Performance Analysis of LSB Color Image Steganography based on Embedding Pattern of the RGB Channels

Abstract

This research aims to analyze three patterns of embedding messages based on the Least Significant Bit (LSB) method on RGB color images. Previous research has suggested a pattern of LSB x-y-z embedding, where the value of x-y-z is 2-3-3 or 3-2-3 or 3-3-2, where the sum of the x-y-z value is 8-bits. The x value represents the number of message bits embedded on the red channel, y on the green channel, and z on the blue channel. Each research claims that the pattern has its advantages, especially to increase payload and imperceptibility. Because of this, a third method is used to compile the three methods using the same dataset, both the host image and the message. To increase the security of the message, encryption is performed using the RSA method before embedded. Stego image quality is measured by comparing it with the host image with four kinds of measuring tools, namely mean square error (MSE), peak signal to noise ratio (PSNR), structural similarity index measurement (SSIM), and histogram analysis. The results showed that all methods were of good quality and identical. It's just that LSB 3-2-3 is slightly superior when measured based on MSE and PSNR values, but the average difference in value does not reach 0.1dB. Whereas based on measuring SSIM LSB 3-3-2 get the best results. Where the difference is not more than 0.001. While at the message extraction stage the value of the bit error ratio (BER) between the original message and the extracted message yields a value of 0, which indicates that all methods can extract the message perfectly.