Analysis of the application of convolutional neural networks in the field of computer vision

• Autores: De la Cruz-Rocca, Marco A., Muñoz-Robles, Williams, Trinidad-Malpartida, Melquiades A.
• Formato: artículo
• Fecha de Publicación: 2024
• Institución: Universidad Nacional Hermilio Valdizan
• Repositorio: Revistas - Universidad Nacional Hermilio Valdizán
• Lenguaje: español
• OAI Identifier: oai:revistas.unheval.edu.pe:article/2105
• Enlace del recurso: http://revistas.unheval.edu.pe/index.php/riv/article/view/2105
• Nivel de acceso: acceso abierto
• Materia: redes neuronales convolucionales; visión artificial; análisis bibliométrico; convolutional neural networks; computer vision; bibliometric analysis

This article analyzes the application of Convolutional Neural Networks (CNN) in the field of computer vision, using the bibliometric method. An analysis of literary samples, using basic descriptive statistics, is performed by filtering the Scopus database of 2526 records, comprising a period of 5 years (2018-2022). The review of the theoretical framework reveals that CNRs are employed in various computer vision applications such as image recognition, object classification, pattern detection and other applications related to image processing including fault diagnosis. The bibliometric analysis indicates a significant increase in the production of articles on CNRs in the area of machine vision, covering several areas, such as computer science and engineering, areas that have the highest concentration of research papers, and Chinese organizations have the highest proportion of affiliation and research funding capacity in this topic, not to mention that China leads the number of publications in CNRs. The most prominent lead author is Schumann, A.W., not the same in other similar studies. Key directions for future research include quantitative experimental exploration, diversification of fields of action.