Textile Fabric Defect Detection Using Enhanced Deep Convolutional Neural Network with Safe Human–Robot Collaborative Interaction

TY - JOUR

T1 - Textile Fabric Defect Detection Using Enhanced Deep Convolutional Neural Network with Safe Human–Robot Collaborative Interaction

AU - Hassan, Syed Ali

AU - Beliatis, Michail

AU - Radziwon, Agnieszka

AU - Menciassi, Arianna

AU - Oddo, Calogero maria

PY - 2024/11/2

Y1 - 2024/11/2

N2 - The emergence of modern robotic technology and artificial intelligence (AI) enables a transformation in the textile sector. Manual fabric defect inspection is time-consuming, error-prone, and labor-intensive. This offers a great possibility for applying more AI-trained automated processes with safe human–robot interaction (HRI) to reduce risks of work accidents and occupational illnesses and enhance the environmental sustainability of the processes. In this experimental study, we developed, implemented, and tested a novel algorithm that detects fabric defects by utilizing enhanced deep convolutional neural networks (DCNNs). The proposed method integrates advanced DCNN architectures to automatically classify and detect 13 different types of fabric defects, such as double-ends, holes, broken ends, etc., ensuring high accuracy and efficiency in the inspection process. The dataset is created through augmentation techniques and a model is fine-tuned on a large dataset of annotated images using transfer learning approaches. The experiment was performed using an anthropomorphic robot that was programmed to move above the fabric. The camera attached to the robot detected defects in the fabric and triggered an alarm. A photoelectric sensor was installed on the conveyor belt and linked to the robot to notify it about an impending fabric. The CNN model architecture was enhanced to increase performance. Experimental findings show that the presented system can detect fabric defects with a 97.49% mean Average Precision (mAP).

AB - The emergence of modern robotic technology and artificial intelligence (AI) enables a transformation in the textile sector. Manual fabric defect inspection is time-consuming, error-prone, and labor-intensive. This offers a great possibility for applying more AI-trained automated processes with safe human–robot interaction (HRI) to reduce risks of work accidents and occupational illnesses and enhance the environmental sustainability of the processes. In this experimental study, we developed, implemented, and tested a novel algorithm that detects fabric defects by utilizing enhanced deep convolutional neural networks (DCNNs). The proposed method integrates advanced DCNN architectures to automatically classify and detect 13 different types of fabric defects, such as double-ends, holes, broken ends, etc., ensuring high accuracy and efficiency in the inspection process. The dataset is created through augmentation techniques and a model is fine-tuned on a large dataset of annotated images using transfer learning approaches. The experiment was performed using an anthropomorphic robot that was programmed to move above the fabric. The camera attached to the robot detected defects in the fabric and triggered an alarm. A photoelectric sensor was installed on the conveyor belt and linked to the robot to notify it about an impending fabric. The CNN model architecture was enhanced to increase performance. Experimental findings show that the presented system can detect fabric defects with a 97.49% mean Average Precision (mAP).

KW - human–robot interaction (HRI); fabric defect detection; computer vision; safe human–robot collaboration; convolutional neural network; transfer learning; quality inspection; AI; DCNN; artificial intelligence in textiles; computer vision for quality contro

KW - DCNN

KW - transfer learning

KW - human–robot interaction (HRI)

KW - convolutional neural network

KW - AI

KW - fabric defect detection

KW - artificial intelligence in textiles

KW - computer vision for quality control

KW - computer vision

KW - quality inspection

KW - safe human–robot collaboration

KW - industrial robotics for fabric inspection

UR - http://www.scopus.com/inward/record.url?scp=85208595607&partnerID=8YFLogxK

U2 - 10.3390/electronics13214314

DO - 10.3390/electronics13214314

M3 - Journal article

SN - 2079-9292

VL - 13

JO - Electronics (Switzerland)

JF - Electronics (Switzerland)

IS - 21

M1 - 4314

ER -