稀疏森林：真彩色直方图快速生成算法

Sparse forest:fast algorithm for the generation of true-color histogram

基于空间数据索引技术,提出了一种新的真彩色图像颜色直方图生成算法,这种算法采用一种新的空间数据结构——稀疏森林,通过将RGB空间中三维颜色(点)投影至(r,g,0)平面进行"降维",将三维空间点索引变成一维数据索引问题,降低了问题的复杂度。进一步,利用B树高度平衡、多分支、低深度、结构紧凑等特点,对一维数据进行索引。理论与实验结果表明,稀疏森林保留了全部颜色空间信息,生成、索引速度快,可以方便地进行点查询和区域查询,并且空间效率比较高。

The generation of color histogram is one of the basic problems in many researches. A novel algo-rithm, sparse forest （SF）, for generation of color histogram is proposed based on spatial data indexing. By projecting colors on the （r, g, 0） plane, the problem of three-dimensional color indexing is reduced to one-dimen- sional indexing, which is performed using B-tree. Though conceptually simple; this data structure is capable of preserving color spatial information and tends to provide excellent computational performance and good space utilization. The analytical and experimental results show that the algorithm compares favorably with the traditional spatial data structures in terms of overall algorithm complexity in the case of color histogram.