Shadow Detection and Removal from a Static Image

Farhana Aktar, Iffat Ara, Dr. Pallab Kanti Podder

For human eyes it is not difficult to distinguish shadows from objects. However, in most situations, identifying shadows by computer is a challenging research problem which is a type of segmentation problem in digital image processing. In real time systems, the automated path finding robots can easily detect obstacle and take alternate path but the problem is that they also consider shadow as a part of obstruction. In this project a hybrid algorithm is proposed to detect and extract cast shadow from a still image using mask thresholding and structuring element feature. The shadow is removed with appropriate energy functions. The proposed algorithm consists of two modules. The first module gives the detection of shadow whereas the second module gives the removal of shadow. Exploiting the geometric property of shadow, structuring elements and morphological operations, cast shadow region is extracted. Finally, it is remapped on original image to visualize the extracted region. The energy functions like additive model, basic and advanced model and YCbCr models are used. Some of the important applications can be in processing satellite images, object tracking in video and, image matching and enhancement.