• Ashwin CS
• Dr Prabha R

Due to the poor lighting condition and compelled dynamic extent of cutting-edge imaging devices, the recorded pictures are much of the time under/over-revealed and with low distinction. Most by far of past Single Image Contrast Enhancer (SICE) methods change the tone curve to address the intricacy of a data picture. Those methodologies, regardless, as often as possible bomb in revealing picture nuances because of the limited information in a single picture. Then again, the SICE task can be better rehearsed if we can take in extra information from appropriately accumulated getting ready data. In this paper, we propose to use the Convolutional Neural Arrange (CNN) to set up a SICE enhancer. One key issue is the ticket to build up a planning enlightening record of low-separation and high-separate picture sets for all the way CNN learning. To this end, we develop an extensive scale multi-presentation picture educational file, which contains 1700 luxuriously picked high-objectives multi-presentation groupings with 4,413 pictures. Thirteen specialist multi-introduction picture mix and stack-based high incredible range imaging figuring’s are used to deliver the separation updated pictures for every game plan, and passionate examinations are coordinated to screen the best quality one as the reference image of each scene. With the created instructive accumulation, a CNN can be viably arranged as the SICE enhancer to improve the intricacy of an under-/over-introduction picture. Test outcomes show the upsides of our system over existing SICE methodologies with a gigantic edge.

Contrast Enhancement, Convolutional Neural Arrange, Single Image Contrast Enhancer, Stack Based, Multi-Exposure Image Fusion

"image contrast magnification using deep learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.254-257, June 2019, Available :http://www.jetir.org/papers/JETIR1906O36.pdf

"image contrast magnification using deep learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp254-257, June 2019, Available at : http://www.jetir.org/papers/JETIR1906O36.pdf