摘要 |
An image is divided into blocks of N consecutive pixels, and each block is coded with reference to M reference pixels, where M and N are integers greater than one. Different patterns of N pixels are obtained from the M reference pixels. If one of these patterns matches the N consecutive pixels sufficiently closely, that block of N consecutive pixels is coded as a flag and a pattern code. When the coded data are decoded, the flags identify blocks that were coded in this way, and these blocks are decoded by copying already-decoded data identified by the pattern codes.
|