Independent component analysis-based defect detection in patterned liquid crystal display surfaces

In this paper, we propose a machine vision approach for automatic detection of micro defects in periodically patterned surfaces and, especially, aim at thin film transistor liquid crystal display (TFT-LCD) panels. The proposed method is based on an image reconstruction scheme using independent component analysis (ICA). ICA is first applied to a faultless training image to determine the de-mixing matrix and the corresponding independent components (ICs). The ICs representing the global structure of the training image are then identified and the associated row vectors of those ICs in the de-mixing matrix are replaced with a de-mixing row representing the least structured region of the training image. The reformed de-mixing matrix is then used to reconstruct the TFT-LCD image under inspection. The resulting image can effectively remove the global structural pattern and preserve only local anomalies. A number of micro defects in different TFT-LCD panel surfaces are evaluated with the proposed method. The experiments show that the proposed method can well detect various ill-defined defects in periodically patterned surfaces.     

Defect detection in patterned wafers using anisotropic kernels

Wafer defect detection often relies on accurate image registration of source and reference images obtained from neighboring dies. Unfortunately, perfect registration is generally impossible, due to pattern variations between the source and reference images. In this paper, we propose a defect detection procedure, which avoids image registration and is robust to pattern variations. The proposed method is based on anisotropic kernel reconstruction of the source image using the reference image. The source and reference images are mapped into a feature space, where every feature with origin in the source image is estimated by a weighted sum of neighboring features from the reference image. The set of neighboring features is determined according to the spatial neighborhood in the original image space, and the weights are calculated from exponential distance similarity function. We show that features originating from defect regions are not reconstructible from the reference image, and hence can be identified. The performance of the proposed algorithm is evaluated and its advantage is demonstrated compared to using an anomaly detection algorithm.     

Classification of electromyography signals using relevance vector machines and fractal dimension

Neural Computing and Applications - Surface electromyography (EMG) signals have been studied extensively in the last years aiming at the automatic classification of hand gestures and movements as...     

Feature selection using correlation fractal dimension: Issues and applications in binary classification problems

Feature selection methods can be classified broadly into filter and wrapper approaches. Filter-based methods filter out features which are irrelevant to the target concept by ranking each feature according to some discrimination measure and then select features with high ranking value. In this paper, a filter-based feature selection method based on correlation fractal dimension (CFD) discrimination measure is proposed. One of the subgoals of this paper is to outline some issues that arise while calculating fractal dimension for higher dimensional ‘empirical’ data sets. It is well known that the calculation of fractal dimension for empirical data sets is meaningful only for an appropriate range of scales. We demonstrate through experimentation on data sets of various sizes that fractal dimension-based algorithms cannot be applied routinely to higher dimensional data sets as the calculation of fractal dimension is inherently sensitive to parameters like range of scales and the size of the data sets. Based on the empirical analysis, we propose a new feature selection technique using CFD that avoids the above issues. We successfully applied the proposed algorithm on a challenging classification problem in bioinformatics, namely, Promoter Recognition.     

Automated steel surface defect detection and classification using a new deep learning-based approach

Neural Computing and Applications - In this study, a new deep learning-based approach has been developed that detects and classifies surface defects that occur in the steel production process. The...     

An effective framework using identification and image reconstruction algorithm for train component defect detection

Applied Intelligence - Under long-term high-speed movement, the precision components of trains are extremely prone to defects, which could potentially endanger the safe operation of the train....     

Void defect detection in ball grid array X-ray images using a new blob filter

Ball grid arrays (BGAs) have been used in the production of electronic devices/assemblies because of their advantages of small size, high I/O port density, etc. However, BGA voids can degrade the performance of the board and cause failure. In this paper, a novel blob filter is proposed to automatically detect BGA voids presented in X-ray images. The proposed blob filter uses the local image gradient magnitude and thus is not influenced by image brightness, void position, or component interference. Different sized average box filters are employed to analyze the image in multi-scale, and as a result, the proposed blob filter is robust to void size. Experimental results show that the proposed method obtains void detection accuracy of up to 93.47% while maintaining a low false ratio. It outperforms another recent algorithm based on edge detection by 40.69% with respect to the average detection accuracy, and by 16.91% with respect to the average false ratio.     

A novel defect detection and identification method in optical inspection

Optical inspection techniques have been widely used in industry as they are non-destructive. Since defect patterns are rooted from the manufacturing processes in semiconductor industry, efficient and effective defect detection and pattern recognition algorithms are in great demand to find out closely related causes. Modifying the manufacturing processes can eliminate defects, and thus to improve the yield. Defect patterns such as rings, semicircles, scratches, and clusters are the most common defects in the semiconductor industry. Conventional methods cannot identify two scale-variant or shift-variant or rotation-variant defect patterns, which in fact belong to the same failure causes. To address these problems, a new approach is proposed in this paper to detect these defect patterns in noisy images. First, a novel scheme is developed to simulate datasets of these 4 patterns for classifiers’ training and testing. Second, for real optical images, a series of image processing operations have been applied in the detection stage of our method. In the identification stage, defects are resized and then identified by the trained support vector machine. Adaptive resonance theory network 1 is also implemented for comparisons. Classification results of both simulated data and real noisy raw data show the effectiveness of our method.     

基于分形和肤色模型的自然态人脸检测方法研究

在对当前人脸检测问题研究过程中常用方法及其特点进行论述基础上,分析了利用分形特征实现人脸检测的可行性,提出了基于分形和肤色模型的自然态人脸检测方法.通过大量实验可知,该算法既克服了传统的基于启发式(知识)模型的方法和基于统计模型方法适应变化能力差、检测速度慢的缺点,又克服了单纯的肤色模型算法对肤色相近区域误检率高的缺点,利用人脸图像所特有分形特征,可以实现自然态环境下,多角度、多姿态人脸检测.     

视线追踪系统眼部特征检测及视线方向计算方法研究

基于单视觉主动红外光源系统,提出了一种视线检测方法．在眼部特征检测阶段,采用投影法定位人脸;根据人脸对称性和五官分布的先验知识,确定瞳孔潜在区域;最后进行人眼特征的精确分割．在视线方向建模阶段,首先在头部静止的情况下采用非线性多项式建立从平面视线参数到视线落点的映射模型;然后采用广义回归神经网络对不同头部位置造成的视线偏差进行补偿,使非线性映射函数扩展到任何头部位置．实验结果及在交互式图形界面系统中的应用验证了该方法的有效性．     

Signature analysis and defect detection in layered manufacturing of ceramic sensors and actuators

This paper presents the concept of a process signature for the use of online signature analysis and defect detection in the layered manufacturing (LM) of ceramic sensors and actuators. To achieve the high quality of parts built by the fused deposition of ceramics (FDC), an online process-monitoring system is implemented to detect the processing defects. Using a process signature extracted from the image of a layer captured by the monitoring system, an ideal image is created that is then compared to the original image to detect and identify the defects. Some results of signature analysis and defect detection for single-material and multi-material parts are also presented.Received: 22 July 1999, Accepted: 21 October 2001, Published online: 29 October 2003 Correspondence to: Mohsen A. JafariThis work was supported by the Office of Naval Research under grant # N-0014-96-1-1175. Ref. US Patent # S-5738817, April 14, 1998.     

Bi- and three-dimensional urban change detection using sentinel-1 SAR temporal series

GeoInformatica - Urban areas are subject to multiple and very different changes, in a two- and three-dimensional sense, mostly as a consequence of human activities, such as urbanization, but also...     

EDGES: Efficient data gathering in sensor networks using temporal and spatial correlations

In this paper, we present an approximate data gathering technique, called EDGES, for sensor networks that utilizes temporal and spatial correlations. The goal of EDGES is to efficiently obtain the sensor reading within a certain error bound. To do this, EDGES utilizes the multiple model Kalman filter, which is for the non-linear data distribution, as an approximation approach. The use of the Kalman filter allows EDGES to predict the future value using a single previous sensor reading in contrast to the other statistical models such as the linear regression and multivariate Gaussian. In order to extend the lifetime of networks, EDGES utilizes the spatial correlation. In EDGES, we group spatially close sensors as a cluster. Since a cluster header in a network acts as a sensor and router, a cluster header wastes its energy severely to send its own reading and/or data coming from its children. Thus, we devise a redistribution method which distributes the energy consumption of a cluster header using the spatial correlation. In some previous works, the fixed routing topology is used or the roles of nodes are decided at the base station and this information propagates through the whole network. But, in EDGES, the change of a cluster is notified to a small portion of the network. Our experimental results over randomly generated sensor networks with synthetic and real data sets demonstrate the efficiency of EDGES.     

Automated reasoning in differential geometry and mechanics using the characteristic set method

This is the first paper of a series of three papers under the same title. It presents an improved version of Ritt-Wu's decomposition algorithm which is the basis of our methods of mechanical theorem proving and mechanical formula derivation in differential geometry and elementary mechanics. We improve the original algorithm in two aspects. First, by using the weak ascending chain and W-perm, the sizes of the differential polynomials occurring in the decomposition can be reduced. Second, by using a special reduction procedure, the number of branches in the decomposition can be controlled effectively. The improved version significantly enhances the efficiency of the original algorithm.The work reported here was supported in part by NSF Grants CCR-8702108 and CCR-9117870.     

基于HJ-1B卫星的作物秸秆提取及其焚烧火点判定模式

作物秸秆焚烧产生的气体和颗粒物严重污染大气环境,威胁人类健康,给交通带安全带来隐患,利用遥感技术优势监管秸秆焚烧火点具有重要的现实意义.文中基于HJ-1B卫星CCD多光谱遥感数据和IRS热红外遥感数据,以中国江苏中东部为研究区,开展作物秸秆提取及其焚烧火点判定的一体化研究.根据秸秆的光谱特征研究建立了秸秆乘积指数(SMI),结合其纹理信息可从HJ-1BCCD遥感图像上快速有效的提取出秸秆分布,继之结合修正后的火点探测算法可对HJ-1BIRS遥感数据进行火点提取.在秸秆分布和火点探测结果矢量化的基础上,通过GIS技术进行火点叠置分析,可有效地判定作物秸秆火点分布,同时结合实地调研及与MODIS火点产品比对分析验证评价了本研究方法的可行性和有效性.     

Illumination and scattered light detection using a light source consisting of sub-micrometer defect arrays formed on a extremely flat light waveguide core

We have previously argued that an optical sensor combined total analysis system (TAS) is one of the indispensable functional components needed to realize a “ubiquitous human healthcare” system. To achieve this goal, we have proposed a fundamental structure for illuminating a minute cell or particle running along a microfluidic channel using a flat waveguide construction. It is desirable that the TAS light source should be arranged as close to the specimen flow as possible in order to acquire the necessary optical properties; hence, artificial defects formed on the surface of a flat light waveguide are considered to be a promising candidate for realizing the arbitrary-shaped light source for a highly functional optical TAS structure. Based on this idea, we fabricated a structure, constructing a flat and square light source consisting of rectangular solids, sub-micrometer in size, with a 1-μm thick and a 12-μm wide light waveguide core. We successfully trial-manufactured an optical TAS chip with a fluidic channel containing a 14 × 10-μm cross section, and an extremely flat light waveguide core. We repeatedly confirmed that the defect array could function as an approximately square light source when a 650-nm wavelength laser power was carefully introduced. Furthermore, we developed a hybrid numerical calculation method base on the finite-difference, time-domain method together with the beam propagation method. Utilizing this hybrid method, we evaluated the optical response when a particle runs across the light source while changing the aperture length of a shading mask to obtain signals with both higher intensity and shorter full width at half maximum. The numerical results were compared with experimental results obtained using an image acquisition system, and demonstrated good qualitative accord.     

Identification of factors that influence defect injection and detection in development of software intensive products

The objective of this study is the identification of factors that influence defect injection and defect detection. The study is part of a broader research project with the goal to lower the number of residual defects in software intensive products, by using the influencing factors to decrease injection of defects and to increase detection of defects. As a first step, we performed an extensive literature search to find influencing factors and processed the factors to achieve consistently formulated sets of factors without duplications. As a second step, we used a cluster analysis to reduce the number influencing factors to manageable-sized sets for practical application. As a last step, final groupings of factors were obtained by expert interpretation of the cluster analysis results. These steps were separately performed for defect injection and detection influencing factors, resulting in sets of, respectively, 16 and 17 factors. Finally, the resulting factor groupings were evaluated.The findings (1) are the basis for further research focusing on a framework for lowering residual defects, (2) already provide information to enable practitioners to devise strategies for lowering residual defects, and (3) may create awareness in organizations to reconsider policies regarding development and Verification & Validation.     

Using perceptual relation of regularity and anisotropy in the texture with independent component model for defect detection

This paper addresses the raw textile defect detection problem using independent components approach with insights from human vision system. Human vision system is known to have specialized receptive fields that respond to certain type of input signals. Orientation-selective bar cells and grating cells are examples of receptive fields in the primary visual cortex that are selective to periodic- and aperiodic-patterns, respectively. Regularity and anisotropy are two high-level features of texture perception, and we can say that disruption in regularity and/or orientation field of the texture pattern causes structural defects. In our research, we observed that independent components extracted from texture images give bar or grating cell like results depending on the structure of the texture. For those textures having lower regularity and dominant local anisotropy (orientation or directionality), independent components look similar to bar cells whereas textures with high regularity and lower anisotropy have independent components acting like grating cells. Thus, we will expect different bar or grating cell like independent components to respond to defective and defect-free regions. With this motivation, statistical analysis of the structure of the texture by means of independent components and then extraction of the disturbance in the structure can be a promising approach to understand perception of local disorder of texture in human vision system. In this paper, we will show how to detect regions of structural defects in raw textile data that have certain regularity and local orientation characteristics with the application of independent component analysis (ICA), and we will present results on real textile images with detailed discussions.