公开(公告)号：EP0794512B1

公开(公告)日：2002-08-28

申请号：EP96830099.6

申请日：1996-03-07

Applicant: STMicroelectronics S.r.l.

Inventor： Mancuso, Massimo ,  Poluzzi, Rinaldo

IPC: G06T5/20 ,  H04N5/21

CPC classification number: H04N5/213 ,  G06T5/20 ,  H04N5/14

公开(公告)号：EP1211636A1

公开(公告)日：2002-06-05

申请号：EP00830782.9

申请日：2000-11-29

Applicant: STMicroelectronics S.r.l.

Inventor： Poluzzi, Rinaldo ,  Mione, Cristoforo ,  Savi, Alberto

IPC: G06N3/04

CPC classification number: G06K9/0051 ,  G06N3/0436

Abstract: The filtering device (80) comprises a neuro-fuzzy filter (1; 80) and implements a moving-average filtering technique in which the weights for final reconstruction of the signal ( oL 3 ( i )) are calculated in a neuro-fuzzy network (3) according to specific fuzzy rules. The fuzzy rules operate on three signal features ( X 1( i ), X 2( i ), X 3( i )) for each input sample ( e ( i )). The signal features are correlated to the position of the sample in the considered sample window, to the difference between a sample and the sample at the center of the window, and to the difference between a sample and the average of the samples in the window. The filter device for the analysis of a voice signal comprises a bank of neuro-fuzzy filters (86, 87). The signal is split into a number of sub-bands, according to wavelet theory, using a bank of analysis filters including a pair of FIR QMFs ( H 0 , H 1 ) and a pair of downsamplers (85, 86); each sub-band signal is filtered by a neuro-fuzzy filter (86, 87), and then the various sub-bands are reconstructed by a bank of synthesis filters including a pair of upsamplers (88, 89), a pair of FIR QMFs ( G 0 , G 1 ), and an adder node (92).

Abstract translation: 过滤装置（80）包括一个神经模糊过滤器（1; 80），并实现移动平均滤波技术，其中用于信号的最终的重建（OL3（i））的权重的神经模糊网络计算（ 3）雅丁具体模糊规则。 模糊规则对三个信号特征（X1（i）中，X2（i）中，X3（i））的每一个输入样本（E（i））的操作。 所述信号特征是相关的，以在所考虑的样品窗口中的样本的位置，到样品，并在该窗口的中心的样本之间的差值，以及在样品和样品中的窗口的平均之间的差。 用于语音信号的分析的过滤器装置包括神经模糊滤波器（86，87）的一组。 的信号被分成多个子频带，gemäß的小波理论，使用分析滤波器包括一对FIR QMFs（H0，H1）的一组和一对向下取样器（85，86）; 每个子带信号由神经模糊滤波器（86，87）过滤，并通过合成滤波器包括一对的银行，则各个子带重构上采样器（88，89），一对FIR QMFs的 （G0，G1），以及加法器节点（92）。

公开(公告)号：EP0626788B1

公开(公告)日：2000-08-30

申请号：EP93830228.8

申请日：1993-05-26

Applicant: STMicroelectronics S.r.l.

Inventor： Scalise, Fabio ,  Poluzzi, Rinaldo

IPC: H04N7/00

CPC classification number: H04N7/0155

公开(公告)号：EP0669598B1

公开(公告)日：1999-10-27

申请号：EP94830092.6

申请日：1994-02-28

Applicant: STMicroelectronics S.r.l.

Inventor： Mancuso, Massimo ,  Poluzzi, Rinaldo ,  Rizzotto, Gianguido

IPC: G06T5/20

CPC classification number: G06T5/20 ,  H03H2222/02

公开(公告)号：EP0927952A1

公开(公告)日：1999-07-07

申请号：EP97830730.4

申请日：1997-12-30

Applicant: STMicroelectronics S.r.l.

Inventor： Colla, Federica ,  Mancuso, Massimo ,  Poluzzi, Rinaldo

IPC: G06T1/00 ,  G06T7/40

CPC classification number: H04N9/643 ,  G06T7/90 ,  H04N1/628

Abstract: A digital image color correction device employing fuzzy logic, for correcting a facial tone image portion of a digital video image, characterized in that it comprises:

a pixel fuzzifier unit (1) receiving in input a stream of pixels belonging to a sequence of correlated frames of a digital video image and computing a multi level value representing a membership of each pixel to a skin color class;
a global parameter estimator (2) receiving in input each of said pixel and the relative membership value, and computing a first and a second parameter which define the characteristics of a portion of said image that belongs to said skin color class;
a processing unit (3) connected downstream to said global parameter estimator and to said pixel fuzzifier unit and adapted to correct each of the pixels of said portion of the image that belongs to said skin color class, according to said first global parameter (300), to obtain corrected pixels; and
a processing switch (4) for outputting said pixels or said corrected pixels according to said second global parameter (400).

Abstract translation: 一种采用模糊逻辑的数字图像颜色校正装置，用于校正数字视频图像的面部色调图像部分，其特征在于，其包括：像素模糊器单元（1），其在输入端接收属于相关帧序列的像素流 并且将表示每个像素的隶属度的多级值计算为肤色等级; 全局参数估计器（2），其中输入每个所述像素和相对隶属值，并且计算定义属于所述肤色类的所述图像的一部分的特征的第一和第二参数; 连接到所述全局参数估计器的下游的处理单元（3）和所述像素模糊器单元，并且适于根据所述第一全局参数（300）来校正属于所述皮肤颜色等级的所述图像的所述部分的每个像素， ，以获得校正像素; 以及用于根据所述第二全局参数（400）输出所述像素或所述校正像素的处理开关（4）。

公开(公告)号：EP0874523A1

公开(公告)日：1998-10-28

申请号：EP97830188.5

申请日：1997-04-24

Applicant: STMicroelectronics S.r.l.

Inventor： Mancuso, Massimo ,  Poluzzi, Rinaldo ,  D'Alto, Viviana ,  Molinari, Luca

IPC: H04N7/01 ,  H04N5/44

CPC classification number: H04N7/0132 ,  H04N5/145 ,  H04N7/014

Abstract: A method and a device for motion estimated and compensated Field Rate Up-conversion (FRU) for video applications, providing for: a) dividing an image field to be interpolated into a plurality of image blocks (IB), each image block made up of a respective set of image elements of the image field to be interpolated; b) for each image block (K(x,y)) of at least a sub-plurality (Q1,Q2) of said plurality of image blocks, considering a group of neighboring image blocks (NB[1]-NB[4]); c) determining an estimated motion vector for said image block (K(x,y)), describing the movement of said image block (K(x,y)) from a previous image field to a following image field between which the image field to be interpolated is comprised, on the basis of predictor motion vectors (P[1]-P[4]) associated to said group of neighboring image blocks; d) determining each image element of said image block (K(x,y)) by interpolation of two corresponding image elements in said previous and following image fields related by said estimated motion vector. Step c) provides for: c1) applying to the image block (K(x,y)) each of said predictor motion vectors to determine a respective pair of corresponding image blocks in said previous and following image fields, respectively; c2) for each of said pairs of corresponding image blocks, evaluating an error function (err[i]) which is the Sum of luminance Absolute Difference (SAD) between corresponding image elements in said pair of corresponding image blocks; c3) for each pair of said predictor motion vectors, evaluating a degree of homogeneity (H(i,j)); c4) for each pair of said predictor motion vectors, applying a fuzzy rule having an activation level (r[k]) which is higher the higher the degree of homogeneity of the pair of predictor motion vectors and the smaller the error functions of the pair of predictor motion vectors; c5) determining an optimum fuzzy rule having the highest activation level (r[opt]), and determining the best predictor motion vector (P[min]) of the pair associated to said optimum fuzzy rule having the smaller error function; c6) determining the estimated motion vector for said image block (K(x,y)) on the basis of said best predictor motion vector (P[min]).

Abstract translation: 一种方法，以及用于运动估计的装置和补偿的场速率向上转换（FRU），用于视频应用，提供了：a）将一个图象场到要插补成图像块IB（多个），每个图像块由的 像场的图像元素的集合respectivement待内插; b）对于每个图像块的（K（X，Y））的至少一个次多个（Q1，图像块的所述多个Q2），考虑一组相邻的图像块（NBÄ1Ü-NBÄ4Ü的）; c）关于对所述图像块（（K X，Y））描述所述图像块从先前图像场的运动（K（X，Y））传送到按照图像场估计的运动矢量确定的采矿其中图像场之间 要被内插包括，关联到所述组的相邻图像块的预测运动向量（PÄ1Ü-PÄ4Ü）的基础上; D）确定的采矿通过在由所述相关所述先前和以下图像场两个相应的图像元素的插值，所述图像块的每个图像元素（K（X，Y））估计的运动矢量。 步骤c）提供：C1）施加到图像块（K（X，Y）），每个所述的预测运动矢量的确定性矿一对分别在前面的说respectivement对应的图像块和图像下列字段的; C2）对于每个所述对相应的图像块，误差函数（errÄiÜ）的评价的所有这是在所述的一对相应的图像块对应的图像元素之间的亮度绝对差（SAD）的总和; C3）对于每对预测的运动矢量的所述，评估的均匀度（H（I，J））; C4）对于每对所述的预测运动矢量的，施加具有在激活电平（乐）所有这是一种模糊规则更高的对预测运动矢量的均匀度和更高的对预测的运动的误差函数较小 矢量; C5）在具有最高活化水平（rÄoptÜ）最佳的模糊规则，和确定性采矿确定性采矿相关联以具有较小的误差函数所述最佳模糊规则对中的最佳预测运动向量（PÄminÜ）; C6）确定性采矿用于所述最佳预测运动向量（PÄminÜ）的基础上，所述图像块（K（X，Y））的估计的运动矢量。