Entre los días del 11 al 15 de Septiembre de 2017, en la ciudad de Catania, Italia, se realizó la “19th International Conference on Image Analysis and Processing (ICIAP)”. En esta conferencia el Dr. Angel Sappa, docente de la FIEC e investigador del CIDIS, presentó el trabajo titulado “Colorizing Infrared Images through a Triplet Conditional DCGAN Architecture”. Este trabajo también tiene como co-autores a la Msc. Patricia Suárez y al Dr. Boris Vintimilla.
El resumen de este artículo es:
Abstract. This paper focuses on near infrared (NIR) image colorization by using a Deep Convolutional Conditional Generative Adversarial Network (DCCGAN) architecture model. The proposed architecture consists of the use of a conditional probabilistic generative model. Firstly, it learns to colorize the given input image, by using a triplet model architecture that tackle every channel in an independent way. In the proposed model, the final layer of red channel consider the infrared image to enhance the details, resulting in a sharp RGB image. Then, in the second stage, a discriminative model is used to estimate the probability that the generated image came from the training dataset, rather than the image automatically generated. Experimental results with a large set of real images are provided showing the validity of the proposed approach. Additionally, the proposed approach is compared with a state of the art showing better results.
Para descargar la publicación click aquí
 |
 |
 |
 |