公开(公告)号：US06735609B2

公开(公告)日：2004-05-11

申请号：US09794296

申请日：2001-02-27

申请人： Rajesh Kumar Dixit ,  Takao Terao ,  Hiroshi Sugawara ,  Masami Goseki ,  Kazushi Sato

发明人： Rajesh Kumar Dixit ,  Takao Terao ,  Hiroshi Sugawara ,  Masami Goseki ,  Kazushi Sato

IPC分类号： G06F1714

CPC分类号： G06F17/147 ,  G06T9/007

摘要： An inverse discrete-cosine transform apparatus that is simple in structure and can yet output pixel data items different in resolution. The apparatus comprises eight inverse discrete-cosine transform multipliers 23, ten field, compression, inverse discrete-cosine transform multipliers 22, eight selectors 24, eight selectors 25, eight buffers 26, eight sign multipliers 27, a control section, eight adders 28, and eight buffers 29. The control section controls the selectors 24, selectors 25, buffers 26 and sign multipliers 27 in accordance with whether the input discrete-cosine block has been subjected to field division and where the discrete-cosine coefficients are located in the block. One of the values input to the selectors 24, selectors 25, buffers 26 and sign multipliers 27 is thereby selected. The value selected is output after added with the plus sign or the minus sign. The adders 28 add the values output from the selectors 24, selectors 25, buffers 26 and sign multipliers 27. The buffers 29 store the values output from the adders 28.

摘要翻译： 一种离散余弦变换装置，结构简单，可以输出分辨率不同的像素数据。 该装置包括八个反离散余弦变换乘法器23，十个场，压缩，反离散余弦变换乘法器22，八个选择器24，八个选择器25，八个缓冲器26，八个符号乘法器27，控制部分，八个加法器28， 和八个缓冲器29.控制部分根据输入的离散余弦块是否已经进行了场分割并且其中离散余弦系数位于块中来控制选择器24，选择器25，缓冲器26和符号乘法器27 。 由此选择输入到选择器24，选择器25，缓冲器26和符号乘法器27的值之一。 选择的值在添加加号或减号后输出。 加法器28添加从选择器24，选择器25，缓冲器26和符号乘法器27输出的值。缓冲器29存储从加法器28输出的值。

公开(公告)号：US06721708B1

公开(公告)日：2004-04-13

申请号：US09470445

申请日：1999-12-22

申请人： Yunbiao Wang

发明人： Yunbiao Wang

IPC分类号： G06F1714

CPC分类号： G06F17/147

摘要： The present invention provides a method and apparatus for performing an inverse modified discrete cosine transform (IMDCT) on at least one block of spectral coefficients representing an information signal in the frequency domain. The IMDCT provides an IMDCT output including at least one block of processed samples in the time domain. The new and novel method of the present invention includes converting spectral coefficients in the block of spectral coefficients to provide a block of frequency domain processed complex samples and processing the block of frequency domain processed complex samples into the block of processed samples in the time domain. Further, the converting spectral coefficients into the frequency domain processed complex samples includes regrouping the spectral coefficients into an even data sequence and an odd data sequence of spectral coefficients, and continuing to regroup the even data sequence and odd data sequence of spectral coefficients until each data sequence includes only two spectral coefficients. Butterfly computations are also performed. The performing of the butterfly computations includes performing at least one complex multiplication and at least one complex addition, and limiting the number of complex multiplications of the butterfly computations by a factor of two by calculating a first set of exponential components, &bgr;N/2,n,1, for n=0, 1, . . . , N/8, and setting a second set of exponential components, &bgr;N/2,n+N/8,1, equal to &bgr;N/2,n,1, for n=0, 1, . . . , N/8.

摘要翻译： 本发明提供一种用于在表示频域中的信息信号的至少一个频谱系数块上执行逆修正离散余弦变换（IMDCT）的方法和装置。 IMDCT提供包括时域中至少一个处理样本块的IMDCT输出。 本发明的新颖和新颖的方法包括转换频谱系数块中的频谱系数，以提供频域处理的复杂样本块，并将频域处理的复杂样本块处理到时域中的经处理采样块中。 此外，将频谱系数转换成频域处理的复数样本包括将频谱系数重新分组为偶数数据序列和频谱系数的奇数数据序列，并且继续重新分组频谱系数的偶数据序列和奇数数据序列，直到每个数据 序列仅包括两个光谱系数。 蝴蝶计算也被执行。 蝴蝶计算的执行包括执行至少一个复数乘法和至少一个复数加法，并且通过计算第一组指数分量βN/ 2，n来限制蝴蝶计算的复乘乘数乘以因子2 ，1，对于n = 0,1，。 。 。 ，N / 8，并且对于n = 0,1，而设置第二组指数分量，βN/ 2，n + N / 8,1等于βN/ 2，n，1。 。 。 ，N / 8。

公开(公告)号：US06574648B1

公开(公告)日：2003-06-03

申请号：US09601803

申请日：2000-10-02

申请人： Masahiro Oohashi ,  Tsuyoshi Nakamura

发明人： Masahiro Oohashi ,  Tsuyoshi Nakamura

IPC分类号： G06F1714

CPC分类号： G06F17/147 ,  H04N19/122 ,  H04N19/60

摘要： There is provided a DCT processor for performing at least one of DCT operation and inverse DCT operation for image data in unit blocks having different sizes. This DCT processor is provided with a bit slice circuit (102) for outputting, bit by bit, the pixel data inputted for each column or row; a first butterfly operation circuit (103) for subjecting the output data of the bit slice circuit (102) to butterfly operation; a ROM address generation circuit (104) for generating continuous ROM addresses; an RAC (105) for reading the data corresponding to the ROM addresses from ROMs (ROM0˜ROM7) and accumulating the data by accumulation circuits (51a˜51h); and a second butterfly operation circuit 106 for subjecting the output data of the RAC 105 to butterfly operation.

摘要翻译： 提供了一种用于对具有不同尺寸的单位块中的图像数据进行DCT运算和逆DCT运算中的至少一个的DCT处理器。 该DCT处理器设置有用于逐位输出针对每列或每行输入的像素数据的位片电路（102） 第一蝶形运算电路（103），用于对位片电路（102）的输出数据进行蝶式运算; 用于产生连续ROM地址的ROM地址产生电路（104）; 用于从ROM（ROM0〜ROM7）读取对应于ROM地址的数据并通过累积电路（51a〜51h）累积数据的RAC（105）; 以及用于对RAC 105的输出数据进行蝶形运算的第二蝶形运算电路106。

公开(公告)号：US06529927B1

公开(公告)日：2003-03-04

申请号：US09540115

申请日：2000-03-31

申请人： Mark E. Dunham

发明人： Mark E. Dunham

IPC分类号： G06F1714

CPC分类号： G06F17/141 ,  G06F17/10 ,  G06F17/14

摘要： A method is provided for logarithmic compression, transmission, and expansion of spectral data. A log Gabor transformation is made of incoming time series data to output spectral phase and logarithmic magnitude values. The output phase and logarithmic magnitude values are compressed by selecting only magnitude values above a selected threshold and corresponding phase values to transmit compressed phase and logarithmic magnitude values. A reverse log Gabor transformation is then performed on the transmitted phase and logarithmic magnitude values to output transmitted time series data to a user.

摘要翻译： 提供了一种用于光谱数据的对数压缩，传输和扩展的方法。 对数Gabor变换由输入的时间序列数据组成，以输出光谱相位和对数幅度值。 通过仅选择高于所选阈值的幅度值和相应的相位值来压缩输出相位和对数幅度值，以传输压缩相位和对数幅度值。 然后对传输的相位和对数幅值执行反向对数Gabor变换，以向用户输出传输的时间序列数据。

公开(公告)号：US06366937B1

公开(公告)日：2002-04-02

申请号：US09267899

申请日：1999-03-11

申请人： Avadhani Shridhar ,  Arindam Saha

发明人： Avadhani Shridhar ,  Arindam Saha

IPC分类号： G06F1714

CPC分类号： G06F9/30014 ,  G06F9/30036 ,  G06F17/142

摘要： A system and method that implement a butterfly operation for a fast fourier transform operation in a processor using a matrix-vector-multiply instruction. A first set of inputs to the butterfly operation are defined as r1+j i1 and r2+j i2, and a twiddle factor Wn is defined as Wn=e−j2&pgr;/N=cos(2&pgr;/N)−j sin(2&pgr;/N)=a+jb. The butterfly operation stores r1, i1, r2 and i2 in a first set of registers and stores the twiddle factor in matrix registers. The matrix-vector-multiply instruction is executed between the matrix registers and the first set of registers.

摘要翻译： 一种在使用矩阵向量乘法指令的处理器中实现用于快速傅里叶变换操作的蝶形运算的系统和方法。 蝶形运算的第一组输入被定义为r1 + ji1和r2 + j i2，旋转因子Wn定义为Wn = e-j2pi / N = cos（2pi / N）-jsin（2pi / N）= a + jb。 蝶形运算将r1，i1，r2和i2存储在第一组寄存器中，并将旋转因子存储在矩阵寄存器中。 矩阵向量乘法指令在矩阵寄存器和第一组寄存器之间执行。

公开(公告)号：US06298363B1

公开(公告)日：2001-10-02

申请号：US09191665

申请日：1998-11-13

申请人： Russell J. Iannuzzelli

发明人： Russell J. Iannuzzelli

IPC分类号： G06F1714

CPC分类号： G06F17/141 ,  H03H21/0027

摘要： Adaptive windowing of Fast Fourier Transform (FFT) data to reduce spectral leakage and increase sidelobe rejection. The adaptive windowing is extended to 5 and 7 point convolution formulas. Thus, the present invention extends the non-static shift-variant data adaptive window generated from a spatial variant apodization. The extensions are achieved by using the window structure of multiple cosines. The sidelobe leakage of the adaptive windows is extremely small, the signal-to-noise ration is higher than conventional techniques and spectral detection is possible with higher order windowing.

摘要翻译： 快速傅里叶变换（FFT）数据的自适应窗口化，以减少频谱泄漏并增加旁瓣抑制。 自适应窗口扩展到5和7点卷积公式。 因此，本发明扩展了从空间变体变迹生成的非静态移位变量数据自适应窗口。 扩展通过使用多余余弦的窗口结构来实现。 自适应窗口的旁瓣泄漏极小，信噪比高于常规技​​术，并且可以通过高阶窗口进行光谱检测。

公开(公告)号：US06282555B1

公开(公告)日：2001-08-28

申请号：US09237856

申请日：1999-01-27

申请人： Kazutake Ohara

发明人： Kazutake Ohara

IPC分类号： G06F1714

CPC分类号： G06F17/14

摘要： A two-dimensional discrete cosine transform processor (two-dimensional DCT processor) includes two one-dimensional DCT circuits and a transposition memory interposed therebetween. Each of the two one-dimensional DCT circuits includes a butterfly operation circuit and a distributed arithmetic circuit at the subsequent level. Partial sums of vector inner products based on a constant matrix obtained by multiplying respective elements of a discrete cosine matrix by frequency-depending weighting according to human visual sense are stored in ROMs included in the distributed arithmetic circuit, and the contents of the ROMs are used to obtain a one-dimensional DCT result with weighting given. In this manner, arbitrary weighting can be given to the transform result without using a multiplier. Thus, for example, in a compressing and coding system for image data, the compression efficiency can be improved as compared with the case where weighting is not given to the transform result.

摘要翻译： 二维离散余弦变换处理器（二维DCT处理器）包括两个一维DCT电路和置于其间的置换存储器。 两个一维DCT电路中的每一个包括蝶形运算电路和后续级别的分布式运算电路。 基于通过将离散余弦矩阵的各个元素乘以根据人类视觉的频率依赖加权而获得的常数矩阵的矢量内积的部分积被存储在分布式运算电路中包括的ROM中，并且使用ROM的内容 以获得给定权重的一维DCT结果。 以这种方式，可以不使用乘数来赋予变换结果任意加权。 因此，例如，在图像数据的压缩编码系统中，与不对变换结果进行加权的情况相比，可以提高压缩效率。

公开(公告)号：US06230177B1

公开(公告)日：2001-05-08

申请号：US09096538

申请日：1998-06-12

申请人： Carroll Philip Gossett ,  Nancy Cam Winget ,  Chien-Ping Lu

发明人： Carroll Philip Gossett ,  Nancy Cam Winget ,  Chien-Ping Lu

IPC分类号： G06F1714

CPC分类号： G06F17/142

摘要： The method and apparatus employ a texture filter in a graphics processor to perform a transform such as, for example, a Fast Fourier Transform. The texturizer can include an array of linear interpolators. The architecture reduces the computational complexity of the transform processes.

摘要翻译： 该方法和装置在图形处理器中采用纹理滤波器来执行诸如快速傅里叶变换的变换。 纹理化器可以包括线性内插器阵列。 该架构降低了转换过程的计算复杂度。

公开(公告)号：US06820104B2

公开(公告)日：2004-11-16

申请号：US09878784

申请日：2001-06-11

申请人： Walter Eugene Pelton ,  Adrian Stoica

发明人： Walter Eugene Pelton ,  Adrian Stoica

IPC分类号： G06F1714

CPC分类号： G06F17/141 ,  G06F17/147

摘要： Apparatus, methods, and computer program products are provided for generating a second set of equations requiring reduced numbers of computations from a first set of general equations, wherein each general equation defines coefficients in terms of a set of samples and a plurality of functions having respective values. A first set of tokens is initially assigned to the plurality of functions such that every value of the functions that has a different magnitude is assigned a different token, thereby permitting each general equation to be defined by the set of samples and their associated tokens. Each general equation is then evaluated and the samples having the same associated token are grouped together. A second set of tokens is then assigned to represent a plurality of unique combinations of the samples. The second set of equations is then generated based at least on the first and second sets of tokens.

摘要翻译： 提供了装置，方法和计算机程序产品，用于从第一组通用方程式产生需要减少计算次数的第二组方程，其中每个通用方程式根据一组样本和具有相应的多个函数来定义系数 价值观。 第一组令牌最初被分配给多个功能，使得具有不同大小的功能的每个值被分配不同的令牌，由此允许由样本集合及其相关联的令牌来定义每个通用方程式。 然后评估每个一般等式，并将具有相同关联令牌的样本分组在一起。 然后分配第二组令牌以表示样本的多个唯一组合。 然后至少基于第一组和第二组令牌生成第二组方程式。

公开(公告)号：US06792441B2

公开(公告)日：2004-09-14

申请号：US09803374

申请日：2001-03-10

申请人： Marwan A Jaber

发明人： Marwan A Jaber

IPC分类号： G06F1714

CPC分类号： G06F17/141 ,  G06F17/142

摘要： The discrete Fourier transform (DFT) is computed in a plurality of parallel processors. A DFT of length N is divided into r partial DFTs of length (N/r), in which the r partial DFTs are calculated in separate parallel processors and then combined in a combination phase to form a complete DFT of length (N). The r partial FFTs are able to be computed in parallel multiprocessors by defining the mathematical model of the combination phase in such manner so as to allow the r parallel processors to operate independently and simultaneously. A second embodiment presents a radix-r fast Fourier algorithm that reduces the computational effort as measured by the number of multiplications and permits the N/r parallel processors to operate simultaneously and with a single instruction sequence.

摘要翻译： 在多个并行处理器中计算离散傅里叶变换（DFT）。 长度为N的DFT被分成长度为（N / r）的r个部分DFT，其中在单独的并行处理器中计算r个部分DFT，然后在组合阶段中组合以形成长度（N）的完整DFT。 通过以这样的方式定义组合阶段的数学模型，可以在并行多处理器中计算r个部分FFT，以便允许r个并行处理器独立和同时运行。 第二个实施例提供了一个radix-r快速傅里叶算法，其降低了乘法次数所测量的计算量，并允许N / r个并行处理器同时进行并且以单个指令序列进行操作。