Anomaly Sewing Pattern Detection for AIoT System using Deep Learning and Decision Tree

• 영문명: Anomaly Sewing Pattern Detection for AIoT System using Deep Learning and Decision Tree
• 발행기관: 한국스마트미디어학회
• 저자명: Nguyen Quoc Toan Seongwon Cho
• 간행물 정보: 『스마트미디어저널』Vol13, No.2, 85~94쪽, 전체 10쪽
• 주제분류: 공학 > 컴퓨터학
• 파일형태: PDF
• 발행일자: 2024.02.29

영문 초록

Artificial Intelligence of Things (AIoT), which combines AI and the Internet of Things (IoT), has recently gained popularity. Deep neural networks (DNNs) have achieved great success in many applications. Deploying complex AI models on embedded boards, nevertheless, may be challenging due to computational limitations or intelligent model complexity. This paper focuses on an AIoT-based system for smart sewing automation using edge devices. Our technique included developing a detection model and a decision tree for a sufficient testing scenario. YOLOv5 set the stage for our defective sewing stitches detection model, to detect anomalies and classify the sewing patterns. According to the experimental testing, the proposed approach achieved a perfect score with accuracy and F1score of 1.0, False Positive Rate (FPR), False Negative Rate (FNR) of 0, and a speed of 0.07 seconds with file size 2.43MB.

목차

Ⅰ. INTRODUCTION

Ⅱ. RELATED WORK

Ⅲ. PROPOSED METHOD

Ⅳ. Experiments

Ⅴ. Conclusion

키워드

Illumination compensation Illumination invariance Face tracking YCbCr Skin locus