Through the combination of the idea of the linear prediction used in the GlicBawls coding scheme and the idea of the quantization taken in the CALIC coding scheme to reduce the number of contexts, a new context model of wavelet coefficients for image compression is proposed. Wavelet coefficients are encoded by the arithmetic encoder, with the contexts formed by quantizing linear prediction values. Experimental results show that the model achieves higher lossless compression rate of image than lossless SPIHT and lossless EBCOT used in JPEG2000. In addition, by exploiting the multiresolution property of wavelet, the model can compress the transformed image for progressive resolution and earn higher compression rate for each scale of the image than EBCOT.