• Sandeep S. Kumar
• Ashutosh B. Jena
• Robin B. Patoliya
• Dr. Jitendra H. Saturwar

With the advancements in generation and its technology, humans are finding ways to make their lives faster, efficient and hassle-free. Graphics is a way of portraying text with ease and better understandability. Blender, Adobe Photoshop, Coreldraw, etc. are still used as conventional ways to render graphics. However, the time and effort required to render files in these software is very high. The learning curve of these software is also a limitation for a naive user. These software also need systems with technical specification that are graphic focused and uncompromisable. These professional software also come with a high price tag that is not affordable by most of the users. Besides, these software are not explicitly crafted to convert sketches into equivalent images. Hence they are not a logical solution for converting sketches into images. The proposed system makes the use of Generative Adversarial Networks to overcome the limitations of the existing systems. A generative adversarial network is a class of machine learning algorithms. Two or more neural networks rencounter with one another in a zero sum game framework. At the beginning, the system uses a feature extraction process to recognize the object. Once the object is recognized, the algorithms fill the outlines of the sketch to generate a number of results. These results are then evaluated against the ground truth to produce an output that is as closely accurate to the training data that was fed onto the system during the training process. The system tends to achieve a high level of accuracy in recognizing and filling user fed sketches into realistic viable images. This would eliminate the need of using intensive aforementioned software, thereby improving the user’s experience and saving their time and efforts.

Sketch to image, Image processing, Generative Adversarial Networks, Graphics rendering, Object recognition, Face Synthesis.

"Sketch to Image Translation with Generative Adversarial Networks", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.7, Issue 4, page no.1992-1996, April-2020, Available :http://www.jetir.org/papers/JETIR2004473.pdf

"Sketch to Image Translation with Generative Adversarial Networks", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.7, Issue 4, page no. pp1992-1996, April-2020, Available at : http://www.jetir.org/papers/JETIR2004473.pdf