Open AccessCBNWI-50: A Deep Learning Bird Dataset for Image Translation and Resolution Improvement using Generative Adversarial Network
Author(s) -
Akanksha Sharma,
Neeru Jindal
Publication year - 2019
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.i1015.0789s19
Subject(s) - image translation , computer science , translation (biology) , artificial intelligence , deep learning , image (mathematics) , adversarial system , generative grammar , function (biology) , segmentation , bridge (graph theory) , transfer of learning , pattern recognition (psychology) , machine learning , medicine , biochemistry , chemistry , evolutionary biology , biology , messenger rna , gene
Generative Adversarial Networks have gained prominence in a short span of time as they can synthesize images from latent noise by minimizing the adversarial cost function. New variants of GANs have been developed to perform specific tasks using state-of-the-art GAN models, like image translation, single image super resolution, segmentation, classification, style transfer etc. However, a combination of two GANs to perform two different applications in one model has been sparsely explored. Hence, this paper concatenates two GANs and aims to perform Image Translation using Cycle GAN model on bird images and improve their resolution using SRGAN. During the extensive survey, it is observed that most of the deep learning databases on Aves were built using the new world species (i.e. species found in North America). Hence, to bridge this gap, a new Ave database, 'Common Birds of North - Western India' (CBNWI-50), is also proposed in this work.