公开(公告)号：EP1087533A1

公开(公告)日：2001-03-28

申请号：EP99913695.5

申请日：1999-04-19

申请人： Ohmi, Tadahiro ,  Ultraclean Technology Research Institute, Co. Ltd

发明人： OHMI, Tadahiro ,  KOTANI, Koji ,  NAKADA, Akira ,  IMAI, Makoto ,  KONDA, Masahiro ,  MORIMOTO, Tatsuo ,  YONEZAWA, Takemi ,  NOZAWA, Toshiyuki ,  NAKAYAMA, Takahiro ,  FUJIBAYASHI, Masanori ,  NITTA, Takahisa,

IPC分类号： H03M7/30 ,  H04N1/41 ,  H04N7/28

CPC分类号： H04N19/94 ,  G06T9/008 ,  H03M7/3082

摘要： With reference to one or more pieces of data (for example, the data at the left end in a block of 4 × 4 pixels) in a data string constituting one code vector in a code book, a code vector is generated by giving a value which increases in an increment of a predetermined value from the reference data value K to each piece of the other data in the block. A greatly versatile code book can be made at least for data on a pattern, for example, a face image, whose data value gradually varies by a small change.

摘要翻译： 与在构成码本中的一个码矢量数据串参照数据的一条或多条（例如，该数据在4×4像素的块的左端），通过给一个值所生成的代码矢量 这增加了在从基准数据值K到块中的每个块的其它数据的预定值的增量。 甲大大多功能码本可以至少进行用于数据上的图案，例如，面部图像，谁的dataValue逐步由一个小型变化而变化。

公开(公告)号：EP1079635A1

公开(公告)日：2001-02-28

申请号：EP99914764.8

申请日：1999-04-19

申请人： Ultraclean Technology Research Institute, Co. Ltd ,  Ohmi, Tadahiro

发明人： OHMI, Tadahiro ,  KOTANI, Koji ,  NAKADA, Akira ,  IMAI, Makoto, Tohoku University ,  KONDA, Masahiro, Tohoku University ,  MORIMOTO, Tatsuo, Tohoku University ,  YONEZAWA, Takemi, Tohoku University ,  NOZAWA, Toshiyuki, Tohoku University ,  NAKAYAMA, Takahiro, Tohoku University ,  FUJIBAYASHI, Masanori, Tohoku University ,  NITTA, Takahisa, Ultraclean Tech. Res. Inst.Co.Ltd

IPC分类号： H04N7/28 ,  H03M7/30

CPC分类号： G06T9/008 ,  H03M7/3082 ,  H04N19/503 ,  H04N19/94

摘要： A correlation ratio calculation section (36) quantizes the vectors of each frame of a moving picture by using a space direction code book. A space direction code book reconstruction calculating section (39) rearranges obtained code string to generate new vectors. The correlation ratio calculation section (36) quantizes the new vectors by using a time-axis code book. In such a way, not only vector quantization in the space direction is performed for each frame image, but also vector quantization in the time-axis direction is performed between frames along the time axis.

摘要翻译： 的相关性比计算部（36），通过使用空间方向的码本量化的运动画面的每帧的矢量。 的空间方向的码本重构计算部（39）重新排列获得的代码串，以产生新向量。 的相关性比计算部分（36）通过使用时间轴码本量化新载体。 在寻求一种方法，在空间方向上不仅矢量量化执行用于每个帧图像的，所以在时间轴方向矢量量化沿时间轴帧，但之间执行。

公开(公告)号：EP1118954A1

公开(公告)日：2001-07-25

申请号：EP99913706.0

申请日：1999-04-19

申请人： Kabushiki Kaisha Ultraclean Technology Research Institute ,  Shibata, Tadashi ,  Ohmi, Tadahiro

发明人： SHIBATA, Tadashi ,  OHMI, Tadahiro ,  NAKADA, Akira ,  MORIMOTO, Tatsuro ,  NITTA, Takahisa, K. K. Ultraclean Tech. Res. Ins.

IPC分类号： G06G7/12

CPC分类号： G06N3/063 ,  G06N3/0635

摘要： It is an object of the present invention to provide a semiconductor arithmetic unit which realizes a maximum or minimum value retrieval operation at high speed and with a high degree of accuracy used in a vector quantization processor composed of a binary-multivalue-analog merged operation processing circuit. In addition, it is another object to add a function for retrieving a vector with a distance of necessary order to the unit.
The present invention is characterized in that, in a multi-loop circuit comprising an amplifying circuit group composed of a plurality of sets of first amplifiers with a floating gate to which first electrodes and a single second electrode are capacitively coupled with a predetermined ratio, a logical operation circuit to which output signals of the amplifying circuit group are inputted and which outputs a logical 0 or 1, and a second amplifying circuit to which an output signal of the logical operation circuit is inputted and whose output is distributed to all of the second electrodes of the amplifying circuit group, the second amplifying circuit includes an adjusting circuit which adjusts an output current driving ability and a controlling circuit which controls the adjustment with a predetermined regulation, and the adjustment of the controlling circuit is executed according to variation of the output of the logical operation circuit.

摘要翻译： 本发明的目的是提供一种半导体运算单元，该半导体运算单元在由二进制多值模拟合并运算处理器构成的矢量量化处理器中以高速度和高精度地实现最大值或最小值检索操作 电路。 此外，另一个目的是添加用于检索具有必要顺序距离的向量到该单元的函数。 本发明的特征在于，在包括由具有浮置栅极的多组第一放大器组成的放大电路组的多回路电路中，第一电极和单个第二电极以预定比率电容耦合， 输入放大电路组的输出信号并输出​​逻辑0或1的逻辑运算电路，输入逻辑运算电路的输出信号的第2放大电路，其输出分配给第2 放大电路组的电极，第二放大电路包括调节输出电流驱动能力的调节电路和控制电路，控制电路以预定的调节进行调节，并且根据输出的变化执行控制电路的调整 的逻辑运算电路。