Segmentation and reversible watermarking of peripheral blood smear images

Abstract

This paper proposes an automated method for the segmentation of peripheral blood smear images, depicting the differential count of white blood cells. It also proposes a reversible fragile watermarking technique, in which the watermark-related information is embedded in the Region of Non-Interest (RONI) of the image. Image authenticity and integrity, is maintained by embedding the Input message along with the Hash Message Authentication Codes (HMAC) of the image and the message itself.