本文選題：印刷品缺陷檢測(cè)　切入點(diǎn)：人工免疫　出處：《西安理工大學(xué)》2017年碩士論文

【摘要】：在印刷行業(yè)中,印刷品缺陷檢測(cè)對(duì)印刷品質(zhì)量的評(píng)定與控制具有重要意義,在實(shí)際生產(chǎn)中,要剔除帶有缺陷的印刷品。現(xiàn)階段的印刷品缺陷檢測(cè)方法大都存在著或多或少的不足,算法有待更新。圖像處理技術(shù)的發(fā)展和新的智能算法的出現(xiàn)促進(jìn)了檢測(cè)技術(shù)的進(jìn)步;多種智能算法的交叉融合應(yīng)用,有望開發(fā)出一種新的更高效的印刷品缺陷檢測(cè)方法。本文基于人工免疫算法對(duì)印刷品缺陷檢測(cè)技術(shù)進(jìn)行了研究。人工免疫算法具有多層檢測(cè)機(jī)制,需要少量或不需要先驗(yàn)知識(shí),僅需要少量缺陷樣本的優(yōu)點(diǎn)。因此,基于人工免疫算法的印刷品缺陷檢測(cè)技術(shù)具有廣闊的發(fā)展空間。在研究了人工免疫算法的陰性選擇原理的基礎(chǔ)上,結(jié)合圖像處理技術(shù),利用能夠反映圖像像素灰度分布規(guī)律的灰度共生矩陣,求得印刷品圖像在0°、45°、90°和135°四個(gè)方向上的能量、熵、對(duì)比度、相關(guān)性、同質(zhì)性五個(gè)紋理特征,并將各特征值的均值作為圖像特征的最終值,以各特征值的均值組成特征向量作為陰性選擇算法的數(shù)據(jù)表示。本文研究了基本陰性選擇算法并對(duì)其進(jìn)行了改進(jìn),提出實(shí)數(shù)值編碼的改進(jìn)陰性選擇算法,樣本數(shù)據(jù)空間采用多維實(shí)數(shù)值向量表示;利用歐氏距離計(jì)算兩樣本間的親和度,并判斷它們是否發(fā)生匹配。在缺陷檢測(cè)方面,針對(duì)基本陰性選擇算法只能識(shí)別正常和缺陷,而不能檢測(cè)缺陷種類的特點(diǎn),提出引入“疫苗”的改進(jìn)辦法,對(duì)缺陷類型進(jìn)行識(shí)別。該方法提取已知缺陷印刷品圖像特征向量作為“疫苗”,對(duì)檢測(cè)器進(jìn)行聚類操作,構(gòu)造多種檢測(cè)器集合,采用多檢測(cè)器集融合診斷對(duì)缺陷種類進(jìn)行判斷。為了提高算法的檢測(cè)精度,降低誤判率,本文提出將待檢樣本與自己集合進(jìn)行二次匹配的方法。最后,本文基于MATLAB編程實(shí)現(xiàn)了從圖像處理到缺陷檢測(cè)的全部過(guò)程,設(shè)計(jì)了印刷品缺陷檢測(cè)系統(tǒng)。實(shí)驗(yàn)結(jié)果表明,本文提出的改進(jìn)陰性選擇算法能夠有效地檢測(cè)出印刷品缺陷;設(shè)計(jì)的印刷品缺陷檢測(cè)系統(tǒng)能夠快速識(shí)別出缺陷種類,且檢測(cè)結(jié)果較為準(zhǔn)確,有一定的應(yīng)用價(jià)值。
[Abstract]:At this stage, most of the defect detection methods of printed matter have more or less shortcomings, and the algorithm needs to be updated.The development of image processing technology and the emergence of new intelligent algorithms promote the progress of detection technology, and the cross-fusion application of many intelligent algorithms is expected to develop a new and more efficient method of print defect detection.In this paper, based on artificial immune algorithm, print defect detection technology is studied.The artificial immune algorithm (AIA) has the advantages of multi-layer detection, which requires little or no prior knowledge, and only a small number of defect samples.Therefore, the printing defect detection technology based on artificial immune algorithm has a broad development space.On the basis of studying the principle of negative selection of artificial immune algorithm and combining with image processing technology, the energy and entropy of printed image in four directions of 0 擄~ 45 擄~ 90 擄and 135 擄are obtained by using the gray level co-occurrence matrix which can reflect the law of image pixel gray distribution.Contrast, correlation and homogeneity are five texture features. The mean value of each eigenvalue is taken as the final value of the image feature, and the average value of each eigenvalue is used as the data representation of the negative selection algorithm.In this paper, the basic negative selection algorithm is studied and improved. An improved negative selection algorithm based on real value coding is proposed. The sample data space is represented by multidimensional real value vector, and the affinity between two samples is calculated by Euclidean distance.And determine whether they match or not.In the aspect of defect detection, in view of the fact that the basic negative selection algorithm can only recognize the normal and the defect, but can not detect the type of defect, an improved method of introducing "vaccine" is put forward to identify the type of defect.In this method, the feature vectors of printed image of known defects are extracted as "vaccines", the detectors are clustered, the sets of multiple detectors are constructed, and the types of defects are judged by the fusion diagnosis of multi-detector sets.In order to improve the detection accuracy of the algorithm and reduce the error rate, this paper proposes a method of quadratic matching between the samples to be checked and their own sets.Finally, the whole process from image processing to defect detection is realized based on MATLAB programming, and the print defect detection system is designed.The experimental results show that the improved negative selection algorithm proposed in this paper can effectively detect print defects, and the designed print defect detection system can quickly identify the types of defects, and the detection results are more accurate and have certain application value.
【學(xué)位授予單位】：西安理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP18;TP391.41;TS807

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 胡方尚;郭慧;邢金鵬;王勇;;基于印刷缺陷檢測(cè)的圖像配準(zhǔn)方法研究[J];光學(xué)技術(shù);2017年01期

2 邵雪;曾臺(tái)英;汪祖輝;;一種基于NIQE的印刷圖像無(wú)參考質(zhì)量評(píng)價(jià)方法[J];包裝學(xué)報(bào);2016年04期

3 胡方尚;郭慧;;基于ROI模板的印刷品圖像配準(zhǔn)方法[J];東華大學(xué)學(xué)報(bào)(自然科學(xué)版);2016年04期

4 張秀珍;吳貴芳;普杰信;陳好剛;;基于模板匹配的彩色印品套印偏差檢測(cè)方法[J];計(jì)算機(jī)仿真;2015年10期

5 王文舉;趙萍;陳偉;謝寒;孫劉杰;姜中敏;陳景華;;彩色印刷品缺陷快速精確檢測(cè)方法研究[J];包裝工程;2015年17期

6 田敏;;印刷品質(zhì)量檢測(cè)技術(shù)的發(fā)展歷程及其優(yōu)缺點(diǎn)[J];廣東印刷;2014年04期

7 甄宗坤;岳建平;;基于LOG算子和灰度共生矩陣的影像紋理特征提取[J];測(cè)繪通報(bào);2013年09期

8 白家森;;圖像處理技術(shù)在印刷缺陷檢測(cè)中的應(yīng)用[J];印刷質(zhì)量與標(biāo)準(zhǔn)化;2013年05期

9 劉麗;匡綱要;;圖像紋理特征提取方法綜述[J];中國(guó)圖象圖形學(xué)報(bào);2009年04期

10 許瑞馨;;印品在線檢測(cè)技術(shù)及發(fā)展[J];印刷技術(shù);2007年25期

相關(guān)博士學(xué)位論文 前1條

1 張靜;PCB表觀缺陷的自動(dòng)光學(xué)檢測(cè)理論與技術(shù)[D];電子科技大學(xué);2013年

相關(guān)碩士學(xué)位論文 前4條

1 李陸陸;基于灰度共生矩陣和MRF的紋理圖像分割[D];遼寧師范大學(xué);2013年

2 楊洋;基于SVM的印刷品缺陷在線檢測(cè)[D];華中科技大學(xué);2012年

3 謝菲;圖像紋理特征的提取和圖像分類系統(tǒng)研究及實(shí)現(xiàn)[D];電子科技大學(xué);2009年

4 陳路;基于畫面的印刷質(zhì)量檢測(cè)控制系統(tǒng)研究[D];西安理工大學(xué);2002年

，

本文編號(hào)：1682920