Abstract: A motion compensated prediction interframe coding system which first measures characteristics regarding the fineness of a pattern or texture of a picture, which is represented by an input television signal and is divided into a group of continuous blocks each quantized by using a quantization step size, and changes the quantization step size into a smaller one if quantizes a block having a picture pattern or texture finer than patterns of the other blocks. Thereby, an amount of generated codes can be limited but a motion compensated prediction frame coding operation can be performed without degrading the fineness of the texture of the original input picture.