为解决现有的图像并行细化算法在串行机上的高效实现问题，首先提出了一种 4× 4邻域二值图像的双字节图像编码方案，由于在该方案中将每个 4× 4邻域的像素用一个双字节的整数来表示，从而将基于整个邻域 16个像素的细化处理转化为一个双字节整数的读、写和比较运算的问题;然后在此基础上提出了一种可在串行机上实现的并行细化算法。实验证明，该算法适用于当前通用的各种基于模板匹配的并行细化算法，其不仅可以取得完全相同的细化结果，而且可以大幅度提高图像细化过程在串行机上的执行速度;最后简要讨论了该算法利用 PC机中的 MMX技术来进一步提高并行粒度和运算效率方面所具有的潜力

In order to improve the computation efficiency of image parallel thinning algorithms implemented on serial computers, this paper proposes a coding scheme for each 44 binary pixels, representing the 44 pixels with a double-byte integer, based on which an effective parallel thinning algorithm for serial computers is presented that transforms the 16-pixel based thinning processing into reading, writing and comparison operations of a double-byte integer. By use of this algorithm, the 16 pixels can be processed simultaneously in the thinning operations with serial computers. Computation complexity analysis of the new algorithm is made in the paper that shows about 70% saving in computations compared with the existing parallel template thinning algorithms (e.g., the OPTA algorithm). The algorithm is suitable for all kinds of parallel template thinning algorithms operated on commonly used personal computers, and can significantly improve the computation efficiency of the algorithm with the same thinning results. The potential advantage of the algorithm is also discussed in the paper for using the MMX (or SSE) technology integrated in PCs to further increase the parallel granularity and speed up the thinning processing.