Automatic classification of defects on the product surface in grinding and polishing

Grinding and polishing are standard operations in material processing. It is important to inspect and classify the potential defects existing on the product surfaces after grinding and polishing in order to obtain high quality in both functionality and aesthetics. Post-processing handling can be carried out after the defects have been correctly classified. A vision system already exists to detect and classify defects based on captured grayscale images automatically. The system is able to find and locate the defects precisely, but is incapable of placing those defects into the right predefined classes. The old system classifies the defects 30% of the time into the 15 predefined classes based on shape features. In this paper, a new classification strategy has been introduced using diverse extracted features. In addition to shape features, some other feature extraction methods were tried, e.g. Laws filter bank, DCT (Discrete Cosine Transformation) filter bank, Gabor filter bank, and statistical features based on co-occurrence matrix. The Support Vector Machine (SVM) was used as a multi-class classifier with input of the extracted features. By combining the Gabor filter features and the statistical features, the classification rate of the system can reach 82% overall right rate, which is applicable practically.     

基于Gabor小波自适应判别的单样本人脸识别

提出一种基于Gabor小波和LDA的人脸识别算法,借助通用训练集估计类内散布矩阵,使才传统LDA算法在单样本问题中可行。最后,在FERET人脸数据库上对所提方法进行了实验,结果表明该方法在单样本问题上取得了较好的结果。     

融合内外特征的性别分类

针对以往仅用人脸特征或头发特征来进行性别分类的片面性,提出了将两类特征相融合的性别分类方法.用对光照、尺度变化具有很强鲁棒性的Gabor小波变换提取人脸内部特征并用PCA方法降维.利用最小代价原理,将动态搜索技术用于图像空间取得头发区域,定义了头发长度、头发表面积两种外部特征,并提出了相应的特征提取方法.采用模糊神经网络对三种特征进行非线性融合.在 Essex 人脸库中进行了性别分类实验,取得了97.1%的准确率.     

第二小方向导数信息熵的兴趣点检测

目的 为了提高兴趣点检测的定位准确性和对噪声的鲁棒性,提出利用图像轮廓线及其邻域内像素点方向导数信息熵检测兴趣点的方法.方法 首先利用多方向Gabor虚部滤波器提取图像灰度变化信息得到第二小方向导数.然后利用Canny边缘检测器提取边缘映射,并填补断裂边缘映射提取边缘轮廓线.最后求解图像边缘轮廓线及其邻域内像素点对应的第二小方向导数所对应的信息熵归一化值并作为新的兴趣点测度.和直接由灰度变化信息及分析边缘轮廓形状或曲率提取兴趣点的方法相比,本文算法结合了两种算法的思想,利用轮廓线上及其邻域内的像素点梯度方向信息熵值作为兴趣点测度.同时不同于同质及边缘区域的梯度方向变化,兴趣点处的梯度方向变化信息呈现各向异性的特性,利用兴趣点第二小方向导数(第一小方向导数可能为零)对应的信息熵值作为新的兴趣点测度可提高算法的定位准确性.结果 通过对检测图像进行仿射变换和加入高斯噪声处理后,分别利用Harris算子、CSS算子、He&Yung算子和本文算法提取图像兴趣点,并比较各算法在仿射变换和高斯噪声情况下检测到的兴趣点的平均重复率和定位误差两个性能指标的平均值.其中本文算法的性能指标平均值为1.625,远高于Harris(3.25)、He&Yung(2.625)和CSS(2.5)三大兴趣点检测算子.结论 通过与典型的3种算法相对比,本文算法具有较好的平均重复率及噪声鲁棒性,尤其是图像在外界干扰的旋转变换和尺度变换下对兴趣点的定位性有着更好的检测性能.     

A new method for expiration code detection and recognition using gabor features based collaborative representation

Text in images and video contains important information for visual content understanding, indexing, and recognizing. Extraction of this information involves preprocessing, localization and extraction of the text from a given image. In this paper, we propose a novel expiration code detection and recognition algorithm by using Gabor features and collaborative representation based classification. The proposed system consists of four steps: expiration code location, character isolation, Gabor features extraction and characters recognition. For expiration code detection, the Gabor energy (GE) and the maximum energy difference (MED) are extracted. The performance of the recognition algorithm is tested over three Gabor features: GE, magnitude response (MR) and imaginary response (IR). The Gabor features are classified based on collaborative representation based classifier (GCRC). To encompass all frequencies and orientations, downsampling and principal component analysis (PCA) are applied in order to reduce the features space dimensionality. The effectiveness of the proposed localization algorithm is highlighted and compared with other existing methods. Extensive testing shows that the suggested detection scheme outperforms existing methods in terms of detection rate for large image database. Also, GCRC show very competitive results compared with Gabor feature sparse representation based classification (GSRC). Also, the proposed system outperforms the nearest neighbor (NN) classifier and the collaborative representation based classification (CRC).     

基于Gabor小波变换的ICA火灾图像纹理识别算法

针对火灾图像纹理识别问题,提出了基于Gabor小波变换的ICA火灾图像纹理识别算法,并根据火灾图像纹理识别特点进行了优化;首先用不同尺度和方向的Gabor滤波器对待识别图像滤波,得到其特征图像,然后将特征图像转化成特征向量作为ICA的输入,得到基矢量子空间,再将测试图像经过Gabor滤波器的特征向量投影到ICA子空间中得到系数向量作为目标识别特征,最后用支持向量机进行识别;通过与Gabor滤波器法和ICA方法的对比实验,表明该算法可以在火灾纹理图像的识别率上比传统方法提高5％以上,为火灾图像识别提供了一种新思路.     

人脸的民族特征抽取及其识别

人脸的民族特征是人脸信息描述的重要特征之一.首先构建了中国多民族人脸数据库,利用人脸识别技术提取民族面部特征和民族识别.在特征抽取方法中,采集人脸中的代数特征和几何特征,采用LDA(线性判别分析)算法提取人脸图像的代数特征.还构建了能够抽取人脸几何特征的弹性模板,并利用Gabor小波进行特征点定位.实验采用KNN和C5.0分别学习训练集中的代数特征和几何特征,并对测试集进行预测分类.实验结果表明,利用代数特征方法和几何特征方法对藏族、维吾尔族、壮族3个民族的平均识别准确率分别达到79%和90.95%.     

基于Gabor滤波的指纹图像识别研究与实现

采用基于Gabor滤波指纹识别算法进行指纹图像中心点计算、扇形化、归一化、Gabor滤波、特征提取以及比对,并利用Matlab仿真实现该算法.在仿真实验中建立一定数量的指纹库,对该算法进行比对分析.     

区域和局部信息结合的双向医学图像配准

提出了一种新的基于区域互信息和局部频率信息结合的双向图像配准测度。首先,以原参考图像为参考,计算出正向变换下图像的区域互信息和Gabor滤波后的得到局部频率 信息;同时,以输入图像为参考图像,计算出逆变换下的逆向互信息和局部频率信息。将正向与逆向变换下的互信息和局部频率信息各自相乘后求和,减去两幅图像对应的配准残 量,得到双向图像配准度量,用于对输入图像进行配准。仿真实验结果在验证分析结果的同时也表明,方法对图像噪声、分辨率等具有较高的鲁棒性,可有效提高配准的精度。     

基于Gabor滤波器的棉花杂质检测算法

棉花杂质检测方法对于提高织物质量和降低生产成本具有重要意义。针对工业环境中非均匀光照条件下的棉花图像设计基于Gabor滤波器的杂质检测算法,依据Otsu法和形态学滤波将图像分割为前景区、背景区和交界区,然后在图像前景和背景区域内分别使用Gabor滤波器提取图像的纹理特征。设计一种针对Gabor滤波输出的自适应阈值分割算法,结合形态学滤波和连通域分析检测出棉花中的杂质。实验结果表明,本文算法有效地消除了由于光照条件造成的干扰,可以精确地检测出棉花中常见的各种杂质。