Inicio  /  Applied Sciences  /  Vol: 14 Par: 6 (2024)  /  Artículo
ARTÍCULO
TITULO

Surface Illumination as a Factor Influencing the Efficacy of Defect Recognition on a Rolled Metal Surface Using a Deep Neural Network

Pavlo Maruschak    
Ihor Konovalenko    
Yaroslav Osadtsa    
Volodymyr Medvid    
Oleksandr Shovkun    
Denys Baran    
Halyna Kozbur and Roman Mykhailyshyn    

Resumen

Modern neural networks have made great strides in recognising objects in images and are widely used in defect detection. However, the output of a neural network strongly depends on both the training dataset and the conditions under which the image was acquired for analysis. We have developed a software?hardware method for evaluating the effect of variable lighting on the results of defect recognition using a neural network model. The proposed approach allows us to analyse the recognition results of an existing neural network model and identify the optimal range of illumination at which the desired defects are recognised most consistently. For this purpose, we analysed the variability in quantitative parameters (area and orientation) of damage obtained at different degrees of illumination for two different light sources: LED and conventional incandescent lamps. We calculated each image?s average illuminance and quantitative parameters of recognised defects. Each set of parameters represents the results of defect recognition for a particular illuminance level of a given light source. The proposed approach allows the results obtained using different light sources and illumination levels to be compared and the optimal source type/illuminance level to be figured out. This makes implementing a defect detection environment that allows the best recognition accuracy and the most controlled product quality possible. An analysis of a steel sheet surface showed that the best recognition result was achieved at an illuminance of ~200 lx. An illuminance of less than ~150 lx does not allow most defects to be recognised, whereas an illuminance larger than ~250 lx increases the number of small objects that are falsely recognised as defects.

 Artículos similares

       
 
Jiantao Gao, Jingting Zhang, Chang Liu, Xiaomao Li and Yan Peng    
Water segmentation is essential for the autonomous driving system of unmanned surface vehicles (USVs), which provides reliable navigation for making safety decisions. However, existing methods have only used monocular images as input, which often suffer ... ver más

 
Venkatachalam Jayaraman, Shanmugam Mahalingam, Shanmugavel Chinnathambi, Ganesh N. Pandian, Aruna Prakasarao, Singaravelu Ganesan, Jayavel Ramasamy, Sivasankaran Ayyaru and Young-Ho Ahn    
The HfO2 nanoparticles and the nanocomposites of HfO2-graphene (10, 30, and 50 wt%) were prepared via precipitation and simple mixing method. The XRD pattern confirmed the presence of monoclinic HfO2 and hexagonal graphene in the nanocomposite. Raman spe... ver más
Revista: Applied Sciences

 
Manar Ahmed Hamza, Hamed Alqahtani, Dalia H. Elkamchouchi, Hussain Alshahrani, Jaber S. Alzahrani, Mohammed Maray, Mohamed Ahmed Elfaki and Amira Sayed A. Aziz    
Unmanned aerial vehicles (UAVs) have significant abilities for automatic detection and mapping of urban surface materials due to their high resolution. It requires a massive quantity of data to understand the ground material properties. In recent days, c... ver más
Revista: Applied Sciences

 
Chang Lin, Wu Chen and Haifeng Zhou    
To visually detect sea-surface targets, the objects of interest must be effectively and rapidly isolated from the background of sea-surface images. In contrast to traditional image detection methods, which employ a single visual feature, this paper propo... ver más

 
Eduard Muslimov, Thibault Behaghel, Emmanuel Hugot, Kelly Joaquina and Ilya Guskov    
In the present paper, we discuss the design of a projection system with curved display and its enhancement by variably adjusting the curvature. We demonstrate that the focal surface curvature varies significantly with a change of the object position and ... ver más
Revista: Applied Sciences