Resumen

GARATE-ESCAMILLA, Anna Karen; MARTINEZ, Rafael; ORTIZ-BAYLISS, José Carlos  y  HAJJAM, Amir. Comparative Analysis of Classification Models Using Midjourney-generated Images in the Realm of Machine Learning. Comp. y Sist. [online]. 2025, vol.29, n.1, pp.103-110.  Epub 05-Dic-2025. ISSN 2007-9737.  https://doi.org/10.13053/cys-29-1-5535.

Artificial intelligence (AI) integration has shaped rapid and remarkable advances in machine learning. In the relentless pursuit of advancing AI capabilities, applications such as Midjourney emerge as pioneering tools designed to create intricate images from the essence of textual prompts. Midjourney, an example of a generative AI tool, utilizes text-to-image methods with an extensive database. This study aims to provide insights into the potential advantages and limitations of generative AI images in machine learning. This research methodology explores Midjourney to generate 500 images of dogs and cats. Subsequently, these images serve as the basis for building classification models. We will explore the classification models and their evaluations in three scenarios: i) 100% of images generated by Midjourney, ii) 100% of real images, and iii) 50% of images generated by Midjourney and 50% of real images. To achieve this goal, the study utilizes two commonly used deep learning models, InceptionV3 and EfficientNetB4, for training and testing the classification models. The analysis results indicate a significant improvement when combining generated Midjourney images and real images for classification. This comparative examination highlights the effectiveness of AI-generated images in enhancing the performance of machine learning models, emphasizing the potential to augment the image subset with synthesized images from generative IA.

Palabras llave : Deep learning; neural networks; generative IA; artificial intelligence; machine learning.

        · texto en Inglés     · Inglés ( pdf )