Application of Neural Networks in Optical Inspection and Classification of Solder Joints in Surface Mount Technology

Acciani, G.; Brunetti, Giuseppe; Fornarelli, G.

doi:10.1109/tii.2006.877265

Cited by 148 publications

(74 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Accian et al [10] presented a well-defined scheme for PCB defect detection with the help of computer vision approach. This work mainly aims on the detection of defective solder joints.…”

Section: Related Workmentioning

confidence: 99%

PCB Defect Detection using Computer Vision based Symbolic Pattern Analysis Technique

Prathiba¹,

Nagendra²,

Hanumantappa³

2017

IJARCSSE

View full text Add to dashboard Cite

Abstract-Recently manufacturing industries have experienced a significant improvement. In manufacturing industries, PCB (Printed Circuit Board) manufacturing is known as the most complex to maintain the quality by producing non-defective printed circuit boards for further process. In order to manufacture the printed circuit boards, various electronic components need to be manufactured which urge for manufacturing accuracy and quality assurance. In order to maintain the quality of these products, various schemes have been introduced which are based on the computer vision and data mining techniques. During PCB image acquisition, original image gets contaminated due to occlusions and orientation or camera quality etc. which degrades the manufacturing quality and leads to the defective product manufacture. To cater this issue, we develop a novel approach for defect detection using computer vision scheme where we apply various pre-processing techniques and classification technique. In this work, a new classifier is developed based on the image background, foreground and defect shadow analysis. This article aims on producing an automated process for PCB defect detection using computer vision application with lower complexities. In order to carry out this work, PCB image is transformed into symbols and various features are extracted from the image by dividing image into sub-regions i.e. background, foreground and shadow of defective region. Finally, a binary classifier is constructed with the help of symbolic dynamics to provide improved classification performance. Experimental study shows improved performance of proposed model when compared with existing state of art algorithms. Keywords-PCB defect; computer vision; symbolic pattern; finite automata; classification I. INTRODUCTIONBare printed circuit boards are the type of electronic components which are used for placing other electronic components for any electronic component manufacturing process [1]. PCB is an important part for producing any electronic component. Now a day, technology has grown rapidly which results in higher production of electronic components and devices. During this mass manufacturing because of various issues some electronic components are produced defective which are not acceptable by consumers or doesn't meet industry manufacturing criteria. These issues increase the cost of manufacturing because a manual inspection is required for better quality assurance. Since electronic components are produced in a massive number where manual inspection is not feasible to implement. To adapt up to this issue, different procedures have been produced as of late for robotized PCB imperfection discovery and characterization. Ercal et al. [2] talked about this issue of PCB imperfection recognition where three classes of PCB assessment methodologies are examined which are given as: (a) reference based strategy (b) non-reference based review system and (c) half and half procedure for PCB deformity investigation. Reference based assessment approaches uses correl...

show abstract

“…Accian et al [10] presented a well-defined scheme for PCB defect detection with the help of computer vision approach. This work mainly aims on the detection of defective solder joints.…”

Section: Related Workmentioning

confidence: 99%

PCB Defect Detection using Computer Vision based Symbolic Pattern Analysis Technique

Prathiba¹,

Nagendra²,

Hanumantappa³

2017

IJARCSSE

View full text Add to dashboard Cite

show abstract

“…In order to reduce the level of redundancy in the hyperspectral data and improve the material separation, decorrelation techniques are applied to obtain a new data representation that has a reduced dimensionality. In this study different decorrelation methods are investigated, namely the PCA-based approach [20], [26], LDA [19], [43], automatic band selection [47], wavelet decomposition [25], and a novel technique based on spectral fuzzyfication that will be detailed in this paper.…”

Section: B Spectral Decorrelationmentioning

confidence: 99%

“…The intraclass variations can be appropriately modeled by the use of pattern recognition techniques since the spectral information is evaluated in a more elaborate fashion [15], [19]. One problem that has to be addressed is the high dimensionality of the hyperspectral data [20]- [22].…”

Section: Introductionmentioning

confidence: 99%

Fuzzy Spectral and Spatial Feature Integration for Classification of Nonferrous Materials in Hyperspectral Data

Picón

Ghita

Whelan

et al. 2009

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

Abstract-Hyperspectral data allows the construction of more elaborate models to sample the properties of the nonferrous materials than the standard RGB color representation. In this paper, the nonferrous waste materials are studied as they cannot be sorted by classical procedures due to their color, weight and shape similarities. The experimental results presented in this paper reveal that factors such as the various levels of oxidization of the waste materials and the slight differences in their chemical composition preclude the use of the spectral features in a simplistic manner for robust material classification. To address these problems, the proposed FUSSER (FUzzy Spectral and Spatial classifiER) algorithm detailed in this paper merges the spectral and spatial features to obtain a combined feature vector that is able to better sample the properties of the nonferrous materials than the single pixel spectral features when applied to the construction of multivariate Gaussian distributions. This approach allows the implementation of statistical region merging techniques in order to increase the performance of the classification process. To achieve an efficient implementation, the dimensionality of the hyperspectral data is reduced by constructing bio-inspired spectral fuzzy sets that minimize the amount of redundant information contained in adjacent hyperspectral bands. The experimental results indicate that the proposed algorithm increased the overall classification rate from 44% using RGB data up to 98% when the spectral-spatial features are used for nonferrous material classification.

show abstract

“…Moreover, the inspected images also have to be precisely matched for a comparison with the reference image [5]. Acciani et al suggested an inspection algorithm that extracts the wavelet and geometric features, and then detects a defect after learning the fault pattern using a neural network and k-nearest neighbors [6]. When extracting the features of a PCB image, this method uses the maximum value of the correlation coefficients between the features of the reference image and the inspected image.…”

Section: Introductionmentioning

confidence: 99%

Feature-Learning-Based Printed Circuit Board Inspection via Speeded-Up Robust Features and Random Forest

Yuk

Park

et al. 2018

Applied Sciences

View full text Add to dashboard Cite

Featured Application: The main contribution of this work is to propose an inspection method using image data generated at the actual manufacturing process. This proposed method can help printed circuit board (PCB) manufacturers more effectively detect defects, such as scratches and improper etching, in an automated optical inspection (AOI). Moreover, the proposed method of this work can be also applied to the field of dermatology, where it has to detect skin diseases, as well as in PCB inspection.Abstract: With the coming of the 4th industrial revolution era, manufacturers produce high-tech products. As the production process is refined, inspection technologies become more important. Specifically, the inspection of a printed circuit board (PCB), which is an indispensable part of electronic products, is an essential step to improve the quality of the process and yield. Image processing techniques are utilized for inspection, but there are limitations because the backgrounds of images are different and the kinds of defects increase. In order to overcome these limitations, methods based on machine learning have been used recently. These methods can inspect without a normal image by learning fault patterns. Therefore, this paper proposes a method can detect various types of defects using machine learning. The proposed method first extracts features through speeded-up robust features (SURF), then learns the fault pattern and calculates probabilities. After that, we generate a weighted kernel density estimation (WKDE) map weighted by the probabilities to consider the density of the features. Because the probability of the WKDE map can detect an area where the defects are concentrated, it improves the performance of the inspection. To verify the proposed method, we apply the method to PCB images and confirm the performance of the method.

show abstract

Application of Neural Networks in Optical Inspection and Classification of Solder Joints in Surface Mount Technology

Cited by 148 publications

References 18 publications

PCB Defect Detection using Computer Vision based Symbolic Pattern Analysis Technique

PCB Defect Detection using Computer Vision based Symbolic Pattern Analysis Technique

Fuzzy Spectral and Spatial Feature Integration for Classification of Nonferrous Materials in Hyperspectral Data

Feature-Learning-Based Printed Circuit Board Inspection via Speeded-Up Robust Features and Random Forest

Contact Info

Product

Resources

About