Fujitsu Corporation

Yuushi Toyoda

Masayoshi Shimizu

Toru Tsuruta

Eishi Morimatsu

Koichiro Niinuma

Hiroyuki Endo

Ryosuke Kawamura

A method includes generating resolution images corresponding to the resolutions from each of a target image which is an image frame, included in a moving image or a still image group photographed continuously, of a processing target among the image frames and a processing target image photographed before the target image, executing block matching between a resolution image of the target image and a resolution image of the processing target image for each of the resolutions, calculating a plurality of motion vector candidates corresponding to the respective resolutions for each pixel of the target image, evaluating reliability of the plurality of motion vector candidates based on an evaluation index using noise characteristics related to pixel areas of a start point and an end point of each of the plurality of motion vector candidates for each pixel of the target image, and calculating a final motion vector.

Motion vector calculation method, information processing apparatus, recording medium recording motion vector calculation program

A recording medium on which a user assistance program is recorded which makes a computer perform: based on image information obtained by photographing a plurality of users who use a given service, calculating state quantities of the plurality of respective users corresponding to the image information; counting, for each time period, a number of users whose amounts of change in the calculated respective state quantities are equal to or more than a given threshold value among the plurality of users; and detecting a time period in which the counted number of users satisfies a given condition.

Recording medium on which user assistance program is recorded, information processing device, and user assistance method

An image correction apparatus includes a difference computing unit which computes an absolute difference value between corresponding pixels in a first and a second image, a combining ratio computing unit which computes a combining ratio of the second image to the first image so that the combining ratio decreases as the absolute difference value of each pixel contained in a filter region defined around an attention pixel on the first image increases, and a combining unit which produces a corrected image by combining the value of the attention pixel in the first image with the value of the corresponding pixel in the second image in accordance with the combining ratio computed for the attention pixel and by taking the combined value as the value of the corresponding pixel in the corrected image.

Image correction apparatus and imaging apparatus

An image synthesis device includes: a first pixel selection unit which selects, from a first filter area around a pixel of interest on a first image, a first pixel having a value within a first allowable range including a value of a pixel of interest; a second pixel selection unit which sets a second filter area around a reference pixel located on a second image having a longer exposure time than the first image in the same position as the pixel of interest, and selects, from the second filter area, a second pixel having a value within a second allowable range including the value of the pixel of interest; and a synthesis unit which sets a synthetic value, acquired by synthesizing the values of the first and the second pixel, as the value of a pixel on the synthetic image in the same position as the pixel of interest.

Image synthesis device and computer program for image synthesis for synthesizing a plurality of images of different exposure times

An image processing apparatus includes a reducing unit that reduces an input image chronologically input as moving images and accumulates a reduced image of the input image as a first reduced image in a predetermined memory. The image processing apparatus further includes a generating unit that generates, as a second reduced image, one reduced image from multiple first reduced images accumulated in the memory. The image processing apparatus further includes a smoothing unit that smooths level values of a pixel included in the second reduced image and pixels surrounding the pixel with respect to each of multiple ranges set according to the width of level values of pixels. The image processing apparatus further includes a synthesizing unit that synthesizes multiple range-by-range results of the smoothing on the basis of the input images. The image processing apparatus further includes an output unit that outputs a synthesized image as an output image.

Image processing apparatus and image processing method

An image processing apparatus creates a basic-structure component image representing an image that an input image except edge is smoothed while preserving the edge in the input image; and creates a detail component image representing an image that the basic-structure component image is subtracted from the input image. Subsequently, the image processing apparatus decomposes the detail component image into a plurality of frequency-band images through multiresolution transform processing, and performs noise removal on the obtained frequency-band images. After that, the image processing apparatus performs inverse multiresolution transform processing of combining the noise-removed frequency-band images, thereby creating a noise-removed detail-component image.

An image processing apparatus sets the pixels of an input image as process target pixels by using low pass filters (LPF #to LPF #) each having different level value ranges, computes the average values of the pixels included in the level value ranges from the pixels of the input image including process target pixels included within the filter sizes of the low pass filters, generates level-value-limited smoothed images #limited by the level values, generates level-value-limited smoothed images #by using low pass filters (LPF #to LPF #) each having level value ranges or filter sizes different from those of LPF #to LPF #selects either of the level-value-limited smoothed images #or the level-value-limited smoothed images #on the basis of the process target pixels and level values different from the level values utilized by LPFs, synthesizes the selected level-value-limited smoothed images, and generates a smoothed image.

An image processing apparatus includes a level-value-limit smoothed-image creating unit, a level-value combining unit, and a smoothed-image creating unit. The level-value-limit smoothed-image creating unit calculates, from the pixels in a received input image within a filter size of the low-pass filters each having different level value ranges, an average value of the pixels in the level value ranges, and creates level-value-limit smoothed images. The level-value combining unit creates a level-value combined image by selecting and combining one or more of the level-value-limit smoothed images. The smoothed-image creating unit determines, based on image information that is different from image information used by the level-value-limit smoothed-image creating unit, a combining ratio of the input image to the level-value combined image and creates a smoothed image by combining the input image and the level-value combined image using the determined combining ratio.

An image processing apparatus includes a low-frequency-component storage unit that stores therein a low-frequency component generated from a frame in an input moving image composed of a plurality of frames, a low-frequency-component generating unit that generates a low-frequency component from an N-th frame of the input moving image, and stores the low-frequency component in the low-frequency-component storage unit, and a dynamic-range correcting unit that corrects a dynamic range by using an (N+1)-th or later frame of the input moving image and the low-frequency component of the N-th frame stored in the low-frequency-component storage unit.

An image processing apparatus holds a plurality of intermediate smoothed images smoothed at a plurality of preset level values, reduces the N-th frame image of a moving image received from the outside to generate a reduced image, performs a smoothing process on the generated reduced image at the plurality of preset level values to generate a plurality of intermediate smoothed images, stores the generated intermediate smoothed images in an intermediate smoothed image storing unit, acquires, when generating the smoothed images of the frames after the (N+1)-th frame, one or a plurality of intermediate smoothed images from the plurality of intermediate smoothed images of the N-th frame stored in the intermediate smoothed image storing unit, synthesizes the acquired intermediate smoothed images of the N-th frame and the frames after the (N+1)-th frame of the moving image received from the outside, and generates smoothed images.

An image processing apparatus performs a gradation conversion on an input image (frame) input from the outside to generate a conversion image and performs a plurality of smoothing processes corresponding to a plurality of preset level values on the generated conversion image or a reduced image generated from the conversion image to generate a plurality of level-value-limited conversion images. Then, the image processing apparatus selects one or a plurality of conversion images from the plurality of level-value-limited conversion images, synthesizes the selected images, generates a synthesis image, performs the gradation conversion on the generated synthesis image, and generates a smoothed image that is converted to have the same gradation as that of the input image.

An image processing device is for generating a smoothed image with an input image blurred. The device includes first low pass filters each set with a different range of level value, using each pixel in the input image or a first input image generated based on the input image as a pixel of interest, extracting each pixel that has a level value of each pixel in a filter size within a range of level value, and generating a first level value limit smoothed image by smoothing a level value of an extracted pixel to be used as a level value of the pixel of interest. The device also includes a first synthesis processing unit that uses each pixel in the input image or a second input image generated based on the input image as a processing object pixel.

Image processing device and image processing method

An image generating apparatus that generates an output image using a difference between an uncorrected pixel in an image and a smoothed pixel obtained by smoothing the uncorrected pixel. The image generating apparatus includes a storage unit, a tone-converted uncorrected pixel generating unit, a tone-converted smoothed pixel generating unit, and an output image generating unit. The storage unit stores an uncorrected pixel tone table for converting the uncorrected pixel and a smoothed pixel tone table for converting the smoothed pixel. The tone-converted uncorrected pixel generating unit converts the uncorrected pixel to a tone-converted uncorrected pixel based on the uncorrected pixel tone table. The tone-converted smoothed pixel generating unit converts the smoothed pixel to a tone-converted smoothed pixel based on the smoothed pixel tone table. The output image generating unit generates the output image based on a difference between the tone-converted uncorrected pixel and the tone-converted smoothed pixel.

Image generating apparatus, image generating method and computer product

An image processing apparatus includes a surrounding-pixels selecting unit that selects surrounding pixels that surround a correction pixel in an input image based on a low-pass filter, a reference-pixels selecting unit that selects pixels from the surrounding pixels based on pixel values of the correction pixel and the surrounding pixels, a smoothed-image creating unit that applies the low-pass filter to the reference pixels to create a smoothed image of the reference pixels, and an output image creating unit that creates an output image based on the smoothed image, and a difference image between the smoothed image and the input image.

Growing community of inventors

Kawasaki, Japan

Yuushi Toyoda