Discovery and Classification of Defects on Facing Brick Specimens Using a Convolutional Neural Network

Abstract

In recent years, visual automatic non-destructive testing using machine vision algorithms has been widely used in industry. This approach for detecting, classifying, and segmenting defects in building materials and structures can be effectively implemented using convolutional neural networks. Using intelligent systems in the initial stages of manufacturing can eliminate defective building materials, prevent the spread of defective products, and detect the cause of specific damage. In this article, the solution to the problem of building elements flaw detection using the computer vision method was considered. Using the YOLOv5s convolutional neural network for the detection and classification of various defects of the structure, the appearance of finished products of facing bricks that take place at the production stage is shown during technological processing, packaging, transportation, or storage. The algorithm allows for the detection of foreign inclusions, broken corners, cracks, and color unevenness, including the presence of rust spots. To train the detector, our own empirical database of images of facing brick samples was obtained. The set of training data for the neural network algorithm for discovering defects and classifying images was expanded by using our own augmentation algorithm. The results show that the developed YOLOv5s model has a high accuracy in solving the problems of defect detection: mAP0.50 = 87% and mAP0.50:0.95 = 72%. It should be noted that the use of synthetic data obtained by augmentation makes it possible to achieve a good generalizing ability from the algorithm, it has the potential to expand visual variability and practical applicability in various shooting conditions.

Detection and Dispersion Analysis of Water Globules in Oil Samples Using Artificial Intelligence Algorithms

“…“ AP@ 50 and AP@ 75 values were calculated showing AP values calculated at IoU = 0.50 and IoU = 0.75 respectively” [ 53 , 54 ]; in this study, AP@ 50 = 89% and AP@ 75 = 78%. If the level of accuracy obtained using the indicated metrics is lower than the level of accuracy declared by the researcher (in practice, from 85%), then it is necessary to increase the number of images in the training set and/or add additional effects to the augmentation process and retrain the CNN.…”

“…Precision and recall can be calculated using the formulas: where “true positive ( TP ) is the correct detection made by the model; false positive ( FP ) is incorrect detection made by the detector; false negative ( FN ) is a true result missed (not detected) by the detector” [ 53 , 54 ].…”

“…If it is difficult to increase the volume of real data, researchers apply various methods of data inflation based on the available data [ 51 ]. In this study, the increase in the size of the original set was artificially carried out using the authors’ augmentation algorithm in which for each image, the coordinates of the bounding box are automatically recalculated [ 52 ].…”

“…Geometric operations: image rotation/reflection, random image shifts along the Ox and Oy axes, and image rotation by 90°, 180°, and 270° [ 53 , 54 ].…”

Unleashing the power of AI in detecting metal surface defects: an optimized YOLOv7-tiny model approach

“…However, there are great differences in the defect scale of defects in the defect detection process. In order to improve the detection accuracy, Beskopylny et al (2023) proposed a feature extraction network that utilizes depth-wise separable convolution to enhance detection. They also introduced dilated convolutions in the spatial pyramid pooling (SPPF) module to enlarge the receptive field and incorporate contextual information.…”