Deformable Convolutional Networks for Efficient Mixed-Type Wafer Defect Pattern Recognition

Wang, Junliang; Xu, Chuqiao; Yang, Zhengliang; Zhang, Jie; Li, Xiaoou

doi:10.1109/tsm.2020.3020985

Cited by 112 publications

(42 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model was evaluated on the synthetic dataset of 16 classes; one non-pattern, four single and eleven mixed types with different levels of imbalance, and train/test configuration. Wang et al [59] proposed a deformable convolutional network for mixed-type defect patterns by selectively sampling and extracting high-quality features from mixed wafer defects. They also introduced a public domain dataset ''MixedWM38'', having 38 types of wafer maps.…”

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

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

“…According to previous works [18,23,44], existing defect detection methods have mainly been based on deep learning (supervised learning) using specifically designed or pre-trained CNN architecture, such as AlexNet [45], Resnet-50 [46], or VGG-16 [18]. For this reason, evaluations have been performed using these methods on specific data, such as visual content generated from laser sensor data [2].…”

Section: Defect Detection By Rcnn With Vgg-16 Networkmentioning

confidence: 99%

Analysis of the Possibilities of Tire-Defect Inspection Based on Unsupervised Learning and Deep Learning

Kuric

Klarák

Sága

et al. 2021

Sensors

View full text Add to dashboard Cite

At present, inspection systems process visual data captured by cameras, with deep learning approaches applied to detect defects. Defect detection results usually have an accuracy higher than 94%. Real-life applications, however, are not very common. In this paper, we describe the development of a tire inspection system for the tire industry. We provide methods for processing tire sidewall data obtained from a camera and a laser sensor. The captured data comprise visual and geometric data characterizing the tire surface, providing a real representation of the captured tire sidewall. We use an unfolding process, that is, a polar transform, to further process the camera-obtained data. The principles and automation of the designed polar transform, based on polynomial regression (i.e., supervised learning), are presented. Based on the data from the laser sensor, the detection of abnormalities is performed using an unsupervised clustering method, followed by the classification of defects using the VGG-16 neural network. The inspection system aims to detect trained and untrained abnormalities, namely defects, as opposed to using only supervised learning methods.

show abstract

“…Figure 1: Hybrid wafer map defects detected by Mask R-CNN with the traditional greedy NMS as the postprocessing method. Each map includes two objects, one for "Loc" and one for "Scratch" (these two categories belong to six basic wafer maps, as defined in [28]). When the image passes through the detector network, a category score is obtained, and postprocessing is performed based on the score.…”

Section: Implementation Detailsmentioning

confidence: 99%

“…Datasets. Experiments on the 6 category wafer map datasets [28] used 2 k training images and 382 validation sets and 429 test images. There are 3.1 k wafer bin maps (WBMs), including 6.2 k objects.…”

Section: Implementation Detailsmentioning

confidence: 99%

A Fast Postprocessing Algorithm for the Overlapping Problem in Wafer Map Detection

Wang

2021

Journal of Sensors

View full text Add to dashboard Cite

Mixed defects have become increasingly popular in defect detection and one of the hottest research areas in wafer maps. Postprocessing methods used to solve the overlapping problem in mass mixed defects have a poor detection speed, which is insufficient for rapid defect detection. In this paper, the fast-soft nonmaximum suppression (fs-NMS) method is proposed to solve this problem. The score of the detection box is updated by optimizing the penalty distribution function. Further, this paper analyzes the performance of the fs-NMS method in wafer defect detection. As a penalty, the logistic function is used, and experiments are conducted using single-stage and two-stage detectors. The final results show that, compared to the soft-NMS, the efficiency for the single-stage and two-stage detectors is increased on average by 9.63% and 21.72%, respectively.

show abstract

Deformable Convolutional Networks for Efficient Mixed-Type Wafer Defect Pattern Recognition

Cited by 112 publications

References 31 publications

A Systematic Review of Deep Learning for Silicon Wafer Defect Recognition

A Systematic Review of Deep Learning for Silicon Wafer Defect Recognition

Analysis of the Possibilities of Tire-Defect Inspection Based on Unsupervised Learning and Deep Learning

A Fast Postprocessing Algorithm for the Overlapping Problem in Wafer Map Detection

Contact Info

Product

Resources

About