Abstract: An image processing device comprising: a recording unit configured to record a previous frame image input before a target frame image that is to be a processing target or an output frame image from the previous frame image; an alignment unit configured to align the target frame image with the previous frame image or with the output frame image from the previous frame image; a correction unit configured to perform a temporal correction process to correct a pixel value of the target frame image by use of a pixel value of the previous frame image or a pixel value of the output frame image from the previous frame image that has been aligned by the alignment unit, with reference to the recording unit; and a generation unit configured to generate an output frame image from the target frame image by use of the target frame image corrected by the correction unit.

Abstract: The image processing device performs noise removal processing for an input image. The image processing device comprises a filter setting unit configured to set first and second filter factors by using a first target pixel value of a noise processing target pixel to be targeted to the processing and a reference pixel value of a plurality of reference pixels surrounding the noise processing target pixel and a noise removal unit configured to calculate a corrected pixel value by sequentially adding a luminance component of the reference pixel value weighted with the first filter factor and sequentially adding a chroma component of the reference pixel value weighted with the second filter factor, and remove noise of the noise processing target pixel by using the corrected pixel value. The input image has pixel values according to Bayer pattern format.

Abstract: A device is provided that generates a composite image using a first image and a second image having different exposure conditions. The device includes an image input unit, a likelihood calculating unit, an exposure estimating unit, and a compositing unit. The image input unit inputs the first image and the second image. The likelihood calculating unit calculates a subject motion likelihood at each pixel based on a difference between the first image and the second image. The exposure estimating unit estimates an exposure transform function that conforms the exposure conditions of the first image and the second image to each other based on the subject motion likelihood. The compositing unit composites the first image and the second image by using the exposure transform function.

Abstract: An image processing apparatus includes: a placement information acquisition section which acquires, for each image sensor, placement information of the image sensors with respect to the imaging section; a movement information acquisition section which acquires movement information of the imaging device; and an output area acquisition section which acquires, for every image sensor, position information of a second output area within the second frame image which corresponds to a first output area within the first frame image. The output area acquisition section acquires: a second output area of a base image sensor based on position information of a first output area determined by the placement information and based on the movement information; and a second output area of another image sensor based on the placement information of the base image sensor, the placement information of the other image sensor, and the movement information.

Abstract: An image processing device includes an input unit, a selection unit, a matching unit, an estimation unit and a merging unit. The input unit sequentially inputs images. The selection unit selects a reference image from among the input images. The matching unit calculates a correspondence relationship between a feature point of the reference image and a feature point of a target image. The estimation unit estimates an equation that causes a coordinate system of the reference image to correspond to a coordinate system of the target image using positional information of a pair of the feature points whose correspondence relationship has been calculated by the matching unit by regarding a motion between the reference image and the target image as only a rotational motion of the imaging element. The merging unit merges the input image and the target image to generate the composite image based on the equation.

Abstract: Provided is a face authentication system (100) including a reflectance image generating unit (107) for generating a blurred image of an input image based on the input image including a face of a person and generating an input reflectance image by separating each corresponding pixel value of the blurred image from each pixel value of the input image, and a face authenticating unit (112) for performing face authentication of the face of the person included in the input image by comparing the input reflectance image with a registered reflectance image of a previously registered person.

Abstract: A device comprises an input unit, a motion acquisition unit, a matrix operation unit, and a drawing unit. The input unit implements sequential input of a first frame image and a second frame image. The motion acquisition unit acquires motion data between the first frame image and the second frame image. The matrix operation unit calculates a projection matrix to project the output frame image to the second frame image, from a first matrix including a rolling shutter distortion component, a second matrix including at least one of a parallel translation component in directions perpendicular to an image-shooting direction and a rotation component with respect to the image-shooting direction, and an auxiliary matrix including a motion component not included in the first matrix and the second matrix. The drawing unit generates the output frame image from the second frame image by using the projection matrix.

Abstract: A moving object detecting device 1 that detects a moving object by using an image includes a motion degree obtaining portion 11 that obtains a motion degree of a pixel between image frames, a color obtaining portion 13 that obtains the color of the pixel included in the image frame, an evaluation score calculating portion 14 that calculates an evaluation score indicating a motion level of the color on the basis of the motion degree for each color obtained by the color obtaining portion, and a moving object detecting portion 15 that detects the moving object on the basis of the evaluation score for each color.

Abstract: An image processing device includes an image input portion, a motion vector acquisition portion and a distortion component estimation portion. The image input portion inputs a target image which is an image to be processed. The motion vector acquisition portion acquires a motion vector generated by relative movement with respect to a subject drawn in the target image when an imaging device which has generated the target image generates the target image. The distortion component estimation portion estimates a rolling shutter distortion component of the target image based on the motion vector.

Abstract: It is an object to generate a desired composite image in which a motion area of a subject is correctly composited. A difference image between a base target and an aligned swap target is generated (S1021), and an extracted contour in the difference image is determined according to the active contour model (S1022). The inner area of the contour and the outer area of the contour are painted with different colors to be color-coded so as to generate a mask image for alpha blending (S1023). Using the mask image thus generated, the swap target that is aligned with respect to the base target is composited with the base target of the base image by alpha blending (S1024).

Abstract: The invention provides an image identification device that classifies block images obtained by dividing a target image into predetermined categories, using a separating plane learning of which has been completed in advance for each of the categories. The image identification device includes a target image input unit inputs the target image, a block image generation unit divides the target image into blocks to generate the block images, a feature quantity computing unit computes feature quantities of the block images, and a category determination unit determines whether the block images are classified into one of the categories or not, using the separating plane and coordinate positions corresponding to magnitudes of feature quantities of the block images in a feature quantity space, wherein the feature quantity computing unit uses, as a feature quantity of a given target block image, local feature quantities and a global feature quantity.

Abstract: An image processing device includes an image input portion, a motion vector acquisition portion and a distortion component estimation portion. The image input portion inputs a plurality of frame images. The motion vector acquisition portion acquires an amount of parallel movement between two frame images. The distortion component estimation portion performs approximation such that a motion matrix indicating a motion between the frame images consists only of a parallel movement component and a rolling shutter distortion component, uses the amount of parallel movement to calculate, for each of the frame images, a tentative distortion coefficient included in the rolling shutter distortion component and uses the plurality of tentative distortion coefficients calculated to estimate a distortion coefficient.

Abstract: A device is provided that generates a composite image using a first image and a second image having different exposure conditions. The device includes an image input unit, a likelihood calculating unit, an exposure estimating unit, and a compositing unit. The image input unit inputs the first image and the second image. The likelihood calculating unit calculates a subject motion likelihood at each pixel based on a difference between the first image and the second image. The exposure estimating unit estimates an exposure transform function that conforms the exposure conditions of the first image and the second image to each other based on the subject motion likelihood. The compositing unit composites the first image and the second image by using the exposure transform function.

Abstract: (Problem) To facilitate setting of an image display style and selection of images in an image display apparatus with a touch screen. (Solution to Problem) Thumbnails included in an area designated by a pinch gesture are all specified. If it is not true that “the thumbnails included in the designated area are all displayed in the selected style” (S2004, No), the thumbnails included in the designated area are all displayed in the selected style (S2005), and the status is set to selected state (S2006). If it is true that “the thumbnails included in the designated area are all displayed in the selected style” (S2004, Yes), the thumbnails included in the designated area are all displayed in unselected style (S2007), and the status is set to unselected state (S2008). If the gesture is continuously changed to a pinch-out gesture or a pinch-in gesture (S2010, No), the selected area or the unselected area are expanded or reduced depending on the status (S2014, S2015).

Abstract: An object detection apparatus that detects an object to be detected captured in a determination image according to a feature amount of the object to be detected preliminarily learned by the use of a learning image, the object detection apparatus including a detector 2 causing strong classifiers 21m to operate in order of lower classification accuracy, continuing processing when the strong classifier 21m has determined that the object to be detected is captured in the determination image, and determining that the object to be detected has not been detected without causing the strong classifier 21m having classification accuracy higher than the aforementioned strong classifier 21m to operate, when the strong classifier 21m has determined that the object to be detected is not captured in the determination image, wherein the strong classifier 21m inputs a classification result of the strong classifier 21m having classification accuracy lower than the aforementioned strong classifier 21m and determines whether the

Abstract: An image processing device includes: processing pixel group determination unit that determines a to-be-processed pixel group from a plurality of frame images of picture signals input based on a first predetermined rule and that determines a processed pixel group from the processed frame image stored based on a second predetermined rule; frequency component processing unit that extracts at least a temporal frequency component from the to-be-processed pixel group and the processed pixel group, that executes predetermined coefficient processing on a temporal high-frequency component of the temporal frequency component and that acquires the executed to-be-processed pixel group; processing completion frame generation unit that generates a processing completion frame image from the executed to-be-processed pixel group; and image output unit that outputs the processing completion frame image and that stores the processing completion frame image in the processed frame storage unit, in which the frequency component pr

Abstract: An object detection apparatus that detects an object to be detected captured in a determination image according to a feature amount of the object to be detected preliminarily learned by the use of a learning image, the object detection apparatus including a detector causing strong classifiers to operate in order of lower classification accuracy, continuing processing when the strong classifier has determined that the object to be detected is captured in the determination image, and determining that the object to be detected has not been detected without causing the strong classifier having classification accuracy higher than the aforementioned strong classifier to operate, when the strong classifier has determined that the object to be detected is not captured in the determination image, wherein the strong classifier inputs a classification result of the strong classifier having classification accuracy lower than the aforementioned strong classifier and determines whether the object to be detected is captured

Abstract: An image data processing method for creating a clear blur-compensated image; the method calculates the motion data between a reference image and a target image, calculates difference in pixel value between the reference image and the target image for every block matched by the motion data, calculates, based on the difference in pixel value, the blending ratio between the reference image and the target image for each block, and creates a synthesized image by synthesizing the reference image and the target image according to the motion data and the blending ratio. An image processing apparatus implementing the image data processing method noted above is also disclosed.

Abstract: An image processing device that accumulatively generates a synthetic image by joining a first image, which is a single image or is constituted by a plurality of the images joined together, and a second image that is input, every time when the second image is input, the device comprising: a center-position obtainment portion (11) that obtains position information on a first center point being a center point of each of the images constituting the first image and position information on a second center point being a center point of the second image; and a synthetic image generation portion (12) that obtains the first center point of an image overlapping the second image among the images constituting the first image, and that joins the first image and the second image to generate the synthetic image, using perpendicular bisectors between the obtained first center points and the second center point as a joint between the first image and the second image, based on the obtained position information on the first cent

Abstract: An image processing device that performs image processing on a composite image obtained by merging a first image and a second image having different exposure conditions. A data acquiring unit acquires the composite image and region data indicating a target region of the composite image. A image processing unit performs different image processes between the target region and a region other than the target region based on the region data. The images include a region on which a moving subject is rendered. In the region on which the moving subject is rendered, the composite image is generated by using a pixel value of one of the first image and the second image. The region data represents one or a plurality of regions generated based on the region of the composite image, on which the moving subject is rendered, as the target region.