本文選題：鋼板缺陷檢測(cè) + 不均勻光照矯正　； 參考：《大連海事大學(xué)》2017年碩士論文

【摘要】：鋼材行業(yè)作為國(guó)民經(jīng)濟(jì)的基礎(chǔ)產(chǎn)業(yè),在經(jīng)濟(jì)建設(shè)、社會(huì)發(fā)展等多方面都發(fā)揮著重要作用,但鋼板表面缺陷嚴(yán)重降低鋼材質(zhì)量,鋼板表面缺陷檢測(cè)是保證鋼材質(zhì)量的關(guān)鍵因素之一。本文對(duì)鋼板表面缺陷檢測(cè)與分類算法進(jìn)行了較為深入的研究,具體成果如下:(1)針對(duì)鋼板表面圖像數(shù)據(jù)量大、計(jì)算效率低的問(wèn)題,本文構(gòu)造了基于梯度的鋼板表面圖像感興趣區(qū)域檢測(cè)算法。通過(guò)鋼板表面圖像的局部梯度統(tǒng)計(jì)值判斷有無(wú)缺陷,該算法可以減小系統(tǒng)后端圖像處理壓力,提升整體效率。(2)針對(duì)部分缺陷圖像受不均勻光照影響且對(duì)比度低的問(wèn)題,本文構(gòu)造了基于Retinex算法與導(dǎo)向?yàn)V波器的不均勻光照矯正和增強(qiáng)算法。利用導(dǎo)向?yàn)V波器估計(jì)光照分量,根據(jù)Retinex算法計(jì)算反射分量,并對(duì)反射分量進(jìn)行增強(qiáng),提高對(duì)比度,恢復(fù)原始灰度信息。(3)針對(duì)缺陷分割準(zhǔn)確度問(wèn)題,本文構(gòu)造了基于Center-Surround Difference的缺陷圖像分割算法。利用帶權(quán)重的組合DoG(Difference of Gaussian)濾波器對(duì)預(yù)處理后缺陷圖像進(jìn)行濾波,根據(jù)Center-Surround Difference提取圖像Local特征和Global特征,并將兩者線性融合,對(duì)融合后圖像進(jìn)行背景抑制和前景恢復(fù),利用自適應(yīng)閾值實(shí)現(xiàn)缺陷區(qū)域提取。(4)根據(jù)缺陷圖像分割前后所含的不同信息,提取36維特征值作為缺陷分類依據(jù)。針對(duì)缺陷分類精度問(wèn)題,從慣性權(quán)值和種群多樣性兩個(gè)方面對(duì)粒子群(Particle Swarm Optimization,PSO)算法進(jìn)行改進(jìn),利用改進(jìn)算法對(duì)前饋(Back Propagation,BP)神經(jīng)網(wǎng)絡(luò)進(jìn)行優(yōu)化,最終實(shí)現(xiàn)缺陷分類。實(shí)驗(yàn)結(jié)果表明,本文設(shè)計(jì)的算法能很好的實(shí)現(xiàn)缺陷的檢測(cè)和分類識(shí)別,實(shí)驗(yàn)主觀效果和客觀效果保持一致。
[Abstract]:As the basic industry of the national economy, the steel industry plays an important role in economic construction, social development and other aspects, but the steel plate surface defects seriously reduce the quality of steel, Surface defect detection of steel plate is one of the key factors to ensure steel quality. In this paper, the surface defect detection and classification algorithm of steel plate is studied in depth. The concrete results are as follows: (1) aiming at the problem of large amount of image data and low computational efficiency of steel plate surface, In this paper, a gradient based region of interest detection algorithm for steel plate surface images is proposed. Based on the local gradient statistical value of the steel plate surface image, the algorithm can reduce the image processing pressure and improve the overall efficiency of image processing, aiming at the problem that some defective images are affected by uneven illumination and the contrast is low. In this paper, a nonuniform illumination correction and enhancement algorithm based on Retinex algorithm and guide filter is constructed. The illumination component is estimated by the guide filter, the reflection component is calculated according to the Retinex algorithm, and the reflection component is enhanced, the contrast is improved, the original gray level information is restored. A defect image segmentation algorithm based on Center-Surround Difference is proposed in this paper. A combined DoG(Difference of Gaussian filter with weights is used to filter the pre-processed defective image. The Local and Global features of the image are extracted according to Center-Surround Difference, and the two features are linearly fused to suppress the background and restore the foreground of the fused image. Based on the different information before and after the defect image segmentation, 36 dimensional eigenvalues are extracted as the basis of defect classification. Aiming at the accuracy of defect classification, the particle swarm optimization (PSOs) algorithm is improved from the aspects of inertia weight and population diversity. The improved algorithm is used to optimize the feedforward back Propagation (BP) neural network, and finally the defect classification is realized. The experimental results show that the algorithm designed in this paper can achieve the defect detection and classification, and the subjective and objective effects of the experiment are consistent.
【學(xué)位授予單位】：大連海事大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 李瑞帥;余淑華;潘凱;王圓;;圖像特征金字塔快速計(jì)算方法[J];電子世界;2014年07期

2 曾喜良;王金娟;;指紋分割的塊圖像梯度因子聚類法[J];計(jì)算機(jī)與數(shù)字工程;2008年07期

3 劉陳;王欣欣;李鳳霞;趙相坤;;一種快速保邊的圖像對(duì)象分割方法[J];北京理工大學(xué)學(xué)報(bào);2010年02期

4 朱薇;劉利剛;;圖像適應(yīng)算法中非冗余顯著圖的計(jì)算[J];中國(guó)圖象圖形學(xué)報(bào);2011年08期

5 柳有權(quán);吳宗勝;韓紅雷;吳恩華;;線條增強(qiáng)的建筑物圖像抽象畫(huà)生成[J];計(jì)算機(jī)輔助設(shè)計(jì)與圖形學(xué)學(xué)報(bào);2013年09期

6 吳駿,唐紅梅,肖志濤,賈志成;一種基于相位信息的圖像對(duì)稱性檢測(cè)方法[J];信號(hào)處理;2004年01期

7 邵靜;高雋;趙瑩;張旭東;;一種基于圖像固有維度的感知物體檢測(cè)方法[J];儀器儀表學(xué)報(bào);2008年04期

8 潘如如;高衛(wèi)東;;高緊度機(jī)織物圖像傾斜的自動(dòng)糾正[J];紡織學(xué)報(bào);2009年10期

9 劉貴喜,趙曙光,楊萬(wàn)海;基于梯度塔形分解的多傳感器圖像融合[J];光電子·激光;2001年03期

10 呂冀;高洪民;汪渤;周志強(qiáng);;圖像制導(dǎo)的目標(biāo)匹配算法與系統(tǒng)設(shè)計(jì)[J];彈箭與制導(dǎo)學(xué)報(bào);2009年05期

相關(guān)會(huì)議論文 前5條

1 張一鳴;劉亞t，

本文編號(hào)：1898704