基于HEVC屏幕图像编码的哈希表的优化算法

Optimization algorithm on hash table based on HEVC screen content coding

仿2维匹配算法对屏幕图像中的非连续色调区域有很好的压缩性能,但该算法中哈希表的空间开销较大,不利于硬件实现。为了减小哈希表的空间,通过对原算法优化提出了一种3字节计算哈希值方法,将源数据看作是一个由以YUV三元组为元素组成的数据集合,然后以YUV三元组为单位计算哈希值,这样不但减少了哈希值的计算量,而且使哈希表的存储空间得到很大的节省。实验结果表明,3字节计算哈希值方法使哈希表的存储空间减少为原算法的1/3,所测试屏幕图像的BD-rate性能也有所提高。

The preudo 2-D matching algorithm has good compression performance for the discontinuous-tone content of screen content. However, the large space overhead of the hash table is not conductive to realize the hardware in this algo-rithm. This paper proposes a 3-byte hash value method to reduce the space of the hash table for optimizing the original method. The source data is treated as the data set composed of elements for YUV triples. Then the hash value of YUV triple is calculated as a unit. It not only can reduce the amount of computation of the hash values, but also can minimize the space overhead of the hash table. The experimental results show that the 3-byte hash value method makes the storage space of the hash table reduce to one-third of the original. And the BD-rate performance of some test screen images is also improved.