Comparison of Bacterial Foraging Optimization (BFO) Neural Network with Haar Wavelet Transform in Image Compression

Abstract

In the present electronic communication scenario, data security is one of the major challenges. After the World War II, the need for a secure and robust communication between the communicating entities has increased due to the fear of terrorism. The publishers of digital audio and video are worried of their works being corrupted by illegal copying or redistribution, hence it is of primary importance to protect information. Cryptography is the method to hide secret data by scrambling so that it is unreadable, however it does not assure security and robustness as the hacker can obviously guess that there is a confidential message passing on from the source to the destination. Steganography is concealed writing and is the scientific approach of inserting the secret data within a cover media such that the unauthorized viewers do not get an idea of any information hidden in it. Steganography is an alternative to cryptography in which the secrete data is embedded into the carrier in such way that only carrier is visible which is sent from transmitter to receiver without scrambling. The combination of cryptography and steganography provide high level security to the secret information. Cover image is known as carrier image and is the original image in which the secret data i.e., the payload is embedded. The unified image obtained after embedding the payload into the cover image is called the stego image. The recent boom in IT industry facilitates embedding data and security issues effectively. Steganography is hiding private or secret data within a carrier in invisible manner. Steganography refers to the information that has been concealed inside a digital picture, video or audio file. This paper is based on JPEG quantization table modification. Firstly, the cover image is divided into 32*32 blocks and DCT is applied on each block. The number of payload LSB bits is embedded into DCT coefficients of the cover image based on the values of DCT coefficients. Secondly, IDCT is applied to produce the stego image which is identical to cover image. Then, the watermarked image is transmitted over the public channel. Our basis objective is to work on the color images with three planes and to work out on the Capacity, PSNR AND MSE values.