Convolutional Neural Network for Semiconductor Wafer Defect Detection

Devika, B; George, Neetha

doi:10.1109/icccnt45670.2019.8944584

Cited by 24 publications

(9 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The main drawback of this approach is that to detect a mixed pattern defect, the output of each individual classifier has to be obtained [400]. A similar approach was proposed by Cheon et al in [134].…”

Section: Deep Learningmentioning

confidence: 99%

A Review and Analysis of Automatic Optical Inspection and Quality Monitoring Methods in Electronics Industry

2020

View full text Add to dashboard Cite

Electronics industry is one of the fastest evolving, innovative, and most competitive industries. In order to meet the high consumption demands on electronics components, quality standards of the products must be well-maintained. Automatic optical inspection (AOI) is one of the non-destructive techniques used in quality inspection of various products. This technique is considered robust and can replace human inspectors who are subjected to dull and fatigue in performing inspection tasks. A fully automated optical inspection system consists of hardware and software setups. Hardware setup include image sensor and illumination settings and is responsible to acquire the digital image, while the software part implements an inspection algorithm to extract the features of the acquired images and classify them into defected and non-defected based on the user requirements. A sorting mechanism can be used to separate the defective products from the good ones. This article provides a comprehensive review of the various AOI systems used in electronics, microelectronics , and opto-electronics industries. In this review the defects of the commonly inspected electronic components, such as semiconductor wafers, flat panel displays, printed circuit boards and light emitting diodes, are first explained. Hardware setups used in acquiring images are then discussed in terms of the camera and lighting source selection and configuration. The inspection algorithms used for detecting the defects in the electronic components are discussed in terms of the preprocessing, feature extraction and classification tools used for this purpose. Recent articles that used deep learning algorithms are also reviewed. The article concludes by highlighting the current trends and possible future research directions.

show abstract

Section: Deep Learningmentioning

confidence: 99%

A Review and Analysis of Automatic Optical Inspection and Quality Monitoring Methods in Electronics Industry

2020

View full text Add to dashboard Cite

show abstract

“…The ensemble of models is easier to adopt for new merging defects and addresses class imbalance, but it means putting more than the required resources for the task. Taking this into account, Devika and George [34] optimally trained a single CNN on four basic types of single defect patterns that could detect combinations of the basic types. For each defect type of the real dataset, more images were generated by drawing patterns in paint that is a very naïve approach for such a sensitive task.…”

Section: B: Cnn For Multi-label Defect Classificationmentioning

confidence: 99%

A Systematic Review of Deep Learning for Silicon Wafer Defect Recognition

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In literature [20], they further proposed a deep convolutional encoding-decoding architecture to segment defect regions, which laid a foundation for feature learning. DEVIKA et al [21] trained an 8-layer CNN model to identify four types of defect patterns and their combinations. SHEN et al [22] introduced transfer learning and applied the typical DenseNet-169 (T-DenseNet) network, which has been pretrained to detect the WBM.…”

Section: Supervised Learningmentioning

confidence: 99%

Wafer bin map inspection based on DenseNet

Qiao

Wang

et al. 2021

J. Cent. South Univ.

View full text Add to dashboard Cite

Wafer bin map (WBM) inspection is a critical approach for evaluating the semiconductor manufacturing process. An excellent inspection algorithm can improve the production efficiency and yield. This paper proposes a WBM defect pattern inspection strategy based on the DenseNet deep learning model, the structure and training loss function are improved according to the characteristics of the WBM. In addition, a constrained mean filtering algorithm is proposed to filter the noise grains. In model prediction, an entropy-based Monte Carlo dropout algorithm is employed to quantify the uncertainty of the model decision. The experimental results show that the recognition ability of the improved DenseNet is better than that of traditional algorithms in terms of typical WBM defect patterns. Analyzing the model uncertainty can not only effectively reduce the miss or false detection rate but also help to identify new patterns.

show abstract

Convolutional Neural Network for Semiconductor Wafer Defect Detection

Cited by 24 publications

References 17 publications

A Review and Analysis of Automatic Optical Inspection and Quality Monitoring Methods in Electronics Industry

A Review and Analysis of Automatic Optical Inspection and Quality Monitoring Methods in Electronics Industry

A Systematic Review of Deep Learning for Silicon Wafer Defect Recognition

Wafer bin map inspection based on DenseNet

Contact Info

Product

Resources

About