A wavelet transform and SOFM based certificate image compression method

A compression method is proposed based on the wavelet transform and self-organizing feature mapping (SOFM) neural network, in order to store the certificate image into the two-dimensional barcode, and at the same time, hold the image quality which must satisfy the requirement of true or false identification under high compression rate. The different sub-band coefficients of wavelet transform are quantized by SOFM with different quantization levels. The high efficient compression of the identification (ID) card image is gained using an adaptive resolution combination method based on sub-block clustering encoding which encodes the sub-band coefficients after quantization. The experimental results show that this method has higher performance than JPEG.