Abstract: Disclosed is a method and an apparatus for dithering a pixel value in a image. The method includes checking a difference in chrominance signals between a particular pixel and a pixel adjacent to the particular pixel, in an input image, designating the particular pixel as being in a flat or a non-flat area in consideration of the difference in chrominance signals and dithering the particular pixel when the pixel is designated as being in the non-flat area.

Abstract: A method and a printing implementing the method for dynamic printer performance tuning. The method includes the steps of processing a page to be printed by a printer description language interpreter to generate a Display List, selecting tuning parameters from the Display List data, analyzing the tuning parameters by a Bayesian analyzer to obtain a score for each tuning parameter, and based on the score of each tuning parameter, adjusting rendering settings of the tuning parameters for printing the page. The steps of training the Bayesian analyzer includes creating a set of training pages, rendering each page to determine best performance settings for each tuning parameter, grouping the pages based on tuning parameter settings, generating Display List data of each page, rendering the training pages in each group to compile training data that are saved for future printing jobs.

Abstract: A method for using a processor to process image data received from an image data source in preparation for multipass printing, comprising multitoning the image data to produce a multitoned image, using the multitone level of a pixel in the multitoned image to select a plane of a print mask, using the location of the pixel in the multitoned image to select a cell of output pixels in the selected plane of the print mask, and copying the selected cell of output pixels to corresponding locations within a print buffer.

Abstract: A method is disclosed for screening color separations of a lenticular image with a lenticular frequency of the lenticular lenses needed for viewing the lenticular image. An amplitude-modulated halftone image is calculated for each of the color separations at a screen angle and at a screen frequency, the tangent of the screen angle being a rational number. For a specific color separation, a screen angle relating to the direction perpendicular to the image strips of the lenticular image is defined, a pair of whole numbers whose ratio is equal to the tangent of the screen angle is determined, and the screen frequency of the color separation is calculated as the product of the lenticular frequency and the square root of the sum of the squares of the two whole numbers.

Abstract: A color image forming apparatus is provided that forms an image by correcting registration shifts during an image forming process by using image data and which prevents toner from being blown away and scattered during a fixing process by thinning pixels without making an erroneous decision. When multivalued color image is binarized, the threshold is corrected by using information on grayscale level correction. Further, when trailing phenomenon prevention operation is performed on the binarized image data, the patterns to be used for pattern matching are changed and selected according to whether the subscan direction line shifting point lies within the reference window.

Abstract: A printing system is disclosed. The printing system includes an image processor to rasterize a received print job and to perform a halftone by comparing a first threshold value from a threshold matrix to a first image component sample, comparing the first threshold value to a first number of sequential image component samples neighboring the first sample if the first threshold value is less than the first sample and comparing the first threshold value to a second number of sequential image component samples neighboring the first sample if the first threshold value is greater than or equal to the first sample.

Abstract: Aspects of the present invention relate to creation, modification and implementation of dither pattern structures applied to an image to diminish contouring artifacts. Some aspects relate to dither pattern structures with pixel values in a first color channel pattern that are spatially dispersed from pixel values in a corresponding pattern in a second color channel. Some aspects relate to application. Some aspects relate to systems and apparatus for creation and application of these dither pattern structures comprising pixel values dispersed across color channels.

Abstract: The present invention is directed to a system and method for halftone screening. A system for halftone screening includes means adapted to receive image data having a number of tonal levels representative of a continuous tone image. The system further includes a memory including a LUT having a number of alternative halftone cell arrangements for each tonal level. Each cell of the LUT consists of a number of device dots describing a particular gray value. For each gray value, there are several alternative cells with different arrangements of the same number of device dots. The LUT is configured with the cells of different arrangements in rows. The rows increase in the number of device dots; hence, each column describes halftone cells of increasing tonal values. The system then communicates the image data having a tonal level to the LUT, and randomly selects a halftone cell arrangement to generate a halftone output.

Abstract: An ink jet printing apparatus which inhibits possible bleeding by thinning color data adjacent to black data and enables printing free from image quality degradation such as gradation skip is provided. Specifically, when only one pixel has color data and pixels located vertically and horizontally adjacent to that pixel have no color data, an isolated point pixel containing a color dot is detected only in that pixel. Then, the dots other than the isolated point are thinned-out. This makes it possible to inhibit possible bleeding at the boundary between a color area and a black area and to achieve proper printing with the appropriate gradation of the entire image maintained.

Abstract: An image forming method is disclosed in which an image is formed on commercial printing paper using a high penetration pigmented ink by performing image processing which makes use of dot patterns corresponding to an output halftone level.

Abstract: When a feeding amount for multi-pass printing is changed, the purpose related to an image quality using a binary data generation pattern can still be attained by, for example, a density pattern method. Specifically, a multi-pass printing mode is identified, and a density pattern selection matrix associated with a cycle of binary data generation is selected in accordance with the selected printing mode. That is, a density pattern selection matrix employed for binary data generation using a density pattern is changed to a size corresponding to the feeding amount designated by the selected printing mode. Thereby, a phenomenon that a unit used for image processing to gain a predetermined purpose related to an image quality does not match a unit area used for a printing operation is avoided, and an image printing purpose using a binary data generation pattern can be appropriately attained.

Abstract: Methods, systems, and apparatus, including computer program products, for reducing artifacts in a color sequential display system. A frame of a digital image is displayed by receiving frame data, determining dither patterns, applying the dither patterns to the data, and displaying the dithered data. Each pixel of a frame of a digital image is displayed by receiving pixel data, grouping the pixel data for the color channels of the image into a plurality of sub-groups of pixel data; and displaying the pixel according to a sequence that separates each pair of sub-groups for a color channel by a sub-group for another color channel. Modified pixel data can be generated by replacing parent bits in the pixel data with corresponding pluralities of divided child bits, where all the child bits for a given parent bit have a divided weight that adds up to the parent bit's weight.

Abstract: The present invention provides an image-forming apparatus capable of reducing the amount of toner at a position at which the trapping is carried out. The apparatus has an image-deformation processing unit where input image data is processed to deform the image shape or the trapping or overprinting is carried out on the respective color plates. The apparatus determines whether or not the trapping should be carried out to the target pixels on the boundary between color plates in the adjacent different objects, determines the color plate having the trap color, obtains the amount of toner of the trap color, determines based on the amount of toner of the trap color and the target pixels whether or not the total amount of toner of the trap exceeds the limit value, and reduces the total amount of toner if the total amount of toner of the trap exceeds the limit value.

Abstract: An image processing system including a lookup table having multi-bit printer output levels and an imaging input level. The imaging input level may be associated with a range of input pixel densities. The system further includes a processor configured to compare the imaging input level with one or more preconfigured threshold output values associated with the printer output levels. The imaging input level may be preferentially weighted to select a printer output level having an increased bit depth.

Abstract: A system and method for reducing the noise induced in a particular section or level of a signal bandwidth. The section is isolated from the rest of the signal data, by rescaling this data to produce a buffer section adjacent the section with little or no data in it. The signal is then transmitted to the output device where all data is the buffer section is considered to be the result of noise, and is mapped back to the predetermined level. The signal data is inversely rescaled to move data back into the buffer section. In this way, more of the data that was input at the predetermined level, will also be at the predetermined level afterwards, thereby correcting noise induced in that level by noise inducing transmission techniques such as JPEG compression.

Abstract: Object image data of a processing object image, which virtually has cells each including a set of M×N pixels, is processed. The cells are arranged in steps and are shifted by Dx pixels and by Dy pixels. An input raster buffer stores (N?1) raster data including pixel values of the processing object image. A data updating circuit updates the raster with inputted pixel values. Cell buffers store M×N pixel values regarding one of the cells. Processing circuits output partial data for the processed image data by ubmining a center of gravity position of gradation values in the one of the cells from the M×N pixel values, A control circuit controls storing pixel values regarding each of cells in k-th step using the raster data inputted and the raster data stored when “k•(N?1)+1”-th raster data is inputted to the data updating circuit.

Abstract: A calibration data creating device includes a reference measured density memory, a dither data memory, a corresponding set density determining unit, a calibration data creating unit, and a calibration data creating unit. The reference measured density memory stores measured densities of reference density patches that are formed by an image-forming unit based on the reference density patch data. The dither data memory stores dither data that has a plurality of dot locations, the dither data having a prescribed threshold at each dot location. The corresponding set density determining unit determines corresponding set densities for the plurality of the reference set densities.

Abstract: Disclosed is a method for controlling the shapes of FM-AM mixed halftone dots on the multi-bit depth imaging apparatus. In the prior art, since the reproduction of the shapes of the dots in various gradations is absolutely based on the theory of random error diffusion and is influenced by the dynamic controlling output mechanism for the multi-bit dots, it is hard to assure the controllability of the shapes of the dots in a certain gradation. Based on the prior art, the dynamic statistic algorithm with adjacent output gray levels is introduced to assure the controllability of the shapes of the dots and solve the problem of random change of the shapes of the dots due to the randomicity of the error diffusion. According to the disclosed method, the features of the multi-bit imaging apparatus can be achieved fully in light of the requirements of the dots on the basis of the original method for multi-bit FM-AM mixed screening using error diffusion based on dual-feedback.

Abstract: Disclosed is a method for processing FM-AM mixed halftone images on a multi-bit depth imaging apparatus, which relates to a method for producing halftone dots in the field of image hard copying. In the prior art, since it is hard to avoid the impact of the error diffusion for the output apparatus to control the mixed dots with multi-bit imaging depth based on the error diffusion, the output of the mixed dots with multi-bit imaging depth cannot satisfy requirements of the apparatus. According to the method of the present invention, the dynamic algorithm for controlling the multi-bit mixed dots is used for screening based on the existing mixed screening process using dual-feedback error diffusion. Furthermore, multi-bit halftone images with high quality and rich gradations can be output by the multi-bit depth imaging apparatus.

Abstract: A liquid ejection device of the invention is constructed to eject a liquid to an ejection object. The liquid ejection device has a dot data generator configured to generate dot data from given image data, where the dot data represents a dot creation state in each pixel set on the ejection object. The liquid ejection device also has a liquid ejector equipped with a nozzle array including multiple nozzles aligned in a specific direction substantially perpendicular to a scanning direction. The liquid ejector makes multiple scans of the nozzle array in the scanning direction in a common printing area according to the generated dot data and ejects the liquid to the ejection object to create dots. The dot data generator has a specific print mode that generates corrective dot data by skipping a virtual dot array created by one scan from a group of dot arrays to be created by the multiple scans of the nozzle array, in order to prevent a potential contact with a dot array to be created by another scan.

Abstract: The image output system of the invention collects a preset number of adjacent pixels to one pixel group to divide a number of pixels constituting an image into multiple pixel groups and specifies a pixel group tone value as a representative tone value of each pixel group. The image output system refers to a conversion table to generate dot number data of each pixel group. The conversion table stores dot number data, which represents number of dots to be created in one pixel group, in relation to a combination of a pixel group classification number allocated to each pixel group and the specified pixel group tone value of the pixel group. The image output system then refers to a priority order of pixels representing potentials of dot creation in respective pixels of one pixel group, determines the positions of dot-on pixels in each pixel group according to the generated dot number data of the pixel group, and actually creates dots according to the determined positions of the dot-on pixels.

Abstract: When a feeding amount for multi-pass printing is changed, the purpose related to an image quality using a binary data generation pattern can still be attained by, for example, a density pattern method. Specifically, a multi-pass printing mode is identified, and a density pattern selection matrix associated with a cycle of binary data generation is selected in accordance with the selected printing mode. That is, a density pattern selection matrix employed for binary data generation using a density pattern is changed to a size corresponding to the feeding amount designated by the selected printing mode. Thereby, a phenomenon that a unit used for image processing to gain a predetermined purpose related to an image quality does not match a unit area used for a printing operation is avoided, and an image printing purpose using a binary data generation pattern can be appropriately attained.

Abstract: The invention relates to printing, to facsimile and publishing techniques, in particular to picture reproducing systems capable to form two optical parameter levels, only. Said invention makes it possible to increase a fine detail reproduction accuracy, in particular, strokes on a screen copy and to more fully use a printing resolution power.

Abstract: A method, apparatus and article of manufacture for modifying printing based upon direct on-the-fly media characteristic parameters is disclosed. The present invention on-the-fly directly measures a media characteristic parameter and performs real-time print modification in response thereto. The measured characteristic parameters include paper texture and composition, as well as adhesion and penetration of print. The modification of print in response to these measured parameters may allow a customer to maintain observed print quality with lower-cost materials. Adjustments may include the addition of coating, hot rolling, or adjustment of toner concentration. Measured parameters may include mottle, paper texture, and bleed through.

Abstract: A dither matrix generator includes: a main-cluster generator that generates at least one main-cluster in a matrix, the matrix including a plurality of cells, the main cluster area including a predetermined number of cells; a sparest searcher that searches a sparest area in the matrix, the sparest area being the area other than the area of main-cluster; a sub-cluster generator that generates at least one sub-cluster area, the sub-cluster area including a smaller number of cells than that of the main-cluster; a dither value allocator that allocates dither values to the plurality of cells of the matrix, the cells in the main-clusters having smaller dither values than those in the sub-cluster areas, the cells in the sub-cluster areas having smaller dither values than those in the areas other than the main-cluster and the sub-cluster areas.

Abstract: A method for processing video data for display on a display device having a plurality of luminous elements comprising: applying a dithering function based on single ones of said luminous elements to at least part of said video data to refine the grey scale portrayal of video pictures of said video data, computing at least one motion vector from said video data, and changing at least one of the phase, amplitude, spatial resolution and temporal resolution of said dithering function in accordance with said at least one motion vector when applying the dithering function to said video data.

Abstract: A method of producing a printed output on a substrate is provided using a drop emitting device which is adapted to emit a plurality of ink quantities in response to a control signal.

Abstract: A halftoning device that converts an input pixel signal of 8 bits per pixel into an output pixel signal of r bits per pixel(r<8), the halftoning device includes: a gradation correction unit that expands the input pixel signal into an expanded pixel signal of n bits per pixel(n>8); a threshold value array storage that stores a threshold value array having a threshold value of 8 bits; and a threshold value expansion unit that expands the threshold value of 8 bits to expanded threshold value of n bits per pixel. A range of the expanded pixel signal output from the gradation correction unit is matched with a range of the expanded threshold value. The output pixel signal is set according to a comparison of the expanded pixel signal with the expanded threshold value corresponding to the threshold value that is selected for each input pixel signal.

Abstract: Multi-valued image data corresponding to a pixel area is divided into the first scanning multi-valued data, first and second scanning common multi-valued data, and second scanning multi-valued data. A quantization processing is executed on each of the multi-valued data to generate first scanning quantized data, first and second scanning common quantized data, and second scanning quantized data. After that, these pieces of quantized data are combined for each scanning to generate first scanning combined quantized data and second scanning combined quantized data. According to this, the amount of pixels where dots are both recorded by performing a scanning by plural times (the amount of overlapping dots) is controlled, and while suppressing the image density variations, the granularity is held to a low level.

Abstract: In an image output control system of the invention, an image processing device makes image data subjected to a preset series of image processing and supplies processed image data to an image output device to output a resulting processed image. The image processing device collects a predetermined number of plural pixels among a large number of pixels constituting the image to one pixel group, specifies number of dots to be created in the pixel group, and outputs dot number data representing the specified number of dots to be created in the pixel group to the image output device. The image output device stores multiple priority orders of pixels for dot formation in each pixel group. The image output device receives the output dot number data, selects one priority order among the stored multiple priority orders, determines position of each dot-on pixel in each pixel group, and actually creates a dot at the determined position of each dot-on pixel, so as to output a resulting image.

Abstract: A disclosed dither matrix is used in halftone processing for converting input image data having M input halftone levels into output image data having N (M>N>2) output halftone levels. In the halftone processing, a concentration type dither matrix is used as the dither matrix when an input halftone level is within a range of input halftone levels corresponding to an output halftone level that is lower than a predetermined threshold level T (N>T>1), and a dispersion type dither matrix is used as the dither matrix when the input halftone level is within a range of input halftone levels corresponding to an output halftone level that is equal to or higher than the predetermined threshold level T.

Abstract: There is provided a dither pattern capable of reducing deterioration in image quality caused due to beading by suppressing the occurrence of grains in printing images using a plurality of color inks. If among threshold dots, for which repulsive force potentials are totalized, a threshold dot Do has the largest total, a change in repulsive force potential is obtained between before and after the movement of dot Do. The threshold dot Do is moved to a dot with the smallest total of repulsive force potentials between before and after its movement. By repeating this process, the total energy of all the three planes can be reduced, achieving a dot distribution, in which the number of low frequency components is reduced and the dots are appropriately dispersed, for superposed dither patterns.

Abstract: Disclosed is an image processing apparatus, comprising: an screen processing unit which shifts a position of a screen cell applied to an input image in at least one direction of a main scanning direction and a sub scanning direction of the input image by a first shift amount which changes according to the applied position of the screen cell, when screen processing is performed to the input image by using the screen cell.

Abstract: This invention provides a method of generating a dither matrix that stores each of a plurality of threshold values in each of elements for determining a status of dot formation of each print pixel of a print image to be produced on a printing medium by carrying out halftone processing on image data.

Abstract: The image output system of the invention collects a preset number of adjacent pixels to one pixel group to divide a number of pixels constituting an image into multiple pixel groups and specifies a pixel group tone value as a representative tone value of each pixel group. The image output system refers to a conversion table to generate dot number data of each pixel group. The conversion table stores dot number data, which represents number of dots to be created in one pixel group, in relation to a combination of a pixel group classification number allocated to each pixel group and the specified pixel group tone value of the pixel group. The image output system then refers to a priority order of pixels representing potentials of dot creation in respective pixels of one pixel group, determines the positions of dot-on pixels in each pixel group according to the generated dot number data of the pixel group, and actually creates dots according to the determined positions of the dot-on pixels.

Abstract: A method for halftoning an image using an error diffusion process generates an upper threshold level and a lower threshold level and selects a region number parameter. A pixel from the input image is selected and compared to the upper and lower threshold levels. A first pixel value is output when the input pixel value is below the lower threshold level. The first pixel value is output when the input pixel value is below the upper threshold level and above the lower threshold level and a value of the input pixel divided by the region number parameter, modulo 2, equals zero. A second pixel value, the first pixel value being different from the second pixel value, is output when the input pixel value is below the upper threshold level and above the lower threshold level and a value of the input pixel divided by the region number parameter, modulo 2, is greater than zero. The second pixel value is output when the input pixel value is above the upper threshold level.

Abstract: Techniques are disclosed for selectively dithering only a subset of a digital image. One or more ranges of digits are selected for dithering. Only those pixels having digits within the selected range(s) in the digital image are dithered. The image is printed after being selectively dithered. Digits may be selected for dithering if they have values within the range(s) of one or more non-monotonic regions of a printer transfer function. Dithering may be performed on the subset of the digital image by applying a nonlinear transformation is applied to the image and adding a dither pattern to the transformed image. The result is quantized, and the inverse of the nonlinear transformation is applied to the quantized image to produce a dithered image. The nonlinear transformation is constructed such that the effects of the dither pattern appear only in that subset of the image having digits in the selected range(s).

Abstract: There is provided an image processing apparatus employing an error diffusion method capable of preventing a pseudo contour attributable to a delayed dot. The image processing apparatus receives an error diffused from a neighboring pixel and corrects a value (an input value of 0 to 1) of a pixel to be processed before it reduces a tone. Then a subtracter calculates an error associated with the tone reduction, which is diffused to a neighboring pixel. Herein, only for an input value of no less than 0.5 an inversion portion multiplies by ?1 an error from a neighboring pixel and an error to a neighboring pixel. Thus a dot can be free of delay to prevent a pseudo contour.

Abstract: The image output system of the invention collects a preset number of adjacent pixels to one pixel group to divide a number of pixels constituting an image into multiple pixel groups and specifies a pixel group tone value as a representative tone value of each pixel group. The image output system refers to a conversion table to generate dot number data of each pixel group. The conversion table stores dot number data, which represents number of dots to be created in one pixel group, in relation to a combination of a pixel group classification number allocated to each pixel group and the specified pixel group tone value of the pixel group. The image output system then refers to a priority order of pixels representing potentials of dot creation in respective pixels of one pixel group, determines the positions of dot-on pixels in each pixel group according to the generated dot number data of the pixel group, and actually creates dots according to the determined positions of the dot-on pixels.

Abstract: A method for enabling a program that communicates a document description from a composition system to a printing system to manage variable-dot halftones for use with variable-dot printing devices, comprising the steps of creating a set of strings, each string defining a halftone cell intensity value and comprising at least one pixel imbution value, wherein said pixel imbution value is in the range of 0 to P, wherein P is the number of physical appearances that a painted pixel can have; using a selected halftone cell intensity value to directly choose a string from said set of strings; and painting at least one pixel within a halftone cell according to a pixel imbution value within the chosen string.

Abstract: The present invention provides a dot data processing apparatus for generating data of dots to be formed on a printing medium.

Abstract: An image processing apparatus includes a determining device, a mode setting device, a storage device, and a dither matrix selecting device that selects a dither matrix corresponding to the one of the plurality of image output modes set by the mode setting device as a dither matrix used by the determining device, wherein when a predetermined image output mode is set by the mode setting device, the dither matrix selecting device selects a dither matrix for higher levels than those of the input image data.

Abstract: Sets of multiple pixels are grouped into pixel groups, and on the basis of tone value distribution in each pixel group, it is decided whether to divide the pixel group. For pixel groups that are not divided, a representative tone value is determined for the pixel group, and for pixel groups that are divided, a representative tone value is determined for each region created by the division. Next, from multilevel halftoning result values derived by multilevel halftoning of the representative tone values, the dot on-off state is determined for each pixel in the pixel groups, and the image is output. At this time, for divided pixel groups, the dot on-off state is determined for each pixel in the regions, based on the multilevel halftoning result value for each region. With multilevel halftoning result values, data creation and transfer can be performed rapidly.

Abstract: An image processing apparatus comprises a processor for quantizing multi-gradation image data with regard to each of R, G and B to convert it into pseudo halftone output image data. First, the processor performs a first quantization for deciding a dot appearance pattern C(B)i,j[k] with respect to an observed pixel of the multi-gradation image data with regard to blue. After that, the processor performs a second quantization for deciding the dot appearance pattern of green with respect to the observed pixel so as to make an anti-correlation with the dot appearance pattern C(B)i,j[k] decided by the first quantization.

Abstract: A printing system is disclosed. The printing system includes an image processor to rasterize a received print job and to perform a halftone by comparing a first threshold value from a threshold matrix to a first image component sample, comparing the first threshold value to a first number of sequential image component samples neighboring the first sample if the first threshold value is less than the first sample and comparing the first threshold value to a second number of sequential image component samples neighboring the first sample if the first threshold value is greater than or equal to the first sample.

Abstract: This invention provides a method for generating a dither matrix includes: setting an evaluation function for calculating an evaluation value of the dither matrix; providing a dither matrix as an initial state which stores in respective elements each of a plurality of threshold values for deciding presence or absence of dot formation for each pixel according to an input tone value; fixing an element for storing a threshold value in an increasing order from a smaller threshold value while transposing at least one of the plurality of threshold values stored in a part of the elements and a threshold value stored in another part of the elements; and outputting a dither matrix in which elements for storing are fixed with regard to at least part of the plurality of threshold values.

Abstract: A main vector: m^=(mx, my) and a sub-vector: s^=(sx, sy) determining cyclic structure of a basic matrix are defined, and a positional vector for a pixel configuring the basic matrix Pi^=(Pix, Piy) is defined, where the suffix i denotes an i-th pixel configuring the basic matrix. Then, the pixels configuring the basic matrix are arranged in such a manner as to satisfy the cyclic structure, and transformation of Pi^?Pi^+km^+ls^ is carried out where k and l are arbitrary integers, and may be negative values. Then a new shape of the basic matrix is obtained with Pi^+km^+ls^ as a new pixel positional vector Pi^.

Abstract: An image printing process of the invention first specifies a pixel group tone value of each pixel group consisting of a preset number of multiple pixels and refers to one of correlation maps selected for the pixel group to convert the specified pixel group tone value to a multivalue code. Each of the correlation maps sets multivalue codes in correlation to pixel group tone values. The multivalue codes of all pixel groups constituting an image are output as control data to an image output device. The image output device determines the dot on-off state in respective pixels of each pixel group according to the received control data and actually creates dots on an output medium to complete an output image. Each correlation map referred to for the multivalue coding has a slightly lower tone resolution in a higher tone value area than in a lower tone value area. This arrangement desirably reduces the data volume of the control data, while preventing deterioration of the picture quality.

Abstract: Efficiently processing contone image data by determining one or more characteristics of the image data and using these characteristics to manipulate the dither matrix so that the printed image is enhanced.

Abstract: In an image processing apparatus that performs a dither processing using a dither matrix based on the result of determination of the segmentation class to which the pixel to be processed belongs, to perform the dither processing, any of a plurality of pairs of threshold values is selected according to the result of determination of the segmentation class, and the selected pair of threshold values are compared with the value of the pixel to be processed, which are set so that in correspondence with each position of a dither matrix of a same configuration and a same size, a different dither processing is performed according to the result of determination of the segmentation class on part of the dither matrix and a same dither processing is performed irrespective of the result of determination of the segmentation class on the remainder of the dither matrix.