Real-time defect detection of steel wire rods using wavelet filters optimized by univariate dynamic encoding algorithm for searches

We propose a new defect detection algorithm for scale-covered steel wire rods. The algorithm incorporates an adaptive wavelet filter that is designed on the basis of lattice parameterization of orthogonal wavelet bases. This approach offers the opportunity to design orthogonal wavelet filters via optimization methods. To improve the performance and the flexibility of wavelet design, we propose the use of the undecimated discrete wavelet transform, and separate design of column and row wavelet filters but with a common cost function. The coefficients of the wavelet filters are optimized by the so-called univariate dynamic encoding algorithm for searches (uDEAS), which searches the minimum value of a cost function designed to maximize the energy difference between defects and background noise. Moreover, for improved detection accuracy, we propose an enhanced double-threshold method. Experimental results for steel wire rod surface images obtained from actual steel production lines show that the proposed algorithm is effective.     

基于谱直方图表示和支持向量机的纹理分类

在纹理分类中采用谱直方图表示(SHR),每个图像窗表示一个包含滤波后图像直方图的特征向量,而直方图是图像谱表示的连接桥梁.在滤波器选择算法之前,结合每个图像分块和滤波器的独立谱表示和直方图,可以获得更加低层的局部特征.最后,时所有独立滤波器采用滤波器选择算法来得到所需的少量滤波器.为了保证分类的可靠性,选择高斯径向基函数(RBF)进行谱直方图表示,采用支持向量机(SVMs)作为分类函数.对本文方法和其它两种方法:Gabor滤波和独立成分分析(ICA)进行了纹理分类和脸部识别的比较实验.实验结果表明,本文方法具有更高的分类准确性,也证明了SVMs优秀的泛化能力.     

Distance-classifier correlation filters for multiclass target recognition

We describe a correlation-based distance-classifier scheme for the recognition and the classification of multiple classes. The underlying theory uses shift-invariant filters to compute distances between the input image and ideal references under an optimum transformation. The original distance-classifier correlation filter was developed for a two-class problem. We introduce a distance-classifier correlation filter that simultaneously considers multiple classes, and we show that the earlier two-class formulation is a special case of the classifier presented. Initial results are presented to demonstrate the discrimination- and distortion-tolerance capabilities of the proposed filter.     

R-D匹配优选小波包零树图像压缩

为使R-D小波包优选算法与零树编码在量化精度上更好地匹配，对R-D小波包优选算法的寻优次序进行修改，使小波包各节点的量化精度差异不超过一位。实验结果表明，R-D匹配优选小波包零树编码可以取得与R—D优选小波包零树编码相当或比后者更好的图像压缩效果，可见R-D匹配优选算法是更适合零树编码的小波包优选算法。     

Gray-level computer-generated hologram filters for multiple-object correlation

Synthesis of gray-level computer-generated holograms allows for an increase of the information storage capability that is usually achieved with conventional binary filters. This is mainly because more degrees of freedom are available. We propose to profit from this feature by synthesizing complex filters formed by many superimposed holograms, each with a different carrier frequency. We apply these gray-level filters to perform multichannel correlation and in this way enhance the capability of optical correlators to process the information in parallel and simultaneously. First, we analyze the behavior of some performance criteria on the impulse response and on the correlation as a function of the number of holograms that are multiplexed. Then we show the results of two experiments: In the first a composed phase-only filter is used in a multiple-object recognition process. In the second a composed synthetic discriminant function filter is used to implement an object classification by means of a binary code.     

应用ICA滤波器技术提取图像纹理特征

针对纹理图像分类问题,本文提出了一种应用ICA滤波器技术提取图像纹理特征的方法.该方法首先从训练图像集中随机抽取图像块作为观测信号,应用ICA技术,提取滤波器组.然后根据训练样本图像对滤波器组的响应值来评估和选择滤波器组,达到降维的目的.最后利用滤波器组对测试图像进行滤波,得到该图像的滤波响应结果,从该响应结果中得到最大响应滤波器编号,提取其直方图作为图像的全局特征和局部特征.对Brodatz纹理图像集中108个纹理类别进行了分类实验,结果表明,与MPEG-7纹理描述子相比,该图像特征对纹理图像具有更好的分类效果.     

Fault Diagnosis for IC Engines Using Wavelet Packet and Image Processing

There are few applications of image processing technology for diagnosing and state monitoring for internal combustion (IC) engines, which is discussed in detail in this paper. The time-frequetwy distribution images of cylinder head vibration signals are obtained by decomposing them with a wavelet packet algorithm. It is the first time that toe look at time-frequency distribution images from the point of images. Based on this, a new method for applying image processing technology for diagnosing and state monitoring for internal combustion engines is presented in this paper. A valve fault diagnosis model is set up by image matching, which is realized on a four-stroke, six-cylinder diesel engine. At the same time,some notes are presented in this paper. It has been proved that it is of no good effect to diagnose with histograms of time-frequency images generated by cylinder head vibration signals that have been processed with a wavelet packet algorithm. The reason is given in this paper. Comparisons of diagnosing effect are carried out between noise-added signals and original signals. It has little effect on diagnosing results after signals have been added with noise. The results show that this method has a clear physical meaning and is of good engineering practicability, feasibility, good precision and high speed.     

Fault Diagnosis of a Turbo—unit Based on Wavelet Packet Theory

In this paper we studied the fault feature of the generator set and the characteristics of wavelet packet theory for signal de-noising.The vibration signal of the generator set in different states is ana-lyzed by using the signal re-construction technique of the wavelet packet theory.The time domain method is given for the generator set fault diagnosis.The experiment results show that the wavelet packet theory can be used to directly identify the state of the generator set and provide a credible new idea for complex machinery fault diagnosis.     

基于小波包分解和PCA-Attention-LSTM的舰船辐射噪声识别技术

为了改进舰船辐射噪声分类系统的性能,进一步提高识别准确率,文章提出了一种基于多特征的小波包分解在长短期记忆(LongShort-TermMemory,LSTM)网络中分类的方法。该方法首先通过小波包分解技术,分频段提取舰船辐射噪声的多种特征,将提取的特征利用主成分分析法(Principal Component Analysis, PCA)进行数据降维,通过添加注意力机制(Attention Mechanism)算法的LSTM网络,对辐射噪声结果分类,提高了学习效率和识别准确率。为了更精细地提取特征,分频段提取了舰船辐射噪声的时频域特征、小波变换特征和梅尔倒谱系数等特征,并将分频段与不分频段的特征、多特征与单一特征、不同信噪比间的算法性能进行对比。实验结果表明,基于小波包分解和PCA-Attention-LSTM的模型可以有效地提高舰船辐射噪声分类的性能,是一种可行的分类方法。     

Medical images compression for remote diagnosis using modified SPIHT data organization and fidelity enhancement filter

In this work, an 8 × 8 Discrete Cosine Transform (DCT) approach is adopted to perform DCT shrinkage, followed by modified set partitioning in hierarchical trees (SPIHT) data organization and fidelity enhancement filter for reducing the memory required to store a remote diagnosis and rapidly transmit it. The DCT shrinkage has the ability to retain the detailed characteristics of an image. By means of a simple transformation to gather the DCT spectrum data with the same frequency domain, the DCT shrinkage exploits all the characteristics of individual blocks to a global framework. In this scheme, insignificant DCT coefficients that correspond to the same spatial location in the high‐frequency sub‐bands can be used to reduce the redundancy by a combined function proposed in association with the modified SPIHT. Meanwhile, quad‐tree decomposition and a set of morphological filters for reducing the artifacts are presented. This set of filters employs 8 predefined morphological operations, namely 4 structuring elements (SE), each of which includes both dilation and erosion operations. The voting strategy is used to select the most suitable morphological filter for each block. Simulation results show that the image compression reduced the computational complexity to only a half of the wavelet based sub‐band decomposition and improved the quality of the reconstructed medical image in terms of both the peak signal‐to‐noise ratio (PSNR) and the perceptual results close to JPEG2000 and the original SPIHT at the same bit rate. © 2007 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 17, 49–61, 2007     

Wavelet-based image enhancement in x-ray imaging and tomography

We consider an application of the wavelet transform to image processing in x-ray imaging and three-dimensional (3-D) tomography aimed at industrial inspection. Our experimental setup works in two operational modes-digital radiography and 3-D cone-beam tomographic data acquisition. Although the x-ray images measured have a large dynamic range and good spatial resolution, their noise properties and contrast are often not optimal. To enhance the images, we suggest applying digital image processing by using wavelet-based algorithms and consider the wavelet-based multiscale edge representation in the framework of the Mallat and Zhong approach [IEEE Trans. Pattern Anal. Mach. Intell. 14, 710 (1992)]. A contrast-enhancement method by use of equalization of the multiscale edges is suggested. Several denoising algorithms based on modifying the modulus and the phase of the multiscale gradients and several contrast-enhancement techniques applying linear and nonlinear multiscale edge stretching are described and compared by use of experimental data. We propose the use of a filter bank of wavelet-based reconstruction filters for the filtered-backprojection reconstruction algorithm. Experimental results show a considerable increase in the performance of the whole x-ray imaging system for both radiographic and tomographic modes in the case of the application of the wavelet-based image-processing algorithms.     

Edge preserving filter of side scan sonar images with wavelet modulus maxima shift‐correlative technique

An edge preserving filter algorithm of side scan sonar (SSS) image based on wavelet modulus maxima shift‐correlative (WMMS) technique is proposed in this article. First, the proposed WMMS algorithm decomposes SSS image into multiscale wavelet coefficients. Then the modulus maxima, which are produced by catastrophe points, are extracted from wavelet coefficients. The algorithm matches these maxima across the different scales to identify signal or noise. After correcting the “drifting” phenomenon of modulus maxima, a correlation factor array of wavelet coefficients is constructed by strengthening the maxima dominated by signal and suppressing those maxima dominated by noise. By correlating wavelet coefficients with the correlation factor array, the WMMS strengthens the useful high‐frequency signal and weakens the noise. Finally, the algorithm restores SSS image from revised wavelet coefficients. We apply the WMMS algorithm to filter SSS images of the experimental sea areas. Results show that WMMS has advantages over traditional algorithms in suppressing noise and preserving useful high‐frequency information. © 2011 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 21, 349–355, 2011     

An effective approach for wavelet lifting based on filter optimization and median operator

In JPEG2000, the Cohen–Daubechies–Feauveau (CDF) 9/7‐tap wavelet filter implemented by using the conventional lifting scheme has two problems. The first problem is that the filter coefficients are remaining complex; second, the conventional lifting scheme ignores image edges in the coding process. In this article, we propose an effective wavelet lifting scheme to solve these problems. For this purpose, we design the optimal 9/7‐tap wavelet filters in two steps. In the first step, we select the appropriate filter coefficients; in the second step, we employ a median operator to consider image edges. Experimental results from using the median lifting scheme and combining filter optimization and median lifting show that our proposed methods outperform the well‐known CDF 9/7‐tap wavelet filter of JPEG2000 on edge‐dominant images. © 2010 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 20, 359–366, 2010     

Texture Analysis for Flaw Detection in Ultrasonic Images

In this paper, we present two approaches for flaw detection in TOFD (Time of Flight Diffraction) images based on texture features. Texture is one of the most important features used in recognizing patterns in an image. The paper describes texture features by two methods: Multiresolution analysis such as wavelet transforms and Gabor filters bank. The two-dimensional wavelet transform is used to decompose the input image into a multiresolution framework. The textural statistical parameters are used to allow the choice of the decomposition channel. The Gabor filter is a Gaussian kernel function modulated by a sinusoidal plane wave. All Gabor filters can be generated from one mother wavelet by dilation and rotation. These filters represent an appropriate choice for tasks requiring simultaneous measurement in both space and frequency domains. The most relevant features are optimized by Principal Components Analysis (PCA) and used as input data on a Fuzzy C-Mean clustering classifier. We use two classes: ‘defects’ or ‘no defects’. The proposed approach is tested on the TOFD image achieved in an industrial field.     

Filter for biomedical imaging and image processing

Image filtering techniques have numerous potential applications in biomedical imaging and image processing. The design of filters largely depends on the a priori, knowledge about the type of noise corrupting the image. This makes the standard filters application specific. Widely used filters such as average, Gaussian, and Wiener reduce noisy artifacts by smoothing. However, this operation normally results in smoothing of the edges as well. On the other hand, sharpening filters enhance the high-frequency details, making the image nonsmooth. An integrated general approach to design a finite impulse response filter based on Hebbian learning is proposed for optimal image filtering. This algorithm exploits the interpixel correlation by updating the filter coefficients using Hebbian learning. The algorithm is made iterative for achieving efficient learning from the neighborhood pixels. This algorithm performs optimal smoothing of the noisy image by preserving high-frequency as well as low-frequency features. Evaluation results show that the proposed finite impulse response filter is robust under various noise distributions such as Gaussian noise, salt-and-pepper noise, and speckle noise. Furthermore, the proposed approach does not require any a priori knowledge about the type of noise. The number of unknown parameters is few, and most of these parameters are adaptively obtained from the processed image. The proposed filter is successfully applied for image reconstruction in a positron emission tomography imaging modality. The images reconstructed by the proposed algorithm are found to be superior in quality compared with those reconstructed by existing PET image reconstruction methodologies.     

Computer-generated multiple-object discriminant correlation filters: design by simulated annealing

The computer generation of multiple-object discriminant correlation filters is studied. The quantization of filter functions influences the correlation response. This may cause misdetection or incorrect classification of patterns and is especially serious in the case of multiple-object discriminant filters. We propose synthesizing the matched-filter functions by the simulated-annealing algorithm. The recording of Lohmann-type computer-generated holograms is considered. By this method the filter functions can be encoded with a reduction in the quantization levels of amplitude and phase. Acomputer simulation is performed, and the expected correlation responses are obtained.     

Segmentation of SAR images using the wavelet transform

Multiresolution representation of images using the wavelet transform is a new approach for the analysis of image information content. The transform can be computed efficiently by a pyramidal algorithm based on convolution with quadrature mirror filters. The result is a set of subband images which consists of a lower resolution version of the original image and a sequence of detail images containing higher frequency spectral information. We used this representation for the supervised segmentation of polarimetric SAR images of the San Francisco Bay area acquired by the airborne JPL system for identifying various terrain covers. Since the wavelet transform generates the localized spatial and spectral information simultaneously, detailed knowledge of the texture variations within an image can be extracted from the data in the spectral subbands. The segmentation algorithm developed in this paper is formulated by taking into consideration both the intensity and the texture information. For polarimetric SAR images, the classification accuracy can be enhanced, if the combined data from copolarized and cross-polarized images are used in the discrimination process. In contrast to other texture segmentation approaches, this algorithm does not require extensive calculations.©1993 John Wiley & Sons Inc     

动态定量称量包装系统滤波算法

目的为了提高动态定量称量包装精度,提升数据采集和信号测量的准确性。方法分析定量称量系统的组成以及工作原理,并针对系统中存在的噪声,提出一种基于小波包滤波的称量包装滤波算法。通过塔式分解方法实现快速离散小波包变换,由离散卷积方程得到小波包分解系数,进而完成滤波算法的重组。结果通过仿真和实验结果可知,小波包滤波方法能够很好地滤除动态称量信号中的噪声,提升了有用信号的品质。结论该滤波算法提升了动态定量称量系统的稳定性,提高了称量包装精度。     

Wavelet networks for face processing

Wavelet networks (WNs) were introduced in 1992 as a combination of artificial neural radial basis function (RBF) networks and wavelet decomposition. Since then, however, WNs have received only a little attention. We believe that the potential of WNs has been generally underestimated. WNs have the advantage that the wavelet coefficients are directly related to the image data through the wavelet transform. In addition, the parameters of the wavelets in the WNs are subject to optimization, which results in a direct relation between the represented function and the optimized wavelets, leading to considerable data reduction (thus making subsequent algorithms much more efficient) as well as to wavelets that can be used as an optimized filter bank. In our study we analyze some WN properties and highlight their advantages for object representation purposes. We then present a series of results of experiments in which we used WNs for face tracking. We exploit the efficiency that is due to data reduction for face recognition and face-pose estimation by applying the optimized-filter-bank principle of the WNs.     

Implementation of arbitrary real-valued correlation filters for the shadow-casting incoherent correlator

We describe an incoherent correlator, based on the shadow-casting principle, that is able to implement any real-valued linear correlation filter. The correlation filter and the input image are displayed on commercial liquid-crystal television (LCTV) panels. Although it cannot handle high-resolution images, the incoherent correlator is lensless, compact, low cost, and uses a white-light source. A bipolar technique is devised to represent any linear filter, computed from a single reference image or composite, in the correlator. We demonstrate experimentally the efficiency of the design in the case of optimal trade-off (OT) filters and optimal trade-off synthetic discriminant function (OT-SDF) filters.