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{173907,
        author = {Adigarla Jayanthi and Palacharla Venkatrao and Pilla Saikumar and Kundeti Durga Sudheer and Bonuboyina Sambasiva rao},
        title = {Predictive Analysis for Wafer Defect Management in Semiconductor Manufacturing},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {10},
        pages = {2177-2183},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=173907},
        abstract = {Predictive analysis for wafer defect management in semiconductor manufacturing play a critical role in ensuring the quality and reliability of semiconductor manufacturing. This work proposes a robust framework leveraging deep learning techniques to enhance detection and classification of wafer defects. We integrate advanced preprocessing techniques, including Contrast Limited Adaptive Histogram Equalization (CLAHE) and local brightness adjustments, to improve image quality and increase Peak Signal-to-Noise Ratio (PSNR). A YOLOv2-based object detection model is employed to localize defects efficiently, while a hybrid Convolutional Neural Network (CNN) is utilized for accurate defect classification. Our framework begins with image pre-processing, where enhancement techniques are applied to improve contrast and noise levels. The YOLOv2 model detects and annotates defects, while the hybrid CNN classifier identifies defect types. By incorporating the improved preprocessing pipeline, the PSNR values of input images are significantly enhanced, ensuring better feature representation for downstream tasks. Experimental results demonstrate the efficacy of the proposed approach, achieving high accuracy in both localization and classification tasks. The proposed system offers a scalable and efficient solution for real-time wafer defect analysis, paving the way for enhanced automation and precision in industrial applications. The framework's modular design ensures adaptability for diverse defect types and manufacturing environments.},
        keywords = {Dataset, Image Processing Techniques, Deep Learning, Yolov2 Detection and Convolutional Neural Network.},
        month = {March},
        }