Robust Fuzzy Logic Technique For Low Contrast Image Shadow Removal
The shadows are playing very hazardous for recognizing objects in low contrast Images. Shadow leads to the
problem of false positive errors and false negative errors. Shadows are created because the light source has been blocked by
object. In the existing method, suspected shadows are extracted and removed by taking the shadow features into
consideration during image segmentation and by calculating the statistical features of the image. But the main limitation of
existing method is that the dark objects which could be mistaken for shadows are ruled out according to object properties
and spatial relationship between objects. Many effective algorithms have been proposed for shadow detection but no
algorithm is produced accurate results. In this project robust fuzzy logic technique is using to eliminate shadow of object.
This method accurately identifies shadow areas with information such as gray scale and brightness of the images. The
threshold value is obtained by s-curve from the estimated grayscale value of the shadow areas by estimating control
parameters. This method work perfectly for low contrast, noisy and overlapped images.
Keywords— Shadow, FBM, MBM, Fuzzy Logic and Control Parameters.