| 摘要 |
Data values, such as residual values based on a predictive value, are compressed based on a number of significant digits used to represent the data value that is termed a magnitude level. Data values are grouped, and a highest magnitude level of the magnitude levels associated with each of the data values is associated with each group. The magnitude level is expressible in fewer digits than a value of that magnitude. Further, selecting one magnitude level for each group reduces a number of magnitude levels stored, further reducing the size of the resulting file. Choosing a magnitude level associated with a group of related data values in most cases results in the highest magnitude level being close to the magnitude level for each of the data values it represents, resulting in few bits being wasted in coding the data values.
|
