Automatic Surface Defect Detection Research Articles

Study on defects detection technique of precise optical element

Aiming at the problems of low efficiency of traditional detection methods for surface defects of precision optical element and inconvenient detection for optical elements of different calibers, a adjustable optical element defects detecting device for large laser devices is designed. The key technical points of system composition, detection environment, illumination design and image stitching are expounded. According to the characteristics of surface defects of optical element, such as the difference of contour, gray scale, contrast and ambiguity, a classification method based on FCM is proposed. The experimental results show that the system can realize the automatic detection of surface defects, also it can effectively distinguishes micron-scale defects and has good defect recognition performance. The overall average recognition rate reached to 93.3%.

Surface Defect Inspection for Vehicle Heat Exchangers Based on LBP and SVM

To tackle the problems appeared in traditional surface defect inspection for vehicle heat exchangers which is mainly depended on manual execution, machine vision has been introduced due to its unparalleled characteristics of on-line, fast, high precision and non-contact. In this paper, an automatic surface defect detection algorithm employing machine vision technology has been presented. Treating the surface defect detection as a texture discrimination problem, the proposed method first uses an LBP (Local Binary Pattern) descriptor to represent the image of the heat exchanger, which has efficiently alleviated the effect of uneven illumination. Then the whole texture image has been partitioned into several non-overlapped 32×32 blocks and each block is subject to classification by an SVM (Support Vector Machine) to judge if it is a defect area. The experiments have been performed and the results have demonstrated the effectiveness and the efficiency of the proposed method.

Automatic detection of surface defects

In the automobile manufacturing industry, the detection of surface defects is a crucial process for quality control. This study simulates the process by which engineers find defects on an outer surface using a parallel light reflection map and the proposed integral reflection map (IRM)detection algorithm. This method is based on the law of reflection and reversibility of light, and detects surface defects by comparing the different behaviors of the reference model and manufactured model under reflection. Furthermore, by doing integral in valid viewpoint areas, this method avoids the instability of detection results under different viewpoint positions. Moreover, to solve the problem that the global alignment of reference and manufacture models cannot detect certain scales of surface defects, this paper proposes a local alignment method. The implementation results show that our method is highly automatic, viewpoint independent, and can detect multi-scale surface defects.

Automatic surface defect detection for mobile phone screen glass based on machine vision

Defect detection using machine vision technology plays an important role in the manufacturing process of mobile phone screen glass (MPSG). This study proposes an improved detection algorithm for MPSG defect recognition and segmentation. Considering the problem of MPSG image misalignment caused by vibrations in the mobile stages, a contour-based registration (CR) method is used to generate the template image used to align the MPSG images. Based on this registration result, the combination of subtraction and projection (CSP) is used to identify defects on the MPSG image, which can eliminate the influence of fluctuation in ambient illumination. To segment the defects with a fuzzy grey boundary from a noisy MPSG image, an improved fuzzy c-means cluster (IFCM) algorithm is developed in this study. A defect detection system is developed, and the proposed algorithms are validated using a number of experimental tests on MPSG images. The testing results demonstrate that the approach proposed in this study can effectively detect various defects on MPSG and that it has better performance than other methods.

Vision-based automatic detection of steel surface defects in the cold rolling process: considering the influence of industrial liquids and surface textures

In the cold rolling process, automatic surface defect detection could be considered as an important technique to monitor product quality, and so far, substantial kinds of surface defects have been already successfully inspected. However, the interference of industrial liquids and produced surface textures has been rarely studied yet. To address this problem, the vision-based automatic detection method is proposed in this paper containing three main parts: (i) region extraction, (ii) defect detection, and (iii) industrial liquid quantification. Four sets of experiments are designed to verify the feasibility, accuracy, and stability of the proposed method. The results indicate that the proposed method can detect most cracks and scratches with the accuracy of more than 91 %. Also, the proposed method could accurately quantify the industrial liquids including their numbers (with the average accuracy of more than 90 %) and their sizes (with the accuracy of more than 91 %); it is therefore expected to be promising because it could be utilized to track the online running status of the rolling system and provide rolling system maintenance suggestions.

Research on Identification of Dust Particles on COF

Chip On Film(COF) is the key component of electronic products, and is different from Printed Circuit Board(PCB). The properties of high flexibility, thin thickness, lightweight and high wiring density make it difficult to inspect COF, especially dust particles interference. Dust particles are similar to defects, and it is hard to identify dust particles from defects, so dust particles interference of quality test is the difficulty of automatic surface defect detection. In this paper, a new method to identify dust particles is discussed from abnormal area called junction points detection and machine learning method Support Vector Machine(SVM) according to the characteristics of dust particles. As a result, a 94.8% correct rate of dust particles images identification has been achieved with the method.

Automatic Detection of Surface Defects on Citrus Fruit based on Computer Vision Techniques

Taking inspiration from the fact that a human can distinguish only a limited number of colors, reducing the number of colors is an interesting task to be incorporated in image retrieval systems that is based on using only the most discriminative colors, which most of the time yields better results. Accordingly, the main goal of this paper is to study the influence on performance of reducing the colors number contained in images. Accomplishing this task poses an extra overhead on the system, which requires more computation time, but, on the other hand, can accelerate the comparison process. Due to their popularity and success, we specifically concentrate this study on histogram indexing methods, using both Euclidean distance and histogram intersection to assess consequently the distance and the similarity between images. Some simple, pertinent ideas related to the way we compare a pair of images using Euclidean Distance are given in the end of the paper, supported by preliminary obtained results.

Optical technique for the automatic detection and measurement of surface defects on thin metallic wires

In industrial applications of thin metallic wires it is important to characterize the surface defects of the wires. We present an optical technique for the automatic detection of surface defects on thin metallic wires (diameters, 50-2000 microm) that can be used in on-line systems for surface quality control. This technique is based on the intensity variations on the scattered cone generated when the wire is illuminated with a beam at oblique incidence. Our results are compared with those obtained by atomic-force microscopy and scanning-electron microscopy.

Automatic detection of surface defects on fruit by using a vision system

The OECD standards for the fresh market make it necessary to estimate the quality of fruit by grading by size, colour and surface defects. While size and colour grading are now automated, sorting of damaged fruit is still done manually. A system for automatic detection of surface defects on Golden Delicious apples has been developed and tested on line, on a conveyor system used for automatic colour grading. While the fruit is rolling, a solid-state camera takes four pictures, and so is able to view most of the surface. A hardware system has been developed to reduce the amount of data to be processed. This is based on a model which assumes the apple to be spherical with variable diameter, according to the fruit size. The system can analyse more than five fruit per second per grading line. The tests on line showed that 69% of the fruit were correctly graded, but 26% were classified immediately above or below the right grade. The rough model employed allowed only marketable fruit (grades 1 and 2) to be distinguished from the unmarketable fruit (grades 3 and waste), and the grade 3 to be distinguished from the waste. Consequently, this system can be used only during the picking period, in order to sort the fruit unmarketable as fresh fruit. However, it can also be used for the pre-size grading operations before storage, since it gives the weight with a standard deviation of ± 5 g ( r = 0·985).

An automatic surface defect detection system for hot ingot casting slabs using an infrared scanning camera and image processors.

An automatic surface defect detection system for hot ingot-casting-slabs has been developed to support hot-direct-rolling operations. Among several possibilities considered, the thermal image of a hot slab provided by an infrared scanning camera was evaluated as being the best. Having shown that the majority of surface defects could be recognized visually on the thermal image, an image processing system to replace visual recognition was developed. The image processing system as designed consists o f a signal processing unit and a mini-computer. Several different data processing stages are involved in the extraction of defect signals. Many parameters in the processing system were given a range of freedom and the final values adjusted to provide optimum detectability for actual defects. It was concluded that this detection system would enable on-line defect detection if some minor improvements were made. Two topics now under consideration are the coupling o f the detection system to an automated spot scarfer and the application of the system to defect detection in continuous-castingslabs.

Electro-magnetic Instrument for the Automatic Detection of Surface Defects on Steel Bars

Automation of non-destructive inspection is particularly regarded important, because any defects of steel products must be checked thoroughly and quickly as well. At this standpoint, a partial field excitation method has been developed. Firstly changing of magnetic phenomenon checked for surface defects on steel bars by detector using partial field excitation out of electro-magnetic testing methods, that have a good many suitableness for automation of nondestructive inspection. And an equipment which automatically tests it developed through electric circuit. Principle of the proble and electrical equipment, and the results tested for the surface defects of steel bars are repotred here. We confirm that we can detect the surface defects whose depth is over 0.1mm and also can check whole steel bars with much faster speed by this equipment.