Abstract: An image processing apparatus includes a memory that stores a first dictionary having first feature data of a reference image of a target object and a second dictionary having second feature data of the reference image that is horizontally inverted, an image processor configured to acquire third feature data of an input image, and a pattern matching circuit configured to calculate a first score by comparing the first and third feature data and a second score by comparing the second and third feature data, and determine whether the target object is present in the input image based on the first and second scores.

Abstract: An image processing apparatus includes an image pyramid generating section, a memory and a matching section. The image pyramid generating section generates an image pyramid including a plurality of layer images of mutually different sizes, from an input image. The memory stores a first dictionary for detecting a first object and a second dictionary for detecting a second object obtained by reducing the first object at a first predetermined reduction ratio. The matching section performs matching between the first dictionary and between the second dictionary, respectively, and a detection frame image within a detection frame configured to move within the layer image.

Abstract: In general, according to one embodiment, an electronic device includes a hardware processor. The hardware processor is configure to outputs a user interface for designating disparity sharpness related to a difference in sharpness at a border between an object and a background of the object, the difference resulting from a difference in depth-direction distances of the object and the background, and to sets the sharpness at the border between the background and the object based on the disparity sharpness designated via the user interface, and to generates one multiscopic image from parallax images.

Abstract: According to one embodiment, a stereoscopic image converting method includes: generating a first depth map comprising depth values of pixels of an input video, wherein the depth values are estimated based on an amount of a characteristic of the input video, and wherein the depth values are represented by pixel shading; generating a second depth map by correcting the depth values of pixels within a distance from each of right and left ends of the depth map to become closer to a depth value corresponding to a screen of a display not protruding forward or recede rearward in stereoscopic viewing as the pixels within the first distance are positioned closer to the each of the right and left ends of the depth map; and generating a multi-parallax image by shifting pixels of the input video by an amount horizontally based on the depth values of the second depth map.

Abstract: According to one embodiment, a stereoscopic image converting method includes: generating a first depth map comprising depth values of pixels of an input video, wherein the depth values are estimated based on an amount of a characteristic of the input video, and wherein the depth values are represented by pixel shading; generating a second depth map by correcting the depth values of pixels within a distance from each of right and left ends of the depth map to become closer to a depth value corresponding to a screen of a display not protruding forward or recede rearward in stereoscopic viewing as the pixels within the first distance are positioned closer to the each of the right and left ends of the depth map; and generating a multi-parallax image by shifting pixels of the input video by an amount horizontally based on the depth values of the second depth map.

Abstract: According to one embodiment, an image processing apparatus includes a motion estimation module, a redundant frame determination module and an interpolation frame generation module. The motion estimation module calculates motion vectors for respective pixel blocks in each frame in moving image data by estimating motion between frames in the moving image data. The redundant frame determination module determines whether a target frame is a redundant frame based on the motion vectors corresponding to the target frame and the motion vectors corresponding to a frame preceding the target frame. The interpolation frame generation module discards the target frame if the target frame is a redundant frame, and generates an interpolation frame between the target frame and the preceding frame by motion compensation using the motion vectors corresponding to the target frame and outputs the interpolation frame and the target frame, if the target frame is a non-redundant frame.

Abstract: An information processing apparatus is presented that includes a first determination unit which determines whether a processing target frame is a frame of a predetermined type and a second determination unit which determines whether an interval between the frame and a frame of the predetermined type located temporally nearest in the forward direction, exceeds a predetermined frame count. In addition, a conversion unit is included which converts the processing target frame into a frame of the predetermined type, when the second determination unit determines that the interval exceeds the predetermined frame count.

Abstract: According to one embodiment, an image processing apparatus includes a vector calculation module, a major vector detection module, and an interpolation frame generation module. The vector calculation module calculates motion vectors of pixel blocks of a frame of moving picture data. The major vector detection module detects as a major vector, motion vectors with the same direction and the same magnitude which have the ratio of the number of the motion vectors with the same direction and the same magnitude to the number of the motion vectors of the frame, the ratio being greater than a predetermined value. The interpolation frame generation module generates an interpolation frame inserted between a processing frame and a preceding frame preceding the processing frame. The motion vector calculation module calculates the motion vectors based on the major vector corresponding to the preceding frame.

Abstract: According to one embodiment, a moving picture decoding apparatus comprises a decoding module configured to decode an input stream containing coded moving picture data and coding information of the coded moving picture data and configured to produce decoded moving picture data and decoding information, an interpolation image generation module configured to generate an interpolation image frame to be interposed between frames in the decoded moving picture data, and an image generation control module configured to control the generation of the interpolation image frame based on the decoding information.

Abstract: According to one embodiment, an image processing apparatus includes an obtaining module, a coefficient filter, a large area filter, and a determination module. The obtaining module obtains a feature value indicating an image structure of a pixel block comprising a target pixel to be processed and a surrounding pixel neighboring the target pixel in an input image. The coefficient filter performs filtering on the pixel block using a filter coefficient corresponding to the feature value. The large area filter performs smoothing on a pixel block that are larger than blocks used with coefficient filter. The determination module determines to cause the large area filter to perform the smoothing when the image structure indicated by the feature value is smooth.

Abstract: According to one embodiment, an image processing apparatus includes an obtaining module, a coefficient filter, a large area filter, and a determination module. The obtaining module obtains a feature value indicating an image structure of a pixel block comprising a target pixel to be processed and a surrounding pixel neighboring the target pixel in an input image. The coefficient filter performs filtering on the pixel block using a filter coefficient corresponding to the feature value. The large area filter performs smoothing on a pixel block that are larger than blocks used with coefficient filter. The determination module determines to cause the large area filter to perform the smoothing when the image structure indicated by the feature value is smooth.

Abstract: According to one embodiment, an image processing apparatus includes a motion estimation module, a redundant frame determination module and an interpolation frame generation module. The motion estimation module calculates motion vectors for respective pixel blocks in each frame in moving image data by estimating motion between frames in the moving image data. The redundant frame determination module determines whether a target frame is a redundant frame based on the motion vectors corresponding to the target frame and the motion vectors corresponding to a frame preceding the target frame. The interpolation frame generation module discards the target frame if the target frame is a redundant frame, and generates an interpolation frame between the target frame and the preceding frame by motion compensation using the motion vectors corresponding to the target frame and outputs the interpolation frame and the target frame, if the target frame is a non-redundant frame.

Abstract: According to one embodiment, an image processing apparatus includes a vector calculation module, a major vector detection module, and an interpolation frame generation module. The vector calculation module calculates motion vectors of pixel blocks of a frame of moving picture data. The major vector detection module detects as a major vector, motion vectors with the same direction and the same magnitude which have the ratio of the number of the motion vectors with the same direction and the same magnitude to the number of the motion vectors of the frame, the ratio being greater than a predetermined value. The interpolation frame generation module generates an interpolation frame inserted between a processing frame and a preceding frame preceding the processing frame. The motion vector calculation module calculates the motion vectors based on the major vector corresponding to the preceding frame.

Abstract: According to one embodiment, a moving picture decoding apparatus comprises a decoding module configured to decode an input stream containing coded moving picture data and coding information of the coded moving picture data and configured to produce decoded moving picture data and decoding information, an interpolation image generation module configured to generate an interpolation image frame to be interposed between frames in the decoded moving picture data, and an image generation control module configured to control the generation of the interpolation image frame based on the decoding information.

Abstract: According to one embodiment, an information processing apparatus includes a first determination unit which determines whether or not a processing target frame is a frame of the predetermined type, a second determination unit which determines whether or not an interval between the frame and a frame of the predetermined type located temporally nearest in a forward direction exceeds a predetermined frame count, when the first determination unit determines that the processing target frame is not a frame of the predetermined type, and a conversion unit which converts the processing target frame into a frame of the predetermined type, when the second determination unit determines that the interval exceeds the predetermined frame count.

Abstract: According to one embodiment, an encoding circuit includes a taking-over unit which takes over probability tables of divided regions of a previous frame image of a frame image having divided regions to divided regions of a present frame image, respectively, an acquiring unit which acquires a parameter of an adjacent macro block of the previous frame image when the macro block is located on a boundary between the divided regions, a selecting unit which calculates the parameter of the macro block to select one of probability models in the probability table, and an encoding unit which arithmetically encodes a residual signal in the frame image on the basis of the selected probability model to generate an encoded bit string.

Abstract: According to one embodiment, an encoding circuit includes a taking-over unit which takes over probability tables of divided regions of a previous frame image of a frame image having divided regions to divided regions of a present frame image, respectively, an acquiring unit which acquires a parameter of an adjacent macro block of the previous frame image when the macro block is located on a boundary between the divided regions, a selecting unit which calculates the parameter of the macro block to select one of probability models in the probability table, and an encoding unit which arithmetically encodes a residual signal in the frame image on the basis of the selected probability model to generate an encoded bit string.