An experimental printed circuit board drilling system automated by pattern recognition

The two-dimensional image processing necessary for closed-loop control of automated printed circuit board drilling and a mechanical prototype capable of drilling simulated printed-circuit boards are described. A single closed-loop correction of position permits correction of errors introduced by vidicon camera positional nonlinearity, noise, irregular lighting, inaccuracy of transformational constants, and mechanical slippage. These errors are corrected to an acceptable degree and in a short enough time that automatic drilling may present a challenge to manual drilling labor costs.     

An optimal orthonormal system for discriminant analysis

This paper proposes a new discriminant analysis with orthonormal coordinate axes of the feature space. In general, the number of coordinate axes of the feature space in the traditional discriminant analysis depends on the number of pattern classes. Therefore, the discriminatory capability of the feature space is limited considerably. The new discriminant analysis solves this problem completely. In addition, it is more powerful than the traditional one in so far as the discriminatory power and the mean error probability for coordinate axes are concerned. This is also shown by a numerical example.     

An automatic surface inspection system for flat rolled steel

The paper describes a feasibility study of on-line classification of visible defects in flat rolled steel, as the steel emerges from the rolling mill. A visual signal developed by a television camera is processed by a software simulation of the proposed hardware system which stores information from the scans and alerts a small computer when a possible flaw has been detected. A pattern recognition algorithm, executable by the computer, makes the final detection and classification decision before the next coil is rolled. A detailed simulation of the hardware using photographs of steel defects is presented.     

Automatic optical inspection of plated through-holes for ultrahigh density printed wiring boards

An automatic optical through-hole inspection system for ultrahigh density printed wiring boards (PWBs) using leakage light detection has been developed. To detect the dim leakage light emitted from the through-hole defect, we enhanced the sensitivity of the light detector 150 times using a microchannel plate tube. However, the tube caused two problems: stray light sensing and image distortion. To solve these problems, we optically isolated the sensing optics and developed a distortion correction method. We have developed a prototype system that can detect a defect as small as 100 m.     

A cost-effective and automatic surface defect inspection system for hot-rolled flat steel

Defective steel brings economic and commercial reputation losses to the hot-strip manufacturers, and one of the main difficulties in using machine-vision-based technique for steel surface inspection is time taken to process the massive images suffering from uneven illumination. This paper develops a modular and cost-effective AOI system for hot-rolled flat steel in real time. Firstly, a detailed system topology is constructed according to the design goals covering the vast majority of steel mills, lighting setup and typical defect patterns are presented as well. Secondly, the image enhancement method is designed to overcome the uneven-lighting, over- or under-exposure. Thirdly, the defect detection algorithm is developed based on variance, entropy and average gradient derived from non-overlapping 32×32 pixel blocks of steel surface images. Fourthly, the proposed algorithms are implemented on FPGA in parallel to improve the inspection speed. Finally, 18,071 contiguous images (4096×1024 pixel) acquired from 7 defective steel rolls have been inspected by the realized AOI system to evaluate the performance. The experimental results show that the proposed method is speedy and effective enough for real applications in the hot-rolled steel manufacturing, with 92.11% average accuracy while 5.54% false-negative rate.     

Workpiece recognition and inspection by a model-based scene analysis system

A scene analysis system for the recognition and inspection of overlapping workpieces in visually noisy scenes is described. It consists of a preprocessing algorithm based on an edge-following operator and a model-based analysis algorithm. In the preprocessing stage, which is not described in detail, features such as corners, straight lines, circles and circular arcs are extracted and described by a few parameters. In the analysis stage, the pattern features extracted by the preprocessing algorithm are used to synthesize, in model-guided fashion, a prototype of the workpiece, which is continuously checked against the model. A similarity measure indicates the match between model and scene. Besides topographical features, the analysis makes use of grey levels, textural measures and values representing colors.Results obtained with different, partly occluded workpieces are given.     

LED cosmetic flaw vision inspection system

The paper describes a vision inspection system that is developed to detect diffused LED defects, namelyscratches, bubbles, contamination, blister/blemish, fuzzy dome andoff centre defects in less than 200 ms using a 200 MHz Pentium PC, a Matrox Genesis frame grabber and a Pulnix high speed camera. Various image-processing techniques are utilised for the inspection task. A machine vision approach that comprises pre-processing, image segmentation, clean up and feature extraction operations is implemented to perform the automated cosmetic flaw inspection. Based on 200 LED samples, the system was found to be 100% accurate in detecting LED dome defects on LEDs of different colour and intensity. The system can also classify defects into different categories and was found to be 90% accurate.     

Recognition and inspection of two-dimensional industrial parts using subpolygons

A model-based scene analysis for the recognition of imperfect and possibly occluded two-dimensional (2D) industrial parts is described. The means of recognition leads reliably to the correct association of the sides making up the unknown object to those of the model. Both the scene polygon and the model are divided into pairs of complementary subpolygons. This is done by a cutting line drawn parallel and close to a selected side. The subpolygons from the object are compared to all possible subpolygons from the model. Invariant moments are used in the analysis. A matching process using clusters of mutually consistent features is used to hypothesize the identity of the object. Examples are given to illustrate the method.     

Fuzzy reasoning based automatic inspection of radiographic welds: weld recognition

A fuzzy reasoning based expert system is developed for the recognition of welds in radiographic images. First, each object in a radiographic image is identified and described with a three-feature vector. Of interest are to distinguish welds from non-weld objects in order to extract welds for further processing, such as, flaws detection. To this end, a fuzzy reasoning method is proposed. The fuzzy rules are extracted from feature data one feature at a time based on a modified fuzzy c-means algorithm. The number of fuzzy terms with overlapping between adjacent terms and the shape of terms are optimized based on the mean squared error criterion. The total number of fuzzy rules is the product of the number of fuzzy terms for each feature. The performance of this optimal set of fuzzy rules is tested with unseen data in terms of accurate rate, false positive rate, and false negative rate. For comparison, selected sets of rules are extracted by varying the number of fuzzy terms for each feature and subsequently tested. The performance of the fuzzy expert system is also found to be better than that of multi-layer perceptron neural networks, if appropriately designed.     

一种改进的基于Fisher准则的线性特征提取方法

针对现有的基于Fisher准则的线性特征提取方法存在的不足,提出了一种新的改进的Fisher特征提取方法.通过重新定义类内散度矩阵与类间散度矩阵,削弱了边缘样本与边缘类别的影响,提高了准则模型的准确性,进而提高了判别矢量的特征提取能力.同时,也给出了一种实用的求解具有统计不相关的最优判别矢量集的方法,实验结果表明,算法得到的最优判别矢量具有更好的特征提取能力.     

Image registration for automated inspection of printed circuit patterns using CAD reference data

An image registration approach for inspection of printed circuit patterns which has been validated on a prototype system is described. Theoffline procedure forms, selects, prioritizes, and sorts registration features from CAD-generated reference data. A feature is selected if it satisfies clearance rules that account for the maximum expecteddiscongruence between captured and reference images. The sorting scheme considers the detection complexity of a feature and its distance away from the center of the expected image, since outer features represent potential global distortions better. Theruntime registration procedure detects features and finds the parameters that transform pixels into reference data coordinates and vice versa. We represent robust feature-measurement techniques that offer accurate subpixel localization and verify feature authenticity. We describe an edge-detection technique based on a novel way of authenticating zero-crossings and a method that disqualifies edges detected on defects of the part under inspection.     

Recent advances in the automatic inspection of integrated circuits for pattern defects

Automatic inspection has become an essential part of manufacturing technology for integrated circuit (IC) chips, but three trends in the geometries of ICs and the chips that they comprise have serious implications for inspection, making further advances in technology challenging. The individual devices (e.g., transistors) are becoming smaller, with the smallest features on some advanced products already crossing the optical resolution threshold; the chip areas are becoming larger; and the chips consist of more layers and undergo more processing steps. Not only are the smallest defects more difficult to detect due to the optical resolution limit, they are also much rarer because the tolerable defect density decreases as the chip area increases. This paper addresses automated IC inspection, surveying recent advances and future challenges. An overview of all inspection on IC chips during the manufacturing process is followed by a detailed discussion of pattern defect inspection (PDI) and its unique requirements, such as detection probability, false alarm rate, throughput, and minimum defect size. The core material of the paper consists of a discussion of approaches and systems for PDI, emphasizing recent developments, but reviewing older work to set the proper context. Both work reported in the literature and commercial systems are considered.     

Automatic visual inspection: An approach with multi-instance learning

One of the industrial applications of computer vision is automatic visual inspection. In the last decade, standard supervised learning methods have been used to detect defects in different kind of products. These methods are trained with a set of images where every image has to be manually segmented and labeled by experts in the application domain. These manual segmentations require a large amount of high quality delineations (on pixels), which can be time consuming and often a difficult task. Multi-instance learning (MIL), in contrast to standard supervised classifiers, avoids this task and can, therefore, be trained with weakly labeled images. In this paper, we propose an approach for the automatic visual inspection that uses MIL for defect detection. The approach has been tested with data from three artificial benchmark datasets and three real-world industrial scenarios: inspection of artificial teeth, weld defect detection and fishbone detection. Results show that the proposed approach can be used with weakly labeled images for defect detection on automatic visual inspection systems. This approach is able to increase the area under the receiver-operating characteristic curve (AUC) up to 6.3% compared with the naïve MIL approach of propagating the bag labels.     

Extended Hough transform for linear feature detection

Improving the accuracy of line segment detection reduces the complexity of subsequent high-level processing common in cartographic feature detection. We developed a new extension to the Hough transform and reported on its application to building extraction. We expanded the Hough space by a third parameter, the horizontal or vertical coordinate of the image space, to provide incremental information as to the length of the lineal feature being sought. Using this extended HT transform allowed us to more accurately detect the true length of a line segment. In addition, we used a Bayesian probabilistic approach to process our extended Hough space that further increased the accuracy of our extended Hough transform.     

An Integrated Face Rec gniti n System Based n Multiscale L cal Discriminatory Features

Despite some successes, the process of Automatic Facial Recognition (AFR) remains a significant challenge when unconstrained imaging conditions are involved. The authors believe that this occurs because an effective feature extraction method of facial images has not been found so far. In this paper a new approach to extract powerful local discriminatory features is described. First, the wavelet transform is used for extraction of multi-resolution coarse features, and then the emphasis is placed on the extraction of Multiscale fine Local Discriminatory Features (MLDFs). Instead of using traditional wavelet features, the authors examine the multiscale local statistical characteristics to derive stronger discriminatory features based on some important wavelet subbands. To efficiently utilise potentials of the extracted multi-MLDFs, an integrated recognition system is developed where the multi-classifiers first conduct the corresponding coarse classification, then a decision making scheme is used to associate different priorities with each of the classifiers to make the final recognition. Experiments have shown that this scheme provides superior performance to popular methods, such as Principal Components Analysis (PCA or Eigenface), wavelet features, neural networks, etc.     

A multilevel information fusion approach for visual quality inspection

For visual quality inspection systems to be applicable in industrial settings, it is mandatory that they are highly flexible, robust and accurate. In order to improve these characteristics a multilevel information fusion approach is presented. A first fusion step at the feature-level enables the system to learn from an undefined number of potential defects which might be segmented from the images. This allows for the quality control operators to label the data at the image-level and the sub-image-level, and use this information during the learning process. Additionally, the operators are allowed to provide a confidence measure for their labelling. The additional information obtained from the increased flexibility of the operator inputs allows to build more accurate classifiers. A second fusion step at the decision-level combines the classifications of different classifiers, making the system more accurate and more robust with respect to the classification method chosen. The experimental results, using various artificial and real-world visual quality inspection data sets, show that each of these fusion approaches can significantly improve the classification accuracy. If both information fusion approaches are combined the accuracy increases even further, significantly outperforming each of the fusion approaches on their own.     

一种变形Fisher判别准则函数及最优判别向量集

基于Fisher判别准则函数式,提出了一种无约束的最优判别矢量集,并给出了求解算法,另外,当训练样本矢量数小于样本矢量维数（即小样本问题）,类内散布矩阵奇异,此时求F-S最优判别向量集及文中提出的无约束的最优判别矢量集都已不可行,对此提出了一种变形的Fisher判别准则函数,并给出了求解最优判别向量集算法。用ORL标准人脸库进行实验,实验结果表明,提出的两种最优判别向量集都有良好的分类能力。