After quantization

a lot of image's wavelet coefficients will become zero valued. How to encode the location of these zero valued coefficients with as few symbols as possible is the key to increase the compression ratio of image coding. Shapiro presented the so called zerotree structure to encode these zero valued coefficients

in which the root of a zerotree is the only symbol to be encoded. One can obtain from the root's location the locations of all zero valued coefficients within the zerotree. Shapiro's zerotree coding has been accepted by JPEG2000

a new image coding international standard. In this paper we present an improvement to Shapiro's zerotree coding. We find in practice that after quantization and zerotree coding of image's wavelet coefficients

the roots of zerotrees will appear consecutively if they are scanned following a certain order. Thus

we add the runlength coding of consecutive roots of zerotrees before entropy coding to increase the compression ratio of image coding. Theoretical analysis and experimental results presented in this paper show that our algorithm improves the performance of Shapiro's zerotree coding.