Supervised and unsupervised neural network methods applied to textile quality control based on improved wavelet feature extraction techniques

This paper aims at investigating novel solutions to the problem of textile defect detection from images, that can find applications in building robust quality control vision based systems in textile production. The proposed solutions focus on detecting defects from the textural properties of their corresponding wavelet transformed images. More specifically a novel methodology is investigated for discriminating defects in textile images by applying supervised and unsupervised neural classification techniques, employing multilayer perceptrons (MLP)-trained with the on-line backpropagation algorithm and Kohonen's Self-Organizing Feature Maps (SOFM) respectively. These parallel techniques are applied to innovative wavelet based feature vectors. These vectors are extracted from the wavelet transformed original images using the cooccurrence matrices framework and SVD analysis. The results of the proposed methodology are illustrated in defective textile images where the defective areas are recognized with about 98.5% accuracy.     

Face recognition using transform domain feature extraction and PSO-based feature selection

This paper presents two new techniques, viz., DWT Dual-subband Frequency-domain Feature Extraction (DDFFE) and Threshold-Based Binary Particle Swarm Optimization (ThBPSO) feature selection, to improve the performance of a face recognition system. DDFFE uses a unique combination of DWT, DFT, and DCT, and is used for efficient extraction of pose, translation and illumination invariant features. The DWT stage selectively utilizes the approximation coefficients along with the horizontal detail coefficients of the 2-dimensional DWT of a face image, whilst retaining the spatial correlation of pixels. The translation variance problem of the DWT is compensated in the following DFT stage, which also exploits the frequency characteristics of the image. Then, all the low frequency components present at the center of the DFT spectrum are extracted by drawing a quadruple ellipse mask around the spectrum center. Finally, DCT is used to lay the ground for BPSO based feature selection. The second proposed technique, ThBPSO, is a novel feature selection algorithm, based on the recurrence of selected features, and is used to search the feature space to obtain a feature subset for recognition. Experimental results obtained by applying the proposed algorithm on seven benchmark databases, namely, Cambridge ORL, UMIST, Extended Yale B, CMUPIE, Color FERET, FEI, and HP, show that the proposed system outperforms other FR systems. A significant increase in the recognition rate and a substantial reduction in the number of features required for recognition are observed. The experimental results indicate that the minimum feature reduction obtained is 98.2% for all seven databases.     

基于小波域差值系数的织物疵点分割与识别

小波分解系数的织物疵点特征曲线容易受各层周期性噪声的影响,不能有效提取特征和定位疵点区域.提出了小波域差值系数的织物疵点分割与识别方法.首先将小波分解后的水平和垂直高频系数与平滑系数相减,除去周期性噪声,然后,分别提取水平和垂直差值系数熵、能量、方差曲线的最大值、均值及方差特征参数,最后利用支持向量机进行分类识别.仿真...     

A 2-D wavelet decomposition-based bag-of-visual-words model for land-use scene classification

Previous works about spatial information incorporation into a traditional bag-of-visual-words (BOVW) model mainly consider the spatial arrangement of an image, ignoring the rich textural information in land-use remote-sensing images. Hence, this article presents a 2-D wavelet decomposition (WD)-based BOVW model for land-use scene classification, since the 2-D wavelet decomposition method does well not only in textural feature extraction, but also in the multi-resolution representation of an image, which is favourable for the use of both spatial arrangement and textural information in land-use images. The proposed method exploits the textural structures of an image with colour information transformed into greyscale. Moreover, it works first by decomposing the greyscale image into different sub-images using 2-D discrete wavelet transform (DWT) and then by extracting local features of the greyscale image and all the decomposed images with dense regions in which a given image is evenly sampled by a regular grid with a specified grid space. After that, the method generates the corresponding visual vocabularies and computes histograms of visual word occurrences of local features found in each former image. Specifically, the soft-assignment or multi-assignment (MA) technique is employed, accounting for the impact of clustering on visual vocabulary creation that two similar image patches may be clustered into different clusters when increasing the size of visual vocabulary. The proposed method is evaluated on a ground truth image dataset of 21 land-use classes manually extracted from high-resolution remote-sensing images. Experimental results demonstrate that the proposed method significantly outperforms previous methods, such as the traditional BOVW model, the spatial pyramid representation-based BOVW method, the multi-resolution representation-based BOVW method, and so on, and even exceeds the best result obtained from the creator of the land-use dataset. Therefore, the proposed approach is very suitable for land-use scene classification tasks.     

基于音频特征和低频系数较小值的水印算法

提出一种基于音频特征和DWT低频系数相对较小值的数字水印算法。分析音频帧的过零率及短时能量,选取适当的阈值初步舍弃表明信号中高频信号成分的音频帧,筛选出待处理的音频帧。将选定的音频帧拼接在一起进行小波变换,选取低频系数并分段,通过相邻3个水印比特组合的二进制之和确定水印在该段中的嵌入位置,将系数修改为相邻系数中较小的值。实验结果表明,该算法通过对音频特征的分析,能降低提取低频分量的时间复杂度,实现水印信息的盲检测,提高水印的鲁棒性。     

A cluster-based wavelet feature extraction method and its application

In this paper, a new cluster-based approach is proposed for extracting features from the coefficients of a two-dimensional discrete wavelet transform. The wavelet coefficients from the matrix of each frequency channel are segregated into non-overlapping clusters in an unsupervised mode using a set of application-specific representative images. In practical situations, this set of representative images can be the same as the ones kept aside for training a classifier. The proposed method divides the matrices of computed wavelet coefficients into disjoint clusters that are centered around the position of dominant coefficients. The features that can distinguish images of one class from those of other classes are obtained by computing energies of the clusters. The feature vectors so obtained are then presented as input patterns to an image classifier, such as a neural network. Experimental results based on the applications for texture classification and wood surface defect detection have shown that the proposed cluster-based wavelet feature extraction method is able to effectively extract important intrinsic information content from the test images, and increase the overall classification accuracy as compared with conventional feature extraction methods.     

FPGA-based IP cores implementation for face recognition using dynamic partial reconfiguration

This paper presents a combination of novel feature vectors construction approach for face recognition using discrete wavelet transform (DWT) and field programmable gate array (FPGA)-based intellectual property (IP) core implementation of transform block in face recognition systems. Initially, four experiments have been conducted including the DWT feature selection and filter choice, features optimisation by coefficient selections and feature threshold. To examine the most suitable method of feature extraction, different wavelet quadrant and scales have been evaluated, and it is followed with an evaluation of different wavelet filter choices and their impact on recognition accuracy. In this study, an approach for face recognition based on coefficient selection for DWT is presented, and the significant of DWT coefficient threshold selection is also analysed. For the hardware implementation, two architectures for two-dimensional (2-D) Haar wavelet transform (HWT) IP core with transpose-based computation and dynamic partial reconfiguration (DPR) have been synthesised using VHDL and implemented on Xilinx Virtex-5 FPGAs. Experimental results and comparisons between different configurations using partial and non-partial reconfiguration processes and a detailed performance analysis of the area, power consumption and maximum frequency are also discussed in this paper.     

基于感兴趣区的小波域彩色图像检索新方法

提出了一种基于感兴趣区的小波域彩色图像检索新方法.该方法首先结合人眼视觉感知特性,在小波变换域内利用K-均值聚类提取出感兴趣区域,然后以感兴趣区的小波系数局部能量作为纹理特征,颜色均值和均方差作为颜色特征,重心坐标作为位置特征,计算图像间内容的相似度并进行检索.仿真实验结果表明,当图像中有明显的感兴趣区域时（特别是背景简单的图像）,该方法能够更加准确地查找出用户所需内容的图像,明显地提高了检索精度.     

Applying wavelets transform,rough set theory and support vector machine for copper clad laminate defects classification

In this paper, we present a multi-resolution approach for the inspection of local defects embedded in homogeneous copper clad laminate (CCL) surfaces. The proposed method does not just rely on the extraction of local textural features in a spatial basis. It is based mainly on reconstructed images using the wavelet transform and inverse wavelet transform on the smooth subimage and detail subimages by properly selecting the adequate wavelet bases as well as the number of decomposition levels. The restored image will remove regular, repetitive texture patterns and enhance only local anomalies. Based on these local anomalies, feature extraction methods can then be used to discriminate between the defective regions and homogeneous regions in the restored image. Rough set feature selection algorithms are employed to select the feature. Rough set theory can deal with vagueness and uncertainties in image analysis, and can efficiently reduce the dimensionality of the feature space. Real samples with four classes of defects have been classified using the novel multi-classifier, namely, support vector machine. Effects of different sampling approach, kernel functions, and parameter settings used for SVM classification are thoroughly evaluated and discussed. The experimental results were also compared with the error back-propagation neural network classifier to demonstrate the efficacy of the proposed method.     

Enhanced Gabor wavelet correlogram feature for image indexing and retrieval

In this paper, a new feature scheme called enhanced Gabor wavelet correlogram (EGWC) is proposed for image indexing and retrieval. EGWC uses Gabor wavelets to decompose the image into different scales and orientations. The Gabor wavelet coefficients are then quantized using optimized quantization thresholds. In the next step, the autocorrelogram of the quantized wavelet coefficients is computed in each wavelet scale and orientation. Finally, the EGWC index vector simply consists of the autocorrelogram coefficients. Due to non-orthogonality of Gabor decomposition, the resulting wavelet coefficients suffer from redundancy, which increases the computational cost and reduces the effectiveness of EGWC. Here, we present a solution to handle the redundancy problem using non-maximum suppression and adjustment of autocorrelogram distance parameters as a function of the wavelet scale. The retrieval results obtained by applying EGWC to index two image databases with 5,000 natural images and 1,792 texture images demonstrated its better performance in terms of retrieval rates with respect to the state-of-the-art content-based and multidirectional texture indexing algorithms.     

Applying wavelets transform and support vector machine for copper clad laminate defects classification

In this paper, we present a multi-resolution approach for the inspection local defects embedded in homogeneous copper clad laminate (CCL) surfaces. The proposed method does not rely on the extraction of local textural features in a spatial basis. It is based mainly on the wavelet transform and inverse wavelet transform on the smooth subimage and detail subimages by properly selecting the adequate decomposition levels. The restored image will remove regular, repetitive texture patterns and enhance only local anomalies. Based on these local anomalies, feature extraction methods can then be used to discriminate between the defective regions and homogeneous regions in the restored image. Real samples with five classes of defects have been classified using this novel multi-classifier, namely, support vector machine. The experimental results show the efficacy of the proposed method.     

Facial feature extraction using complex dual-tree wavelet transform

In this paper, we propose a novel method for facial feature extraction using the directional multiresolution decomposition offered by the complex wavelet transform. The dual-tree implementation of complex wavelet transform offered by Selesnick is used (DT-DWT(S)) [I.W., Selesnick, R.G. Baraniuk, N.C. Kingsbury, The dual-tree complex wavelet transform, IEEE Signal Processing Magazine, 6, s.l., IEEE, November 2005, vol. 22, pp. 123–151.]. In the dual-tree implementation, two parallel discrete wavelet transform (DWT) with different lowpass and highpass filters in different scales are used. The linear combination of subbands generated by two parallel DWT is used to generate 6 different directional subbands with complex coefficients. A test statistic, which is derived with absolute value of complex coefficient, whose distribution matches very closely with the directional information in the 6 subbands of the DT-DWT(S) is derived and used for detecting facial feature edges. The use of the complex wavelet transform is motivated by the fact that it helps eliminate the effects of non-uniform illumination, and the directional information provided by the different subbands makes it possible to detect edge features with different directionalities in the corresponding image. Edge information of facial area is enhanced using multiresolution structure of DT-DWT(S). The proposed method also employs an adaptive skin colour model instead of a predefined skin colour statistic. The model is developed with a unimodal Gaussian distribution using the skin region which is extracted excluding the detected edge map obtained from the DT-DWT(S). By combining the edge information obtained by using DT-DWT(S) and the non-skin areas obtained from the pixel statistics, the facial features are extracted. The algorithm is tested over the well known Carnegie Mellon University (CMU) and Marks Weber face databases. The average detection rate of the proposed method using DT-DWT(S) provides up to 9.6% improvement over the same method using discrete wavelet transform (DWT).     

基于纹理的自适应提升小波变换图像压缩

经典二维小波变换仅在图像的水平和竖直方向应用小波滤波,不能提供灵活的方向信息,对纹理信息丰富的自然图像稀疏化效果不理想,在基于小波变换的图像压缩中还需改进.为了实现更有效的图像的稀疏表示,文中提出一种新型的基于图像纹理的自适应提升小波变换:根据局部特征将图像自适应分块,预先判断局部图像纹理方向,保持正交性质不变;沿纹理方向应用小波滤波,结合提升变换格式实现即位运算;沿纹理方向插值获取分数像素值,保护纹理信息不被破坏,总体变换对图像纹理描述更有效;结合JPEG2000中的编码方法EBCOT,对变换系数和方向信息分别编码,应用于图像压缩.仿真实验是在数值结果和视觉效果上将文中方法和JPEG2000方法作比较,以体现文中方法的优越性.     

人眼视觉感知特性的非下采样Contourlet变换域多聚焦图像融合

目的针对传统的单特征融合方法不足以衡量像素清晰度的问题,同时综合考虑非下采样Contourlet变换(NSCT)系数特点及人眼视觉感知特性,提出一种基于NSCT的多聚焦图像融合方法。方法首先对来自同一场景待融合的源图像进行NSCT变换;然后对低频分量采用基于局部可见度、局部视觉特征对比度和局部纹理特征的综合特征信息进行融合;对高频分量采用基于邻域和兄弟信息归一化的关联权重局部视觉特征对比度进行融合;最后进行逆NSCT变换得到融合图像。结果将本文方法与传统离散小波变换(DWT)、移不变小波变换(SIDWT)、CT(Contottral变换)、NSCT及基于邻域和兄弟信息的NSCT域多聚焦图像融合方法进行了实验对比,本文方法能获得更好的视觉效果以及较大的边缘信息保留值和互信息值。结论定性和定量的实验结果表明了本文方法的有效性。     

Automated extraction of street-scene objects from mobile lidar point clouds

Mobile laser scanning or lidar is a new and rapid system to capture high-density three-dimensional (3-D) point clouds. Automatic data segmentation and feature extraction are the key steps for accurate identification and 3-D reconstruction of street-scene objects (e.g. buildings and trees). This article presents a novel method for automated extraction of street-scene objects from mobile lidar point clouds. The proposed method first uses planar division to sort points into different grids, then calculates the weights of points in each grid according to the spatial distribution of mobile lidar points and generates the geo-referenced feature image of the point clouds using the inverse-distance-weighted interpolation method. Finally, the proposed method transforms the extraction of street-scene objects from 3-D mobile lidar point clouds into the extraction of geometric features from two-dimensional (2-D) imagery space, thus simplifying the automated object extraction process. Experimental results show that the proposed method provides a promising solution for automatically extracting street-scene objects from mobile lidar point clouds.     

基于离散小波变换的数字音频水印

该文根据小波变换的时频分析特性,提出了一种在数字音频信号中加入二值标志图像的水印嵌入方法。该方法结合人的听觉特性,将水印和原始音频数据分别进行小波变换,将变换后水印和音频小波系数更好地融合,使水印不可感知。实验结果表明,利用该方法嵌入的二值标志图像水印对一般的信号处理具有较好的不可感知性和鲁棒性。所提出的方法在数字音频的版权保护和身份验证方面具有特殊的保密性。     

基于小波能量特性的图像增强研究

为了提高图像的清晰度使之更适合于人的视觉特性或机器的识别,需要对图像的特征或边缘进行加强.本文根据图像的小波系数反映了图像的频率和能量的分布特性,提出了依据各尺度的小波分解得到的子图块能量的分布来相应地采取阀值.从而,依据阀值对子图进行系数变换,之后通过小波重构得到最终的增强图像.     

一种多尺度高光谱影像小波分形维特征计算方法

提出了一种基于高光谱曲线小波分形测度的高光谱影像多尺度分形维特征分析方法。对高光谱影像的光谱响应曲线的小波域高频和低频系数统计特性、分形特征进行了分析,提出以小波低频分形维表征原始光谱曲线分形特征,以小波系数高频分形维表征高光谱细节特征方法,设计了基于高光谱曲线小波分形维的多尺度特征计算算法,实验结果表明,小波分形维值可有效表征丰富的光谱特征,可用于高光谱影像特征提取和分类。     

手写体数字识别与认证的小波特征提取

本文提出了基于Kirsch边缘增强的二维小波特征与二维复小波特征的提取技术。这两类特征与几何特征融合识别手写体数字。此外,对所提取的小波特征提取方法的优点进行了讨论。最后进行的手写体数字识别与认证实验表明,这两类混合特征的集合能获得很好的识别与认证性能。