• Sparsh Goyal

Small garment makers in developing nations have usually relied on manual quality inspection of fabric and finished clothes. Raw fabric is a very big part of the manufacturer’s total costs, and unflagged defects that are missed by human inspectors have a huge impact on their razor-thin profit margins. This paper shows that computer vision is perhaps one of the best ways to avoid errors that human inspectors miss due to fatigue after an hour or so of continuous work. While small factories have avoided automation because it was simply too expensive, modern low-cost edge computing systems, such as NVIDIA Jetson boards running the YOLOv8 model, make automated defect detection much more affordable. YOLOv8 has a clear advantage over older ResNet systems because it runs nearly four times as fast and on less expensive hardware. Another major benefit is that defect detection cameras can be easily bolted right onto existing machines without completely changing current production setups. As a result, these technologies can save a lot of money by increasing material yield and preventing liabilities due to defective clothes reaching international buyers.

"A Keen Digital Eye: Using Computer Vision to Develop Low-cost, High Accuracy Defect Detection Systems for Small Garment Manufacturers", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 10, page no.b728-b732, October-2026, Available :http://www.jetir.org/papers/JETIR2610173.pdf

"A Keen Digital Eye: Using Computer Vision to Develop Low-cost, High Accuracy Defect Detection Systems for Small Garment Manufacturers", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 10, page no. ppb728-b732, October-2026, Available at : http://www.jetir.org/papers/JETIR2610173.pdf