Redirigiendo al acceso original de articulo en 23 segundos...
Inicio  /  Applied Sciences  /  Vol: 13 Par: 6 (2023)  /  Artículo
ARTÍCULO
TITULO

Recovering Microscopic Images in Material Science Documents by Image Inpainting

Taeyun Kim and Byung Chul Yeo    

Resumen

Microscopic images in material science documents have increased in number due to the growth and common use of electron microscopy instruments. Through the use of data mining techniques, they are easily accessible and can be obtained from documents published online. As data-driven approaches are becoming increasingly common in the material science field, massively acquired experimental images through microscopy play important roles in terms of developing an artificial intelligence (AI) model for the purposes of automatically diagnosing crucial material structures. However, irrelevant objects (e.g., letters, scale bars, and arrows) that are often present inside original microscopic photos should be removed for the purposes of improving the AI models. To avoid the issue above, we applied four image inpainting algorithms (i.e., shift-net, global and local, contextual attention, and gated convolution) to a learning approach, with the aim of recovering microscopic images in journal papers. We estimated the structural similarity index measure (SSIM) and ℓ1" role="presentation" style="position: relative;">l1l1 l 1 /ℓ2" role="presentation" style="position: relative;">l2l2 l 2 errors, which are often used as measures of image quality. Lastly, we observed that gated convolution possessed the best performance for inpainting the microscopic images.

 Artículos similares

       
 
Luca Lanteri, Sara Calandra, Francesca Briani, Chiara Germinario, Francesco Izzo, Sabrina Pagano, Claudia Pelosi and Alba Patrizia Santo    
This paper provides the results of a 3D photogrammetric survey of the apsidal conch of St. Panfilo Church in Tornimparte (L?Aquila, Italy). The images were acquired and then processed in order to obtain a three-dimensional model available on Sketchfab pl... ver más
Revista: Applied Sciences

 
Yidong Chen, Xiang Ji, Dongting Xu, Xi Zhou, Yujing Wang and Yixiao Hu    
To enhance the continuity of character in the preservation of architectural heritage, this approach focuses on the horizontal self-similarity characteristics of architectural texture. A method using K-means and the Bhattacharyya approach for color select... ver más
Revista: Applied Sciences

 
Giuseppe Ciaburro, Sankar Padmanabhan, Yassine Maleh and Virginia Puyana-Romero    
The modern conception of industrial production recognizes the increasingly crucial role of maintenance. Currently, maintenance is thought of as a service that aims to maintain the efficiency of equipment and systems while also taking quality, energy effi... ver más
Revista: Informatics

 
Andrea Abreu-García, Ricardo M. Souto and Javier Izquierdo    
In this paper, the applicability of Ti6Al7Nb as a more biocompatible alternative for bone and dental implants than Ti6Al4V and pure titanium in terms of corrosion resistance and electrochemical inertness is investigated. The chemical inertness and corros... ver más
Revista: Coatings

 
Emad Farahani, Andre C. Liberati, Amirhossein Mahdavi, Pantcho Stoyanov, Christian Moreau and Ali Dolatabadi    
Ice formation affects the performance of many industrial components, including aircraft wings, spacecraft, and power transmission cables. In particular, ice build-up on airplane components increases drag and fuel consumption. A large number of studies ha... ver más
Revista: Coatings