Block truncation coding (BTC), known as a simple and efficient digital image compression algorithm, its essential is to encode the non-overlapping sub-blocks of input images with a pair of low-/high- quantity levels and a distribution matrix. Absolute Moment Block Truncation Coding (AMBTC) is a widely used modified version of BTC. Based on BTC, we paper propose a new approach by means of an adjusted threshold to classify each sub-block. Then, for those blocks grouped as to be modified we apply a new BTC-based modification method by searching optimized threshold as the replacement of the mean value of sub-blocks in AMBTC for pixels grouping. Experimental results show that, compared with AMBTC, the reconstructed image quality of proposed scheme can be improved by 0.5~0.8dB in Peak signal to noise ratio (PSNR)
