Abstract: To tackle the empty cell phenomenon in the LBG algorithm，this paper presents a new empty cell strategy which is based on maximization the distance between the code words.The empty cell is filled with the input vector which has the largest distance to the codebook.The goal is to get an even distribution of the code words，alleviating the overall distorting in vector quantization.Experimental results show：the presented strategy can resolve the empty cells problem effectively，outperforming the standard LBG and other competing algorithms.The improvement of peak signal-noise ratio is 3 dB compared with the conventional LBG algorithm.