本文選題：織物疵點(diǎn)　切入點(diǎn)：疵點(diǎn)檢測(cè)　出處：《中原工學(xué)院》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：織物疵點(diǎn)嚴(yán)重影響織物質(zhì)量,對(duì)織物疵點(diǎn)的有效自動(dòng)檢測(cè)已成為紡織品質(zhì)量評(píng)價(jià)的關(guān)鍵之一。由于織物疵點(diǎn)圖像紋理復(fù)雜多變,給基于機(jī)器視覺(jué)的疵點(diǎn)自動(dòng)檢測(cè)帶來(lái)了挑戰(zhàn)。近年來(lái),人們模擬生物的視覺(jué)注意機(jī)制引入了基于視覺(jué)顯著性的圖像處理和模式識(shí)別檢測(cè)方法,并取得了良好的效果。本文對(duì)基于視覺(jué)顯著性的織物疵點(diǎn)檢測(cè)算法進(jìn)行了深入探究。針對(duì)織物圖像復(fù)雜紋理特點(diǎn),考慮其方向性和隨機(jī)性,模擬人類視覺(jué)感知通路的層次化處理機(jī)制,構(gòu)建了基于視覺(jué)顯著性的織物疵點(diǎn)檢測(cè)模型,提出了有效的織物疵點(diǎn)檢測(cè)算法。采用小波變換或平穩(wěn)小波變換與背景估計(jì)相結(jié)合,提出了一種基于平穩(wěn)小波變換和背景估計(jì)的織物疵點(diǎn)檢測(cè)算法。首先,分別對(duì)織物圖像進(jìn)行小波變換或平穩(wěn)小波變換獲得特征圖像;其次,采用分區(qū)處理得到特征圖像的多個(gè)背景圖,求取原始圖像與每一個(gè)背景圖的歐氏距離生成多個(gè)子顯著圖,經(jīng)融合后獲得包含候選疵點(diǎn)區(qū)域的視覺(jué)顯著圖;最后,基于全局估計(jì)的高斯分布模型獲得疵點(diǎn)顯著圖,經(jīng)圖像分割檢測(cè)出疵點(diǎn)。實(shí)驗(yàn)結(jié)果表明,該算法能準(zhǔn)確定位疵點(diǎn)區(qū)域,實(shí)現(xiàn)對(duì)織物疵點(diǎn)的有效檢測(cè)且平穩(wěn)小波變換具有更高的檢測(cè)準(zhǔn)確率。利用互信息具有的基本性質(zhì),提出了一種基于互信息測(cè)度及上下文分析的織物疵點(diǎn)檢測(cè)算法。首先,對(duì)織物圖像進(jìn)行均勻的部分重疊的分塊處理獲得圖像塊;其次,分別計(jì)算每個(gè)圖像塊與周圍的K個(gè)圖像塊兩兩之間的信息熵;最后,基于上下文分析的圖像塊信息熵比對(duì)獲得視覺(jué)顯著圖,經(jīng)閾值分割檢測(cè)出疵點(diǎn)。實(shí)驗(yàn)結(jié)果表明,該算法無(wú)需特征提取就可清晰定位疵點(diǎn)區(qū)域,實(shí)現(xiàn)對(duì)織物疵點(diǎn)的有效檢測(cè)且優(yōu)于現(xiàn)有的相似性檢測(cè)算法的檢測(cè)結(jié)果。
[Abstract]:Fabric defects seriously affect fabric quality. Effective automatic detection of fabric defects has become one of the key issues in textile quality evaluation. In recent years, the visual attention mechanism of simulated organisms has introduced visual salience based image processing and pattern recognition detection methods. In this paper, the fabric defect detection algorithm based on visual salience is deeply explored. Considering the complex texture characteristics of fabric image, the direction and randomness of fabric defect detection algorithm are considered. This paper simulates the hierarchical processing mechanism of human visual perception path, constructs a fabric defect detection model based on visual salience, and proposes an effective fabric defect detection algorithm, which combines wavelet transform or stationary wavelet transform with background estimation. A fabric defect detection algorithm based on stationary wavelet transform and background estimation is proposed. Firstly, the fabric image is obtained by wavelet transform or stationary wavelet transform. The multi-background images of feature images are obtained by partition processing, and the Euclidean distance between the original image and each background image is obtained. After fusion, the visual salience images containing candidate defect regions are obtained. Finally, the Euclidean distance between the original image and each background image is obtained. Gao Si distribution model based on global estimation obtains defect salience map and detects defects by image segmentation. Experimental results show that the proposed algorithm can locate defect region accurately. In order to realize the effective detection of fabric defects and the higher detection accuracy of stationary wavelet transform, a fabric defect detection algorithm based on mutual information measurement and context analysis is proposed. The fabric image is partitioned evenly and partially overlapped to obtain the image block. Secondly, the information entropy between each image block and the surrounding K image blocks is calculated respectively. Finally, The information entropy of image blocks based on context analysis is used to obtain visual saliency images, and defects are detected by threshold segmentation. Experimental results show that the proposed algorithm can clearly locate defect regions without feature extraction. The detection results of fabric defects are better than the existing similarity detection algorithms.
【學(xué)位授予單位】：中原工學(xué)院
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TS101.97;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 李敏;崔樹(shù)芹;陳佳;;應(yīng)用視覺(jué)顯著性的小提花織物疵點(diǎn)檢測(cè)[J];紡織學(xué)報(bào);2016年12期

2 尉苗苗;李岳陽(yáng);蔣高明;叢洪蓮;;應(yīng)用最優(yōu)Gabor濾波器的經(jīng)編織物疵點(diǎn)檢測(cè)[J];紡織學(xué)報(bào);2016年11期

3 李敏;崔樹(shù)芹;謝治平;;高斯混合模型在印花織物疵點(diǎn)檢測(cè)中的應(yīng)用[J];紡織學(xué)報(bào);2015年08期

4 劉洲峰;趙全軍;李春雷;董燕;閆磊;;基于局部統(tǒng)計(jì)與整體顯著性的織物疵點(diǎn)檢測(cè)算法[J];紡織學(xué)報(bào);2014年11期

5 金永男;曹國(guó);;基于多層馬爾科夫隨機(jī)場(chǎng)模型的變化檢測(cè)[J];南京師范大學(xué)學(xué)報(bào)(工程技術(shù)版);2014年03期

6 李春雷;張兆翔;劉洲峰;廖亮;趙全軍;;基于紋理差異視覺(jué)顯著性的織物疵點(diǎn)檢測(cè)算法[J];山東大學(xué)學(xué)報(bào)(工學(xué)版);2014年04期

7 槐向兵;厲征鑫;劉建立;高衛(wèi)東;;基于輪廓波變換的織物疵點(diǎn)分割[J];計(jì)算機(jī)工程與設(shè)計(jì);2014年06期

8 管聲啟;高照元;吳寧;徐帥華;;基于視覺(jué)顯著性的平紋織物疵點(diǎn)檢測(cè)[J];紡織學(xué)報(bào);2014年04期

9 朱丹丹;潘如如;高衛(wèi)東;;基于傅里葉特征譜和相關(guān)系數(shù)的織物疵點(diǎn)檢測(cè)[J];計(jì)算機(jī)工程與應(yīng)用;2014年19期

10 楊曉波;;基于GMRF模型的統(tǒng)計(jì)特征畸變織物疵點(diǎn)識(shí)別[J];紡織學(xué)報(bào);2013年04期

，

本文編號(hào)：1570413