Application of Convolutional Neural Networks in the Problem of Removing Shadows from Photographs

The article proposes a method for removing shadows from photographs using deep learning methods. The proposed method consists of several stages: dividing the image into rectangular fragments of 32x32 pixels, localizing shadows on each fragment, restoring the color of shadowed objects, and combining the fragments back into a whole image. Shadow localization is considered as a semantic segmentation problem; to solve it, a neural network of encoder-decoder architecture has been developed and trained. To restore the color of objects in identified shaded areas, another neural network based on the CDNet architecture is used. Examples of image processing using the developed method are given, including images from a drone, and the high quality of restoration of shaded areas is demonstrated.

1. Zhang X., Zhao Y., Gu C., Lu C., Zhu S. SpA-Former: An Effective and lightweight Transformer for image shadow removal // International Joint Conference on Neural Networks (IJCNN). P. 1-8.
2. Simonyan K., Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition // 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA. 2015. Conference Track Proceedings.
3. Soria X., Sappa A., Hammoud R. Wide-Band Color Imagery Restoration for RGB-NIR Single Sensor Images // Sensors (Basel, Switzerland). Vol.18. №7. P. 2059.
4. Kuzmin С. А. Ustranenie vliyaniya tenej na tochnost vydeleniya obyektov v videoposledovatelnostyah [Eliminating the influence of shadows on the accuracy of object selection in video sequences] // Zhurnal Radioelektroniki=Radioelectronics Journal [Online journal]. №5. 2012. Available at: jre.cplire.ru/jre/may12/2/text.html (Accessed 01.02.2024). (In Russ.).