• Rushikesh Kamble
• Kapil Vhatkar
• Radha Deoghare
• Prathamesh Kanva
• Shakyadeep Khobragade

This research paper explores the application of deep learning techniques for automated quality inspection in the manufacturing industry. By leveraging convolutional neural networks (CNNs) and other deep learning algorithms, the proposed system is capable of accurately detecting defects in manufacturing products. The effectiveness of the system is demonstrated through extensive experiments and comparisons with traditional methods, highlighting its potential to significantly enhance the efficiency and quality of manufacturing operations. In addition to the technical details of the proposed system, this research paper also discusses the broader implications of automated quality inspection in the manufacturing industry. The potential benefits include reduced costs, increased production speed, improved accuracy, and better safety for workers. Moreover, the use of deep learning methods for quality inspection can lead to more consistent and reliable results, as well as improved defect recognition rates. The paper also discusses some of the challenges and limitations of the proposed system, including the need for extensive data preparation and the potential for false positives. Overall, this research paper presents a valuable contribution to the field of manufacturing quality inspection and provides insights into the potential of deep learning methods for automated inspection in various industries.

CNN, Deep learning, Quality Inspection, Manufacturing products, Products defects, Automated Quality inspection

"A Comparative Review of Deep Learning-Based Approaches for Automated Quality Inspection in Manufacturing", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 5, page no.c1-c5, May-2023, Available :http://www.jetir.org/papers/JETIR2305201.pdf

"A Comparative Review of Deep Learning-Based Approaches for Automated Quality Inspection in Manufacturing", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 5, page no. ppc1-c5, May-2023, Available at : http://www.jetir.org/papers/JETIR2305201.pdf