• Aswin V
• Dhushanthan S
• Boopathi S

This project addresses the pressing need for efficient quality control in manufacturing, particularly focusing on metal shaft production, using Convolutional Neural Networks (CNNs) to automate defect detection. By training the CNN on a diverse dataset, including normal and defective shaft images, various defects like cracks and pits can be identified. Through techniques such as preprocessing, data augmentation, and transfer learning, the system aims to achieve real-time, automated defect identification, reducing manual inspection needs and enhancing product reliability. Integration into production lines aligns with industry 4.0 principles, driving innovation and competitiveness in manufacturing. Ongoing research aims to further enhance the system's capabilities and performance.

Metal shafts, Defect detection, Convolutional Neural Networks (CNNs), Automation, Product reliability, Industry 4.0

"DEFECT DETECTION ON METAL SHAFT SURFACES USING DEEP LEARNING TECHNIQUES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 3, page no.g734-g738, March-2024, Available :http://www.jetir.org/papers/JETIR2403699.pdf

"DEFECT DETECTION ON METAL SHAFT SURFACES USING DEEP LEARNING TECHNIQUES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 3, page no. ppg734-g738, March-2024, Available at : http://www.jetir.org/papers/JETIR2403699.pdf