A robust image hash function based on color and texture features of the image
Arambam Neelima, Kh. Manglem Singh · 2015
As the internet grows, the amounts of digital data like images generated by the users are increasing in huge amount. Thus a mechanism is needed to manage large database and at the same time provide protection, verification, integrity and authentication of data. An image hash function is one such mechanism. It takes an image data as an input and produces a value of foxed size as output. The main aim of this paper is to develop a robust hash function which can withstand legitimate modification. A robust hash function based on Discrete Cosine Transformation (DCT) and local variations in the Gray Level Cooccurence Matrix (GLCM) is being proposed in this paper. The image is partitioned into several rings before extracting the image features which makes it more robust to rotation attack which is not robust to most of the existing hash functions. The experimental result shows that the proposed method is robust against various geometrical methods.