)展具有自主知識(shí)產(chǎn)權(quán)的、適合我國國情的AVI系統(tǒng)，具有重要的意義。 以軟件構(gòu)架為主、基于PC的機(jī)器視覺檢測(cè)系統(tǒng)以其經(jīng)濟(jì)、靈活的特點(diǎn)，已經(jīng)逐漸成為國內(nèi)廠家為新設(shè)備配套和舊設(shè)備改造的認(rèn)可方案。基于PC的機(jī)器視覺的藥品包裝檢測(cè)方法還具有非接觸、智能化、高精度和高速度的特點(diǎn)。如何在泡罩藥品包裝過程中，應(yīng)用機(jī)器視覺技術(shù)實(shí)現(xiàn)對(duì)藥品缺粒、破損等缺陷進(jìn)行在線檢測(cè)，并做出相應(yīng)的處置，是這篇論文主要討論的問題。 本文采用非接觸式的機(jī)器視覺檢測(cè)技術(shù)作為基本思路。根據(jù)藥廠包裝藥品所用實(shí)際設(shè)備的情況，首先通過對(duì)包裝機(jī)械的結(jié)構(gòu)、運(yùn)行情況和檢測(cè)系統(tǒng)的應(yīng)用的分析，對(duì)檢測(cè)系統(tǒng)的整體方案及硬件設(shè)備進(jìn)行介紹。論文的重點(diǎn)是對(duì)藥品泡罩包裝機(jī)器視覺的關(guān)鍵技術(shù)進(jìn)行研究：首先對(duì)采集到的藥品包裝圖像進(jìn)行濾波預(yù)處理便于后續(xù)缺陷分割；然后采用一種改進(jìn)的基于形態(tài)學(xué)重構(gòu)和控制標(biāo)記符的分水嶺算法對(duì)圖像進(jìn)行分割，截取只包含單個(gè)藥品目標(biāo)的圖像，便于后續(xù)缺陷特征的提取。該方法有效地克服了傳統(tǒng)分水嶺方法的過分割問題，具有分割效果好、抗干擾能力強(qiáng)、穩(wěn)定的特點(diǎn)，且本方法不需要先驗(yàn)知識(shí)，實(shí)用性較強(qiáng)；接著對(duì)特征提取方法進(jìn)行分析研究，對(duì)單個(gè)目標(biāo)的幾何形狀特征進(jìn)行提取，作為后續(xù)神經(jīng)網(wǎng)絡(luò)的輸入，用來進(jìn)行缺陷分類；對(duì)藥品包裝缺陷的分類方法的原理進(jìn)行分析對(duì)比，最終比較了BP神經(jīng)網(wǎng)絡(luò)和RBF神經(jīng)網(wǎng)絡(luò)的優(yōu)缺點(diǎn)，，采用RBF網(wǎng)絡(luò)完成了對(duì)藥品表面圖像的分類，提高了識(shí)別效率；最后在Matlab平臺(tái)上實(shí)現(xiàn)了算法的仿真，在VC++6.0實(shí)驗(yàn)平臺(tái)上利用Opencv語言實(shí)現(xiàn)了整個(gè)軟件的程序編寫。試驗(yàn)結(jié)果表明本系統(tǒng)能夠?qū)ε菡炙幤钒b缺陷進(jìn)行正確的分類檢測(cè)，取得了較好的檢測(cè)效果。
[Abstract]:Drug packaging is an important process on the assembly line, but the packaging defects such as drug leakage, breakage, defect, contaminant and so on often occur in the process. Automated Visual Inspection (AVI) has become an important part of quality control in modern pharmaceutical industry. The development of AVI in China started relatively late. At present, the AVI system used by domestic enterprises is still dominated by foreign products. It is of great significance to develop a AVI system with independent intellectual property rights that is suitable for China's national conditions. Based on the software architecture, the PC-based machine vision inspection system has gradually become the approved scheme of the domestic manufacturers for the new equipment matching and the old equipment transformation due to its economic and flexible characteristics. PC-based machine vision based drug packaging testing method also has the characteristics of non-contact, intelligent, high precision and high speed. This paper mainly discusses how to use machine vision technology to detect and deal with defects such as lack of grain and breakage in the packaging process of drug bubble mask. In this paper, the contactless machine vision detection technology is used as the basic idea. According to the actual equipment used in drug packaging in pharmaceutical factory, the whole scheme and hardware equipment of the testing system are introduced through the analysis of the structure, operation and application of the testing system. The focus of this paper is to study the key technology of drug bubble packaging machine vision: firstly, filter and preprocess the collected drug packaging image to facilitate the subsequent defect segmentation; Then an improved watershed algorithm based on morphological reconstruction and control markers is used to segment the image and intercept the image which contains only a single drug target so as to facilitate the subsequent extraction of defect features. This method overcomes the over-segmentation problem of the traditional watershed method, and has the characteristics of good segmentation effect, strong anti-interference ability and stability. Moreover, the method does not need prior knowledge and has strong practicability. Then the feature extraction method is analyzed and studied, and the geometric shape feature of a single target is extracted as the input of the subsequent neural network, which is used for defect classification; the principle of the drug packaging defect classification method is analyzed and compared. Finally, the advantages and disadvantages of BP neural network and RBF neural network are compared, the classification of drug surface images is completed by RBF neural network, and the recognition efficiency is improved. Finally, the algorithm is simulated on Matlab platform. The program of the whole software is realized by using Opencv language on VC 6.0 experimental platform. The test results show that the system can correctly classify and detect the packaging defects of the bubble mask and obtain good results.
【學(xué)位授予單位】：石家莊鐵道大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TP391.41;TP274

【參考文獻(xiàn)】

相關(guān)期刊論文 前9條

1 蘭海軍;文友先;;機(jī)器視覺技術(shù)的發(fā)展和應(yīng)用[J];湖北農(nóng)機(jī)化;2007年05期

2 李蒙;方家樂;朱穎合;;LED芯片圖像的勢(shì)函數(shù)標(biāo)記分水嶺分割[J];機(jī)電工程;2010年07期

3 顏發(fā)根,劉建群,陳新,丁少華;機(jī)器視覺及其在制造業(yè)中的應(yīng)用[J];機(jī)械制造;2004年11期

4 蔡桂艷;;距離變換和分水嶺分割的粘連人群分割算法[J];欽州學(xué)院學(xué)報(bào);2008年03期

5 戚德虎,康繼昌;BP神經(jīng)網(wǎng)絡(luò)的設(shè)計(jì)[J];計(jì)算機(jī)工程與設(shè)計(jì);1998年02期

6 曹亮;魏怡;姚思勤;;機(jī)器視覺技術(shù)及其發(fā)展和應(yīng)用[J];中國科技信息;2008年11期

7 郭百巍;陳大融;;結(jié)合小波分析和分水嶺分割法的微觀表面形貌分析方法[J];中國機(jī)械工程;2007年17期

8 高麗;楊樹元;李海強(qiáng);;一種基于標(biāo)記的分水嶺圖像分割新算法[J];中國圖象圖形學(xué)報(bào);2007年06期

9 張五一;趙強(qiáng)松;王東云;;機(jī)器視覺的現(xiàn)狀及發(fā)展趨勢(shì)[J];中原工學(xué)院學(xué)報(bào);2008年01期

相關(guān)博士學(xué)位論文 前1條

1 牟洪波;基于BP和RBF神經(jīng)網(wǎng)絡(luò)的木材缺陷檢測(cè)研究[D];東北林業(yè)大學(xué);2010年

本文編號(hào)：1819374