Automatic Detection and Identification of Defects by Deep Learning Algorithms from Pulsed Thermography Data

• Main Authors: Duan, Y. (Author), Fang, Q. (Author), Garrido, I. (Author), Ibarra-Castanedo, C. (Author), Maldague, X. (Author)
• Format: Article
• Language: English
• Published: MDPI 2023
• Subjects: automatic defect identification and segmentation; Automatic defect identification and segmentation; Convolution; convolutional neural network; Convolutional neural network; Convolutional neural networks; Deep learning; Deep-learning non-destructive evaluation; deep-learning non-destructive evaluation (NDE); Defect identification; Defects; Detection and identifications; Image quality; infrared image processing; Infrared image processing; infrared thermography; Learning algorithms; Learning systems; Non destructive evaluation; Nondestructive examination; pulsed thermography; Pulsed thermography; Quality management; Region-based; Segmentation methods; Semantic Segmentation; Semantics; Thermography (imaging)
• Online Access: View Fulltext in Publisher; View in Scopus

 Infrared thermography (IRT), is one of the most interesting techniques to identify different kinds of defects, such as delamination and damage existing for quality management of material. Objective detection and segmentation algorithms in deep learning have been widely applied in image processing, although very rarely in the IRT field. In this paper, spatial deep-learning image processing methods for defect detection and identification were discussed and investigated. The aim in this work is to integrate such deep-learning (DL) models to enable interpretations of thermal images automatically for quality management (QM). That requires achieving a high enough accuracy for each deep-learning method so that they can be used to assist human inspectors based on the training. There are several alternatives of deep Convolutional Neural Networks for detecting the images that were employed in this work. These included: 1. The instance segmentation methods Mask–RCNN (Mask Region-based Convolutional Neural Networks) and Center–Mask; 2. The independent semantic segmentation methods: U-net and Resnet–U-net; 3. The objective localization methods: You Only Look Once (YOLO-v3) and Faster Region-based Convolutional Neural Networks (Fast-er-RCNN). In addition, a regular infrared image segmentation processing combination method (Absolute thermal contrast (ATC) and global threshold) was introduced for comparison. A series of academic samples composed of different materials and containing artificial defects of different shapes and nature (flat-bottom holes, Teflon inserts) were evaluated, and all results were studied to evaluate the efficacy and performance of the proposed algorithms. © 2023 by the authors.