| 摘要 |
The present invention relates to data processing apparatuses which improve the quality of decoded data, such as an image and sound, more. A decoding section 21 decodes, for example, encoded data obtained by JPEG-encoding an image, and an encoding section 22 encodes first decoded data obtained as a result to output re-encoded data. Further, a decoding section 23 decodes the re-encoded data to obtain second decoded data. A class-classification adaptive processing circuit 24 generates a prediction tap used for a predetermined prediction calculation with tap coefficients obtained by learning, from the first decoded data and the second decoded data, and performs the predetermined prediction calculation by using the prediction tap and the tap coefficients to obtain a prediction value corresponding to master data used as a master in the learning. The present invention can be applied to transfer systems for encoding images and sound to transfer them.
|
