Improving Recognition of Defective Epoxy Images in Integrated Circuit Manufacturing by Data Augmentation
This paper discusses the problem of recognizing defective epoxy drop images for the purpose of performing vision-based die attachment inspection in integrated circuit (IC) manufacturing based on deep neural networks. Two supervised and two unsupervised recognition models are considered. The supervis...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/3/738 |
| _version_ | 1797318253357301760 |
|---|---|
| author | Lamia Alam Nasser Kehtarnavaz |
| author_facet | Lamia Alam Nasser Kehtarnavaz |
| author_sort | Lamia Alam |
| collection | DOAJ |
| description | This paper discusses the problem of recognizing defective epoxy drop images for the purpose of performing vision-based die attachment inspection in integrated circuit (IC) manufacturing based on deep neural networks. Two supervised and two unsupervised recognition models are considered. The supervised models examined are an autoencoder (AE) network together with a multi-layer perceptron network (MLP) and a VGG16 network, while the unsupervised models examined are an autoencoder (AE) network together with k-means clustering and a VGG16 network together with k-means clustering. Since in practice very few defective epoxy drop images are available on an actual IC production line, the emphasis in this paper is placed on the impact of data augmentation on the recognition outcome. The data augmentation is achieved by generating synthesized defective epoxy drop images via our previously developed enhanced loss function CycleGAN generative network. The experimental results indicate that when using data augmentation, the supervised and unsupervised models of VGG16 generate perfect or near perfect accuracies for recognition of defective epoxy drop images for the dataset examined. More specifically, for the supervised models of AE+MLP and VGG16, the recognition accuracy is improved by 47% and 1%, respectively, and for the unsupervised models of AE+Kmeans and VGG+Kmeans, the recognition accuracy is improved by 37% and 15%, respectively, due to the data augmentation. |
| first_indexed | 2024-03-08T03:49:46Z |
| format | Article |
| id | doaj.art-5d57f6ba4e0e4d82a98e7c655e80dff9 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-08T03:49:46Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-5d57f6ba4e0e4d82a98e7c655e80dff92024-02-09T15:21:41ZengMDPI AGSensors1424-82202024-01-0124373810.3390/s24030738Improving Recognition of Defective Epoxy Images in Integrated Circuit Manufacturing by Data AugmentationLamia Alam0Nasser Kehtarnavaz1Department of Electrical and Computer Engineering, University of Texas at Dallas, Richardson, TX 75080, USADepartment of Electrical and Computer Engineering, University of Texas at Dallas, Richardson, TX 75080, USAThis paper discusses the problem of recognizing defective epoxy drop images for the purpose of performing vision-based die attachment inspection in integrated circuit (IC) manufacturing based on deep neural networks. Two supervised and two unsupervised recognition models are considered. The supervised models examined are an autoencoder (AE) network together with a multi-layer perceptron network (MLP) and a VGG16 network, while the unsupervised models examined are an autoencoder (AE) network together with k-means clustering and a VGG16 network together with k-means clustering. Since in practice very few defective epoxy drop images are available on an actual IC production line, the emphasis in this paper is placed on the impact of data augmentation on the recognition outcome. The data augmentation is achieved by generating synthesized defective epoxy drop images via our previously developed enhanced loss function CycleGAN generative network. The experimental results indicate that when using data augmentation, the supervised and unsupervised models of VGG16 generate perfect or near perfect accuracies for recognition of defective epoxy drop images for the dataset examined. More specifically, for the supervised models of AE+MLP and VGG16, the recognition accuracy is improved by 47% and 1%, respectively, and for the unsupervised models of AE+Kmeans and VGG+Kmeans, the recognition accuracy is improved by 37% and 15%, respectively, due to the data augmentation.https://www.mdpi.com/1424-8220/24/3/738vision-based inspection in IC manufacturingepoxy drop images for die attachmentdata augmentation via enhanced CycleGANsupervised and unsupervised recognition of defective epoxy drop imagesimpact of data augmentation on recognition accuracies |
| spellingShingle | Lamia Alam Nasser Kehtarnavaz Improving Recognition of Defective Epoxy Images in Integrated Circuit Manufacturing by Data Augmentation Sensors vision-based inspection in IC manufacturing epoxy drop images for die attachment data augmentation via enhanced CycleGAN supervised and unsupervised recognition of defective epoxy drop images impact of data augmentation on recognition accuracies |
| title | Improving Recognition of Defective Epoxy Images in Integrated Circuit Manufacturing by Data Augmentation |
| title_full | Improving Recognition of Defective Epoxy Images in Integrated Circuit Manufacturing by Data Augmentation |
| title_fullStr | Improving Recognition of Defective Epoxy Images in Integrated Circuit Manufacturing by Data Augmentation |
| title_full_unstemmed | Improving Recognition of Defective Epoxy Images in Integrated Circuit Manufacturing by Data Augmentation |
| title_short | Improving Recognition of Defective Epoxy Images in Integrated Circuit Manufacturing by Data Augmentation |
| title_sort | improving recognition of defective epoxy images in integrated circuit manufacturing by data augmentation |
| topic | vision-based inspection in IC manufacturing epoxy drop images for die attachment data augmentation via enhanced CycleGAN supervised and unsupervised recognition of defective epoxy drop images impact of data augmentation on recognition accuracies |
| url | https://www.mdpi.com/1424-8220/24/3/738 |
| work_keys_str_mv | AT lamiaalam improvingrecognitionofdefectiveepoxyimagesinintegratedcircuitmanufacturingbydataaugmentation AT nasserkehtarnavaz improvingrecognitionofdefectiveepoxyimagesinintegratedcircuitmanufacturingbydataaugmentation |