Overview / Usage

Shadow removal has been proved very helpful in higher-level computer vision applications which involves object detection, object tracking as part of the process. Removal of the shadow has always been a challenge, especially for ensuring higher-quality images after the shadow removal process. In order to unveil the information occluded by shadow, it is essential to remove the shadow. This is a two-step process which involves shadow detection and shadow removal. In this paper, shadow-less image is generated using a modified conditional GAN (cGAN) model and using shadow image and the original image as the inputs. The proposed novel method uses a discriminator that judges the local patches of the images. The model not only use the residual generator to produce high-quality images but also use combined loss, which is the weighted sum of reconstruction loss and GAN loss for training stability. Proposed model evaluated on the benchmark dataset, i.e., ISTD, and achieved significant improvements in the shadow removal task compared to the state of the art models. Structural similarity index (SSIM) metric also used to evaluate the performance of the proposed model from the perspective of Human Visual System.

Methodology / Approach

Pl. have a look at the complete methodology details in the link:

https://link.springer.com/chapter/10.1007/978-981-16-7167-8_5

Technologies Used

Pl. have a look at the technologies used in the link:

https://link.springer.com/chapter/10.1007/978-981-16-7167-8_5