-
Patent Agency Ranking
公开(公告)号：JP2001195592A
公开(公告)日：2001-07-19
申请号：JP2000350169
申请日：2000-11-16
Applicant: ST MICROELECTRONICS SRL
Inventor： DE PONTI MAURO , SCHETTINI RAIMONDO , BRAMBILLA CARLA , VALSASNA ANNA , CIOCCA GIANLUIGI
IPC: G06T7/00
Abstract: PROBLEM TO BE SOLVED: To provide a digital image sorting method by contents, by which the complexity of calculation required for analyzing the image of a large number of pixels is avoided. SOLUTION: The set of N pieces of low level features for describing the semantic contents of the image composed of a quantity provided from the image is defined while using a known logical and mathematical expression (step 10), and the image of a sorting target is indexed (20) for extracting a feature vector formed from the values of these N low level features. Next, a feature space (vector space) specified by N selected features is divided into the finite number of areas (30). Each of these divided areas is the locus of a point in the relevant feature space, where the value of at least one component of the feature vector satisfies a prescribed relation with each of thresholds. A sorting area including the feature vector is identified (40) from the area dividing such a feature space and an image class made correspond thereto is identified (50).
-
公开(公告)号：JPH11225334A
公开(公告)日：1999-08-17
申请号：JP32157498
申请日：1998-11-12
Applicant: ST MICROELECTRONICS SRL
Inventor： PAU DANILO , ROVATI FABRIZIO , VALSASNA ANNA , BRUNI ROBERTA
Abstract: PROBLEM TO BE SOLVED: To obtain a device which calculates the dispersion value of a macroblock of a digital video by outputting the square value of an image that is continuously inputted, inputting each pixel of the macroblock, counting up, resetting a counter simultaneously with the input of a final pixel, transmitting the pixel value and square value of a pixel to an accumulator and storing accumulative result value of the accumulator. SOLUTION: For an algorithm that is executed by an accelerator for dispersion value calculation, a simple counter LC is used and two demultiplexers transmit an input line which processes in a method such as decides to which dispersion value a prescribed input pixel belongs to eight separate dispersion value operation paths. Relating to a prescribed line pattern in which a macroblock is scanned, as a rule, the bit of the counter LC that drives multiplexers is selected so that a dispersion value can be accurately operated. The counter LC is reset at the time of starting each macroblock and is counted up by the input of each pixel.
-
公开(公告)号：IT1311443B1
公开(公告)日：2002-03-12
申请号：ITTO990996
申请日：1999-11-16
Applicant: ST MICROELECTRONICS SRL
Inventor： DE PONTI MAURO , SCHETTINI RAIMONDO , BRAMBILLA CARLA , VALSASNA ANNA , CIOCCA GIANLUIGI
Abstract: The classification method involves the following steps: defining a set of low-level features describing the semantic content of the image, said features being quantities obtainable from the image by means of logico-mathematical expressions that are known beforehand, and the choice of said features depending upon the image classes used for the classification; indexing an image to be classified, with the purpose of extracting therefrom a feature vector, the components of which consist of the values assumed, in the image, by said low-level features; splitting the feature space defined by the low-level features into a plurality of classification regions, to each one of said regions there being associated a respective image class, and each classification region being the locus of the points of the feature space defined by a finite set of conditions laid on at least one component of the feature vector; associating the feature vector to the feature space; identifying, among the classification regions, a specific classification region containing the feature vector extracted from the image to be classified; and identifying the image class associated to the specific classification region identified.
-
公开(公告)号：ITTO990996A1
公开(公告)日：2001-05-16
申请号：ITTO990996
申请日：1999-11-16
Applicant: ST MICROELECTRONICS SRL
Inventor： DE PONTI MAURO , SCHETTINI RAIMONDO , BRAMBILLA CARLA , VALSASNA ANNA , CIOCCA GIANLUIGI
Abstract: The classification method involves the following steps: defining a set of low-level features describing the semantic content of the image, said features being quantities obtainable from the image by means of logico-mathematical expressions that are known beforehand, and the choice of said features depending upon the image classes used for the classification; indexing an image to be classified, with the purpose of extracting therefrom a feature vector, the components of which consist of the values assumed, in the image, by said low-level features; splitting the feature space defined by the low-level features into a plurality of classification regions, to each one of said regions there being associated a respective image class, and each classification region being the locus of the points of the feature space defined by a finite set of conditions laid on at least one component of the feature vector; associating the feature vector to the feature space; identifying, among the classification regions, a specific classification region containing the feature vector extracted from the image to be classified; and identifying the image class associated to the specific classification region identified.
-
公开(公告)号：ITTO990996D0
公开(公告)日：1999-11-16
申请号：ITTO990996
申请日：1999-11-16
Applicant: ST MICROELECTRONICS SRL
Inventor： DE PONTI MAURO , SCHETTINI RAIMONDO , BRAMBILLA CARLA , VALSASNA ANNA , CIOCCA GIANLUIGI
Abstract: The classification method involves the following steps: defining a set of low-level features describing the semantic content of the image, said features being quantities obtainable from the image by means of logico-mathematical expressions that are known beforehand, and the choice of said features depending upon the image classes used for the classification; indexing an image to be classified, with the purpose of extracting therefrom a feature vector, the components of which consist of the values assumed, in the image, by said low-level features; splitting the feature space defined by the low-level features into a plurality of classification regions, to each one of said regions there being associated a respective image class, and each classification region being the locus of the points of the feature space defined by a finite set of conditions laid on at least one component of the feature vector; associating the feature vector to the feature space; identifying, among the classification regions, a specific classification region containing the feature vector extracted from the image to be classified; and identifying the image class associated to the specific classification region identified.
-
-
-
-
Search Results
5
records
(took 0.023 seconds)
