Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{178515,
        author = {P.ANIL KUMAR and M.SAI KRISHNA and N.MADHU and K.SHIVA KUMAR REDDY},
        title = {SILICON WAFER DEFECT DETECTION USING MACHINE LEARNING TECHNIQUES},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {3868-3873},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=178515},
        abstract = {The detection of defects in silicon wafers is crucial for maintaining the performance and reliability of semiconductor devices. Traditional inspection methods, which often rely on manual or semi-automated techniques, are not only time-consuming but also susceptible to human error. Machine learning provides a compelling solution to these issues by enabling quicker and more precise identification of defects. This project explores different machine learning [4][5][6] strategies spanning supervised, unsupervised, and deep learning models for detecting irregularities in high-resolution images of silicon wafers. Techniques such as feature extraction and classification are assessed with respect to their effectiveness, sensitivity, and computational performance. Special attention is given to deep learning architectures like Convolutional Neural Networks (CNNs [1][5][6]), which can autonomously recognize complex defect structures.
Integrating machine learning [4][5][6] into wafer inspection processes can drastically reduce inspection time and improve detection rates, leading to higher production yields and better-quality control. The study also highlights practical challenges, such as data scarcity, defect variability, and the need for real-time processing, and proposes future directions like hybrid models and transfer learning [1][15] to enhance system robustness.},
        keywords = {Silicon Wafer, Defect Detection, Machine Learning, Deep Learning, CNN [1][5][6], VGG16[15], Feature Extraction, Tkinter[7] GUI, Semiconductor, Quality Control.},
        month = {May},
        }