International Journal of Science and Research (IJSR)

International Journal of Science and Research (IJSR)
Call for Papers | Fully Refereed | Open Access | Double Blind Peer Reviewed

ISSN: 2319-7064


Downloads: 194 | Views: 358 | Weekly Hits: ⮙1 | Monthly Hits: ⮙1

Research Paper | Information Technology | India | Volume 8 Issue 5, May 2019 | Popularity: 6.3 / 10


     

Novel Approach to Fashion Design using Artificial Intelligence

Ashwin Kherde, Prashant Jawade, Indrajeet Mane-Deshmukh, Pradnyoday Mirajkar


Abstract: The task of fashion designing now days is becoming more and more difficult due to increasing expectations of the consumers. For this, Artificial Intelligence is going to aid the growing need for variety of designs and their faster production which will also minimize the huge loss in production. Recent approaches include use of deep neural networks and here we are extending their use to generate the apparel designs. A class of deep neural networks known as Generative Adversarial Networks (GANs) which are comprised of two networks namely generative and discriminative. Specifically, we are using Deep Convolutional Generative Adversarial Networks (DCGANs) have certain constraints on their architecture which help them to be a good prospect for unsupervised learning. Additionally, we show that the proposed model functions generatively i. e. , according to the user preferences, it can generate new images of clothing items similar to the user taste.


Keywords: Fashion Designing, Generative Adversarial Networks, Artificial Intelligence, Deep Convolutional Generative Adversarial Networks


Edition: Volume 8 Issue 5, May 2019


Pages: 285 - 289



Make Sure to Disable the Pop-Up Blocker of Web Browser




Text copied to Clipboard!
Ashwin Kherde, Prashant Jawade, Indrajeet Mane-Deshmukh, Pradnyoday Mirajkar, "Novel Approach to Fashion Design using Artificial Intelligence", International Journal of Science and Research (IJSR), Volume 8 Issue 5, May 2019, pp. 285-289, https://www.ijsr.net/getabstract.php?paperid=ART20197150, DOI: https://www.doi.org/10.21275/ART20197150