Using Different Types of Artificial Neural Networks to Classify 2D Matrix Codes and Their Rotations-A Comparative Study.

Artificial neural networks can solve various tasks in computer vision, such as image classification, object detection, and general recognition. Our comparative study deals with four types of artificial neural networks-multilayer perceptrons, probabilistic neural networks, radial basis function neural networks, and convolutional neural networks-and investigates their ability to classify 2D matrix codes (Data Matrix codes, QR codes, and Aztec codes) as well as their rotation. The paper presents the basic building blocks of these artificial neural networks and their architecture and compares the classification accuracy of 2D matrix codes under different configurations of these neural networks. A dataset of 3000 synthetic code samples was used to train and test the neural networks. When the neural networks were trained on the full dataset, the convolutional neural network showed its superiority, followed by the RBF neural network and the multilayer perceptron.

Comparative Study of Data Matrix Codes Localization and Recognition Methods.

We provide a comprehensive and in-depth overview of the various approaches applicable to the recognition of Data Matrix codes in arbitrary images. All presented methods use the typical "L" shaped Finder Pattern to locate the Data Matrix code in the image. Well-known image processing techniques such as edge detection, adaptive thresholding, or connected component labeling are used to identify the Finder Pattern. The recognition rate of the compared methods was tested on a set of images with Data Matrix codes, which is published together with the article. The experimental results show that methods based on adaptive thresholding achieved a better recognition rate than methods based on edge detection.

Introduction of Deep Learning in Thermographic Monitoring of Cultural Heritage and Improvement by Automatic Thermogram Pre-Processing Algorithms.

The monitoring of heritage objects is necessary due to their continuous deterioration over time. Therefore, the joint use of the most up-to-date inspection techniques with the most innovative data processing algorithms plays an important role to apply the required prevention and conservation tasks in each case study. InfraRed Thermography (IRT) is one of the most used Non-Destructive Testing (NDT) techniques in the cultural heritage field due to its advantages in the analysis of delicate objects (i.e., undisturbed, non-contact and fast inspection of large surfaces) and its continuous evolution in both the acquisition and the processing of the data acquired. Despite the good qualitative and quantitative results obtained so far, the lack of automation in the IRT data interpretation predominates, with few automatic analyses that are limited to specific conditions and the technology of the thermographic camera. Deep Learning (DL) is a data processor with a versatile solution for highly automated analysis. Then, this paper introduces the latest state-of-the-art DL model for instance segmentation, Mask Region-Convolution Neural Network (Mask R-CNN), for the automatic detection and segmentation of the position and area of different surface and subsurface defects, respectively, in two different artistic objects belonging to the same family: Marquetry. For that, active IRT experiments are applied to each marquetry. The thermal image sequences acquired are used as input dataset in the Mask R-CNN learning process. Previously, two automatic thermal image pre-processing algorithms based on thermal fundamentals are applied to the acquired data in order to improve the contrast between defective and sound areas. Good detection and segmentation results are obtained regarding state-of-the-art IRT data processing algorithms, which experience difficulty in identifying the deepest defects in the tests. In addition, the performance of the Mask R-CNN is improved by the prior application of the proposed pre-processing algorithms.

Experimental Assessment of Time-Limited Operation and Rectification of a Bridge Crane.

This paper describes a problem related to a casting bridge crane with a combined load of 200/50/12.5 t and a span of 18.6 m, working in a heavy metallurgical operation. Due to the specific stress of the structure after its long-term operation, longitudinal fillet welds between the upper flange and the web of the main box beam on the rail side of the 200 t trolley were irreparably damaged. As a result, the cross-section of the main beam had opened, thereby substantially reducing its strength and stiffness. This resulted in a disproportionate increase and undesirable redistribution of stresses in the beam and, at the same time, an increase in the probability of acute fatigue or the loss of stability of the elastic beam shape. Therefore, the rectification of the damaged load-bearing structure was carried out by specific structural modifications. Critical load-bearing elements were subjected to complicated strength and fatigue life analyses before and after rectification. These analyses were supported by experimental measurements. The applied modifications resulted in a partial strengthening of the lifting device with the possibility of its further operation, but only in a limited mode, with a limited period of operation with a time limit of 2 years and a reduced total load capacity of 150 t. The applied methods are also applicable for the fatigue analysis of load-bearing elements and equipment for bridge, gantry and tower cranes, crane tracks, road and railway bridges and support structures under machinery and other devices with a dominant transverse and rotating effect.

Measuring the Water Content in Wood Using Step-Heating Thermography and Speckle Patterns-Preliminary Results.

The relationship between wood and its degree of humidity is one of the most important aspects of its use in construction and restoration. The wood presents a behavior similar to a sponge, therefore, moisture is related to its expansion and contraction. The nondestructive evaluation (NDE) of the amount of moisture in wood materials allows to define, e.g., the restoration procedures of buildings or artworks. In this work, an integrated study of two non-contact techniques is presented. Infrared thermography (IRT) was able to retrieve thermal parameters of the wood related to the amount of water added to the samples, while the interference pattern generated by speckles was used to quantify the expansion and contraction of wood that can be related to the amount of water. In twenty-seven wooded samples, a known quantity of water was added in a controlled manner. By applying advanced image processing to thermograms and specklegrams, it was possible to determine fundamental values controlling both the absorption of water and the main thermophysical parameters that link the samples. On the one hand, results here shown should be considered preliminary because the experimental values obtained by IRT need to be optimized for low water contents introduced into the samples. On the other hand, speckle interferometry by applying an innovative procedure provided robust results for both high and low water contents.

Identification of QR Code Perspective Distortion Based on Edge Directions and Edge Projections Analysis.

QR (quick response) Codes are one of the most popular types of two-dimensional (2D) matrix codes currently used in a wide variety of fields. Two-dimensional matrix codes, compared to 1D bar codes, can encode significantly more data in the same area. We have compared algorithms capable of localizing multiple QR Codes in an image using typical finder patterns, which are present in three corners of a QR Code. Finally, we present a novel approach to identify perspective distortion by analyzing the direction of horizontal and vertical edges and by maximizing the standard deviation of horizontal and vertical projections of these edges. This algorithm is computationally efficient, works well for low-resolution images, and is also suited to real-time processing.