CBNWI-50: A Deep Learning Bird Dataset for Image Translation and Resolution Improvement using Generative Adversarial Network
Akanksha Sharma1, Neeru Jindal2
1Akanksha Sharma, Department of Electronics and Communication, Thapar Institute of Engineering and Technology Patiala(Punjab), India.
2Neeru Jindal, Department of Electronics and Communication, Thapar Institute of Engineering and Technology Patiala (Punjab), India.
Manuscript received on 09 August 2019 | Revised Manuscript received on 17 August 2019 | Manuscript Published on 26 August 2019 | PP: 91-102 | Volume-8 Issue-9S August 2019 | Retrieval Number: I10150789S19/19©BEIESP DOI: 10.35940/ijitee.I1015.0789S19
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: 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.
Keywords: Generative Adversarial Networks, Indian-Subcontinent, Bird Dataset, Image Translation, Single Image Super Resolution.
Scope of the Article: Deep Learning