Evaluation of the Transfer Learning Models in Wafer Defects Classification

Jizat, Jessnor Arif Mat; Majeed, Anwar P. P. Abdul; Nasir, Ahmad Fakhri Ab.; Taha, Zahari; Yuen, Edmund; Lim, Shi Xuen

doi:10.1007/978-981-33-4597-3_78

Cited by 9 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Transfer learning provides a method to leverage pretrained CNNs on general image datasets and transfer the learned features to new tasks with limited data. As reported in the literature, the aforesaid technique has been successfully employed on different applications [4]- [9]. With regards to defect detection, Tabl et al [10] used a fine-tuned ResNet-50 CNN model to classify manufacturing defects as either normal or defective.…”

Section: Introductionmentioning

confidence: 99%

Surface Defect Detection: A feature-based transfer learning approach

Abdul Majeed,

Abdullah,

Ab. Nasir

et al. 2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Surface defect detection is critical for maintaining product quality in manufacturing. In this work, we apply a feature-based transfer learning approach for surface defect classification on the NEU surface defect database. The database contains defects across 6 categories captured under various conditions. We utilised two pretrained convolutional neural network (CNN) architectures - VGG16 and InceptionV3 - by removing the final classification layer and using the CNN as a fixed feature extractor. The output feature vectors were classified using a logistic regression (LR) model. The data was split into train, validation, and test sets with a 70:15:15 ratio. The VGG16-LR model achieved classification accuracy (CA) of 100%, 98%, and 99% for the train, validation, and test sets respectively. The InceptionV3-LR model attained CA of 100%, 91%, and 92% for train, validation, and test. The results demonstrate the effectiveness of transfer learning with CNN feature extraction for surface defect detection on challenging multi-category industrial datasets. Further work includes tuning hyperparameters and evaluating additional architectures.

show abstract

Section: Introductionmentioning

confidence: 99%

Surface Defect Detection: A feature-based transfer learning approach

Abdul Majeed,

Abdullah,

Ab. Nasir

et al. 2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…It was shown from the study that the InceptionV3-RF pipeline demonstrates a test classification accuracy of 91%, in demarcating the normal and OSCC classes, suggesting that the proposed architecture has an attractive proposition. In this chapter, a feature-based transfer learning approach [7][8][9] by considering the VGG16 pretrained CNN model with its fully connected layers replaced by the SVM, kNN and RF classifiers in the classification of OSCC is investigated.…”

Section: Introductionmentioning

confidence: 99%

A VGG16 Feature-Based Transfer Learning Evaluation for the Diagnosis of Oral Squamous Cell Carcinoma (OSCC)

Arzmi¹,

Majeed²,

Musa³

et al. 2023

Deep Learning in Cancer Diagnostics

Self Cite

View full text Add to dashboard Cite

Oral Squamous Cell Carcinoma (OSCC) is the most prevalent type of oral cancer. Early detection of such cancer could increase a patient's survival rate by 83%. This chapter shall explore the use of a feature-based transfer learning model, i.e., VGG16 coupled with different types of conventional machine learning models, viz. Support Vector Machine (SVM), Random Forest as well as k-Nearest Neighbour (kNN) as a means to identify OSCC. A total of 990 evenly distributed normal and OSCC histopathological images are split into the 60:20:20 ratio for training, testing and validation, respectively. A testing accuracy of 93% was recorded via the VGG16-RF pipeline from the study. Consequently, the proposed architecture is suitable to be deployed as artificial intelligence-driven computer-aided diagnostics and, in turn, facilitate clinicians for the identification of OSCC. Keywords Computer-Aided Diagnosis• Transfer Learning • Oral Cancer • OSCC

show abstract