• B Avinash
• P Maneesh Kumar
• G Datha
• N Naveen Kumar

Manual inspection in industrial manufacturing is time-consuming, subjective, and prone to human error, leading to inconsistencies in product quality assessment. This paper presents an Automated Product Defect Detection and Sorting System using Anomaly Detection, a computer vision–based approach designed to identify defective products through intelligent image analysis. The proposed system acquires product images and performs preprocessing operations including resizing, normalization, and noise reduction using OpenCV. Defect identification is carried out through two complementary machine learning strategies. First, a supervised learning approach utilizing the YOLOv8 object detection model is implemented to recognize predefined defect categories such as scratches and cracks. Second, an unsupervised anomaly detection model is employed, trained exclusively on defect-free images, enabling the detection of previously unseen or unknown defects. The system generates a binary classification output indicating the presence or absence of defects, and optionally highlights the defective region for visual interpretation. The entire framework operates on a standard computing platform without the requirement of specialized industrial hardware, making it cost-effective and suitable for academic and small-scale industrial applications. The proposed solution minimizes dependency on manual inspection, enhances detection accuracy and consistency, and demonstrates the practical integration of deep learning and computer vision in automated quality control.

Automated Defect Detection, Anomaly Detection, Deep Learning, YOLOv8, Computer Vision, Quality Control, Image Processing, Industrial Inspection

"AUTOMATED PRODUCT DEFECT DETECTION AND SORTING SYSTEM USING ANOMALY DETECTION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 3, page no.b546-b553, March-2026, Available :http://www.jetir.org/papers/JETIR2603167.pdf

"AUTOMATED PRODUCT DEFECT DETECTION AND SORTING SYSTEM USING ANOMALY DETECTION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 3, page no. ppb546-b553, March-2026, Available at : http://www.jetir.org/papers/JETIR2603167.pdf