公开(公告)号：US20020041711A1

公开(公告)日：2002-04-11

申请号：US09933073

申请日：2001-08-21

申请人： KDDI R&D LABORATORIES, INC.

发明人： Ryoichi Kawada ,  Atsushi Koike ,  Shuichi Matsumoto

IPC分类号： G06K009/34 ,  G06K009/46 ,  G06K009/36

CPC分类号： H04N19/85 ,  H04N19/537

摘要： A shape entropy, a motion vector entropy, and a texture entropy of a certain area i of an input image are derived by a shape entropy calculation section, a motion vector entropy calculation section, and a texture entropy calculation section, respectively. Among them, the texture entropy is derived by taking an allowed value n of encoding degradation given according to a limit (encoding rate) of an entropy which can transmitted into consideration. Therefore, a generated entropy obtained by adding up the shape entropy, the motion vector entropy, and the texture entropy becomes a value according to the encoding rate. In such optimizing segmentation encoding as to minimize the generated entropy, therefore, it becomes possible to conduct segmentation according to the encoding rate. According to the present invention, there is provided an image segmentation apparatus capable of conducting such optimizing segmentation as to minimize the generated entropy while taking the limit (encoding rate) of the entropy which can be transmitted into consideration.

摘要翻译： 输入图像的特定区域i的形状熵，运动矢量熵和纹理熵分别由形状熵计算部分，运动矢量熵计算部分和纹理熵计算部分导出。 其中，通过考虑根据可以传输的熵的限制（编码率）给出的编码劣化的允许值n来导出纹理熵。 因此，通过将形状熵，运动矢量熵和纹理熵相加而获得的生成熵变为根据编码率的值。 因此，在使生成的熵最小化的优化分割编码中，可以根据编码率进行分割。 根据本发明，提供了一种图像分割装置，其能够进行这样的优化分割，以使所产生的熵最小化，同时考虑可以传输的熵的极限（编码率）。