Abstract: An acquisition unit acquires image data resulting from reading an image printed sequentially in a first direction. A setting unit sets a division size in the first direction and a second direction of a division area for dividing the image data, the second direction crossing the first direction, as well as a shift amount in the first direction and the second direction of the division area. A processing unit performs a predetermined process including an averaging process on the image data in accordance with the division size and the shift amount. An extraction unit extracts a unique portion from image data on which the predetermined process has been performed. The setting unit sets (i) the division size greater in the second direction than in the first direction, and/or (ii) the shift amount greater in the second direction than in the first direction.

Abstract: Parameters are set according to features of a unique portion appearing in a print image, ensuring that the unique portion can be efficiently determined in the print image. In order to do so, information about a form of appearance of the unique portion in the print image is acquired, and the parameters are set in accordance with the form of the appearance.

Abstract: By setting a parameter in accordance with features of a unique portion appearing in a print image, the unique portion in the print image is efficiently determined. The image is printed on a sheet along with a relative movement in a main scanning direction of the sheet and a print head on which multiple printing elements are arrayed in a sub-scanning direction. One division area is set such that a size in the main scanning direction is greater than a size in the sub-scanning direction. A shift amount from one division area to another division area is set such that a shift amount in the main scanning direction greater than a shift amount in the sub-scanning direction.

Abstract: An image processing apparatus sets a predetermined reading resolution for acquiring image data and a division size for performing a predetermined process on the image data and extract a unique portion from image data resulting from performing the predetermined process. The predetermined process includes an averaging process on the image data for each of division areas obtained by dividing the image data by the predetermined division size, a quantization process for quantizing values obtained by the averaging process, and an addition process for adding values obtained by the quantization process, that are different in the dividing way of the image data in the averaging process. The setting unit sets the predetermined reading resolution so as to make the width of the unique portion in the image correspond to N read pixels (N?2), and sets the division size so as to have a width larger than N pixels.

Abstract: A shake detection sensor detects the shaking of an imaging device attached to a telescopic pole. An extraction filter selector selects any extraction filter from a plurality of extraction filters, and extracts a signal component of a predetermined frequency band in a detection signal, which is outputted from the shake detection sensor, by the selected extraction filter. A shake corrector corrects the shaking of video captured by the imaging device, based on the signal component outputted from the extraction filter selector. An extraction filter selection controller controls the extraction filter selector to select any extraction filter among the plurality of extraction filters in response to the length of the pole.

Abstract: An image processing apparatus accurately determines the inclination of an original even in the case where an original of a white sheet is read with a white sheet as a background. For this, the image processing apparatus extracts a fiber section having a feature of paper fiber from image data, analyzes a direction of fiber in the fiber section, and calculates the inclination of an original at the time of reading the original based on the direction.

Abstract: Based on information corresponding to the degree of compression of image data compressed in a lossy compression method, a parameter to be used when error diffusion processing is performed on the image data is determined.

Abstract: The number of gradation levels to be obtained after lossy-compressed data corresponding to a predetermined number of gradation levels is expanded and gradation conversion is performed is determined in such a manner that the number of gradation levels is determined to be a first number of gradation levels in a case where the degree of compression when the data to be processed is compressed in lossy compression is more than a first threshold value, and the number of gradation levels is determined to be a second number of gradation levels in a case where the degree of compression is less than or equal to the first threshold value, the first number of gradation levels being smaller than the second number of gradation levels.

Abstract: A method includes a state determination step of determining the quality of an object in image data, an extraction step of extracting feature information from the object, and a registration step of registering, in a dictionary, the feature information extracted in the extraction step. In the registration step, when the quality of the object determined in the determination step is lower than a predetermined reference, registration of the feature information of the object in the dictionary by the registration step is not performed.

Abstract: This invention provides a technique which can enhance personal recognition precision in personal recognition processing of a face in an image. To this end, a management unit classifies feature patterns each including feature information of a plurality of parts of a face region of an object extracted from image data, and manages the feature patterns using a dictionary. A segmenting unit determines whether or not feature information of each part of the face region of the object is segmented, and segments the feature information of the part of interest into a plurality of feature information as new feature information. A registration unit registers a feature pattern as a combination of the new feature information of the part of interest and feature information of parts other than the part of interest in the dictionary as a new feature pattern of the object.

Abstract: Information corresponding to the degree of compression of lossy-compressed image data to be printed is acquired. Furthermore, based on the acquired information, a providing method of a recording agent when the image data to be printed is expanded and an image based on the expanded image data is printed, is determined.

Abstract: Because the spectral characteristics of an original of a printing sheet and those of an original of a photographic image are different, in the case where the same color conversion table is applied at the time of color conversion processing, a deviation occurs in color reproducibility. By determining the sheet type with accuracy based on the feature of fiber that occurs in manufacture of paper and by applying color conversion processing in accordance with the determination result, a highly accurate color reproduction method of an image is implemented.

Abstract: An image processing apparatus comprises, a management unit configured to classify a face feature information of a face region of an object extracted from image data into a predetermined category in accordance with a similarity determination, and manage the face feature information in a dictionary, a condition setting unit configured to set category determination conditions for classifying the face feature information into the category in accordance with individual information representing at least one of an age and sex of the object and a determination unit configured to determine, based on the category determination conditions set by the condition setting unit, a category to which the face feature information belongs in the dictionary.

Abstract: The present invention provides an apparatus for processing image data obtained by reading a document and a background image outside the document, and method of controlling the apparatus. The apparatus determines a degree of similarity between a color of the background image and a color of a marginal region of the document from the image data, sets a region extraction parameter based on the determined degree of similarity, and determines a document region by using the region extraction parameter from the image data.

Abstract: An image processing apparatus executes color conversion so that when printing is performed based on image data compressed and decompressed with a lossy compression method, the image data reproduces expected colors of the image data before compression. More specifically, a range of a signal value of a black image affected by compression of image data, such as black character to be printed with black ink, is obtained, and a color separation table is generated such that color ink is not used but black ink is used within this range. This allows the image data to reproduce expected colors of the image data before compression when printing is performed based on the image data compressed and decompressed with a lossy compression method.

Abstract: An image processing apparatus includes an image data acquisition unit to acquire image data by optically reading a document. A frequency distribution acquisition unit acquires a first frequency distribution of luminances from the image data acquired by the image data acquisition unit. A generation unit generates a second frequency distribution of luminances of a background of the document, by using a maximum frequency of the first frequency distribution as a maximum frequency of the second frequency distribution of luminances of the background of the document. An acquisition unit acquires information indicating a degree of deviation of the second frequency distribution from the first frequency distribution. A correction unit corrects the second frequency distribution based on the information indicating the degree of deviation acquired by the acquisition unit.

Abstract: Based on information corresponding to the degree of compression of image data compressed in a lossy compression method, a parameter to be used when error diffusion processing is performed on the image data is determined.

Abstract: The number of gradation levels to be obtained after lossy-compressed data corresponding to a predetermined number of gradation levels is expanded and gradation conversion is performed is determined in such a manner that the number of gradation levels is determined to be a first number of gradation levels in a case where the degree of compression when the data to be processed is compressed in lossy compression is more than a first threshold value, and the number of gradation levels is determined to be a second number of gradation levels in a case where the degree of compression is less than or equal to the first threshold value, the first number of gradation levels being smaller than the second number of gradation levels.

Abstract: Information corresponding to the degree of compression of lossy-compressed image data to be printed is acquired. Furthermore, based on the acquired information, a providing method of a recording agent when the image data to be printed is expanded and an image based on the expanded image data is printed, is determined.

Abstract: Because the spectral characteristics of an original of a printing sheet and those of an original of a photographic image are different, in the case where the same color conversion table is applied at the time of color conversion processing, a deviation occurs in color reproducibility. By determining a sheet type with accuracy based on the feature of fiber that occurs in manufacture of paper and by applying color conversion processing in accordance with the determination result, a highly accurate color reproduction method of an image is implemented.