發(fā)布時(shí)間：2018-03-26 14:32

  本文選題：疵點(diǎn)檢測(cè)　切入點(diǎn)：Gabor濾波簇　出處：《武漢紡織大學(xué)》2017年碩士論文

【摘要】：提高疵點(diǎn)辨識(shí)精度和效率對(duì)提升紡織品質(zhì)量具有重要意義。針對(duì)疵點(diǎn)圖像光照不均和對(duì)比度低的問(wèn)題,開展基于Gabor小波簇的疵點(diǎn)圖像增強(qiáng)方法研究。首先,利用由3個(gè)尺度和5個(gè)方向的15個(gè)Gabor濾波簇對(duì)疵點(diǎn)圖片進(jìn)行不同方向和尺度的濾波,減少圖像不均和對(duì)比度低對(duì)特征提取精度的影響;然后,將濾波圖像劃分成面積相等互不重合的鄰域,并從鄰域中提取高維特征向量。接下來(lái),針對(duì)Gabor特征向量維數(shù)高和冗余信息大的問(wèn)題,使用等距映射方法對(duì)Gabor特征進(jìn)行非線性降維,剔除高維特征中冗余信息,強(qiáng)化分類器擬合能力,達(dá)到強(qiáng)化Gabor特征靈敏度的目的。其次,針對(duì)等距映射算法在Gabor特征降維過(guò)程中遇到的結(jié)構(gòu)參數(shù)選擇困難的問(wèn)題,應(yīng)用Ncut準(zhǔn)則作為適度函數(shù)建立結(jié)構(gòu)參數(shù)優(yōu)化模型,使用離散離子群算法進(jìn)行參數(shù)優(yōu)化,提出基于粒子群和Ncut準(zhǔn)則的等距映射參數(shù)優(yōu)化方法;針對(duì)等距映射算法新增樣本低維特征提取困難的問(wèn)題,利用樣本在高維空間和低維空間幾何結(jié)構(gòu)相同的假設(shè)建立新樣本低維嵌入模型,提出新增樣本低維特征提取方法。最后,將低維特征輸入概率神經(jīng)網(wǎng)絡(luò)分類器中進(jìn)行疵點(diǎn)辨識(shí),突破疵點(diǎn)圖像光照不均和對(duì)比度低等對(duì)疵點(diǎn)檢測(cè)精確的制約。實(shí)驗(yàn)研究中,利用2組不同紋理的疵點(diǎn)圖片數(shù)據(jù)進(jìn)行實(shí)驗(yàn)研究,結(jié)果表明:基于Gabor濾波簇和等距映射算法的疵點(diǎn)檢測(cè)準(zhǔn)確率達(dá)97%左右。但是,同時(shí)也存在濾波器數(shù)量多、運(yùn)算量大的問(wèn)題。為提高疵點(diǎn)檢測(cè)效率,利用頻域協(xié)調(diào)算法抗噪能力強(qiáng)和計(jì)算量小優(yōu)點(diǎn),替代Gabor濾波器簇用于疵點(diǎn)圖像增強(qiáng),達(dá)到提高檢測(cè)效率的目的。針對(duì)頻域協(xié)調(diào)算法在疵點(diǎn)檢測(cè)中遇到的疵點(diǎn)辨識(shí)精度受高斯濾波器模板尺寸影響大的問(wèn)題,利用Ncut準(zhǔn)則作為適度函數(shù),建立高斯濾波器模板尺寸優(yōu)化模型,使用離散離子群算法進(jìn)行參數(shù)優(yōu)化;針對(duì)Lab顏色空間對(duì)單一顏色紡織品疵點(diǎn)顯著效果不明顯的問(wèn)題,利用HSV顏色空間代替Lab顏色空間,強(qiáng)化顯著效果;針對(duì)色調(diào)特征、飽和度特征和亮度特征取值范圍不同且變化不一致導(dǎo)致顯著值不能很好地體現(xiàn)各個(gè)分量作用的問(wèn)題,展開了色調(diào)特征、飽和度特征和亮度特征的歸一化研究,建立顯著值歸一化模型。最后,采用灰度共生矩陣進(jìn)行特征提取,將提取的特征向量輸入概率神經(jīng)網(wǎng)絡(luò)進(jìn)行疵點(diǎn)辨識(shí)。通過(guò)改進(jìn)頻域協(xié)調(diào)顯著方法和Gabor濾波簇方法的對(duì)比實(shí)驗(yàn)研究發(fā)現(xiàn):基于改進(jìn)頻域協(xié)調(diào)顯著算法的疵點(diǎn)檢測(cè)方法能夠在保證疵點(diǎn)檢測(cè)精度的前提下,運(yùn)算速度比Gabor小波方法提高70%。
[Abstract]:Improving the accuracy and efficiency of defect identification is of great significance to improve the quality of textiles. Aiming at the problem of uneven illumination and low contrast of defect image, the defect image enhancement method based on Gabor wavelet cluster is studied. Using 15 Gabor filter clusters with three scales and five directions to filter defect images in different directions and scales to reduce the influence of uneven image and low contrast on the accuracy of feature extraction. The filtered image is divided into two neighborhoods whose area is equal to each other, and high dimensional feature vectors are extracted from the neighborhood. Then, for the problems of high dimension of Gabor eigenvector and large redundant information, The method of equidistant mapping is used to reduce the nonlinear dimension of Gabor features, eliminate redundant information from high dimensional features, and enhance the classifier fitting ability to enhance the sensitivity of Gabor features. Aiming at the difficulty of selecting structural parameters in the process of Gabor feature dimensionality reduction using the isometric mapping algorithm, the structural parameter optimization model is established by using the Ncut criterion as an appropriate function, and the discrete ion swarm algorithm is used to optimize the structure parameters. A parameter optimization method for equidistant mapping based on particle swarm optimization and Ncut criterion is proposed, and it is difficult to extract low-dimensional feature of new samples in offset mapping algorithm. Based on the assumption that the geometric structure of samples is the same in high-dimensional space and low-dimensional space, a new low-dimensional embedding model of samples is established, and a new low-dimensional feature extraction method is proposed. Finally, the low-dimensional feature is input into the probabilistic neural network classifier for defect identification. In the experimental research, two groups of defect image data of different textures are used to carry out experimental research. The results show that the defect detection accuracy is about 97% based on Gabor filter cluster and equidistant mapping algorithm. Using the advantages of strong anti-noise ability and small computational complexity of frequency domain coordination algorithm, instead of Gabor filter cluster, it can be used for defect image enhancement. Aiming at the problem that the defect identification accuracy of frequency domain coordination algorithm is greatly affected by the size of Gao Si filter template, the Ncut criterion is used as a moderate function. The template size optimization model of Gao Si filter is established, and the discrete ion swarm algorithm is used to optimize the parameters. Aiming at the problem that the Lab color space has no obvious effect on single color textile defects, the HSV color space is used to replace the Lab color space. Aiming at the problem that the significant value of each component is not well reflected due to the difference in the range of the values of hue feature, saturation feature and luminance feature, the color feature is developed. The normalization of saturation feature and luminance feature is studied, and the normalized model of significant value is established. Finally, the gray level co-occurrence matrix is used to extract the feature. The feature vector input probabilistic neural network is used for defect identification. Through comparing the improved frequency domain coordination saliency method and Gabor filter cluster method, it is found that the defect detection method based on improved frequency domain coordination saliency algorithm is based on improved frequency domain coordination saliency algorithm. The method can guarantee the precision of defect detection, The operation speed is 70% higher than that of Gabor wavelet method.
【學(xué)位授予單位】：武漢紡織大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 王傳桐;胡峰;徐啟永;吳雨川;余聯(lián)慶;;采用Gabor濾波簇和等距映射算法的織物疵點(diǎn)檢測(cè)方法[J];紡織學(xué)報(bào);2017年03期

2 李敏;崔樹芹;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

3 石美紅;張正;郭仙草;陳永當(dāng);;基于顯著紋理特征的織物疵點(diǎn)檢測(cè)方法[J];紡織學(xué)報(bào);2016年10期

4 包麗梅;;粒子群算法在工程優(yōu)化設(shè)計(jì)中的應(yīng)用[J];電子技術(shù)與軟件工程;2016年17期

5 胡峰;王傳桐;吳雨川;范良志;余聯(lián)慶;;基于改進(jìn)監(jiān)督LLE算法的故障特征提取方法[J];振動(dòng)與沖擊;2015年21期

6 胡峰;蘇訊;劉偉;吳雨川;范良志;;基于改進(jìn)局部線性嵌入算法的故障特征提取方法[J];振動(dòng)與沖擊;2015年15期

7 李鵬飛;姜萌;景軍鋒;張蕾;張宏偉;;基于小波分解和奇異值分解的織物疵點(diǎn)檢測(cè)[J];棉紡織技術(shù);2015年06期

8 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

9 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

10 于乃昭;姚志均;楊波;;一種改進(jìn)的頻率調(diào)諧顯著性檢測(cè)方法[J];艦船電子對(duì)抗;2013年01期

相關(guān)碩士學(xué)位論文 前1條

1 劉曉召;基于小波變換的紋理圖像多尺度分割算法研究[D];重慶大學(xué);2010年

，

本文編號(hào)：1668255