Sony Corporation

Other

Sony Semiconductor Solutions Corporation

Sony Electronics Inc

Jun Murayama

Yoichi Yagasaki

Osamu Sunohara

Masayuki Hattori

Kazuki Aisaka

Masatoshi Yokokawa

Toshiyuki Miyauchi

Takefumi Nagumo

Nodoka Tokunaga

Takashi Yokokawa

Ken Tamayama

Masaya Kinoshita

Toshio Yamazaki

Kouhei Yamamoto

Takashi Kameya

Seiji Kobayashi

Kazuhiro Yamada

Kazuyuki Yamamoto

Atsushi Ito

Kenji Tanaka

Takayuki Yoshigahara

Takeo Ohishi

Shuzo Sato

Masahiro Watanabe

Hung-Ju Lee

Tatsuo Fujiwara

Tamaki Eyama

Ken Nishida

Robert J McEliece

An image processing device includes depth acquisition circuitry that uses a parallax corresponding to image data to electronically generate a depth map of an image and object detection circuitry that uses distance information and the depth map to electronically detect a specific object in the image by identifying specific pixels in the image data. The depth map includes information that pertains to distances from a reference position for each pixel in the image.

Image processing device, imaging device, image processing method and program

An image processing device includes a viewpoint separating unit configured to separate multi-viewpoint image data, including images of multiple viewpoints and representing intensity distribution of light and the direction of travel of light according to positions and pixel values of pixels, into a plurality of single-viewpoint image data for each of the individual viewpoints; and a parallax control unit configured to control amount of parallax between the plurality of single-viewpoint image data obtained by separation into individual viewpoints by the viewpoint separating unit.

Image processing device, method, and recording medium

A video-information encoding apparatus and decoding apparatus with a guarantee of a fixed processing time. By limiting the amount of data to be input into/output from a CABAC encoding unit and decoding unit on a unit-of-encoding basis, such as one picture, slice, macroblock or block, and by encoding uncompressed video data, it is possible to provide a video-information encoding apparatus and decoding apparatus with a guarantee of a fixed processing time. Thereby, an apparatus with a guarantee of the processing time can be mounted.

Video-information encoding method and video-information decoding method

Image processing device and method, recording medium, and program

An image processing device includes a subject detecting unit detecting a subject on a material image, a working unit performing a working process on the material image such that a region of the subject puts in the block, an image generating unit clipping a subject-including region of the material image so as to have the same form and size as the block and generating a subject-including clipped image and a replacing unit setting one clipped image which is the most similar to the block in terms of color-related characteristics as the replacement image for each block of the production target image and replacing the block by the replacement image to generate a photo-mosaic image.

Image processing device, method and program

An apparatus for improving the quality of a captured image may include a first computing unit, a second computing unit, and an advice generating unit. The first computing unit may be configured to compute a first value representing a first aspect of the quality of a first image. The second computing unit may be configured to compute a second value representing a second aspect of the quality of the first image. The advice generating unit may be configured to generate advice for capturing a second image based on at least one of the first and second computed values.

Apparatus, camera, method, and computer-readable storage medium for generating advice for capturing an image

A basic pattern generating unitgenerates a film grain basic patternin which the histogram of random noise is substantially the same as the film grain basic pattern information. The film grain basic patternis of (64&#xd7;64) pixels and an area of (16&#xd7;16) pixels is cut out and supplied to a multiplierStrength informationis generated based on film grain strength informationproduced on the encoding side and an average valueof a pixel value in the area of (16&#xd7;16) pixels of decoded image information. The strength of basic patternis adjusted by this strength information. Film grain imagewhose strength is adjusted is added to the area of (16&#xd7;16) pixels of the decoded image informationby an adderby the unit of pixel.

Image processing apparatus and image processing method

The present invention relates to an image processing apparatus and method, and a program that are capable of more appropriately evaluating the image-capture state of an image. A blur degree score calculation unitthrough to a chroma score calculation unitextract a feature quantity of a pre-specified feature from an input image, and calculate a feature-by-feature score indicating an evaluation for the input image on the basis of the feature. For example, the luminance score calculation unitextracts, as a feature quantity, a luminance value from the input image, and calculates a luminance score indicating an evaluation based on the distribution of the luminance values in the subject portion of the input image. The overall score calculation unitcalculates an overall score indicating the evaluation of the image-capture state of the input image from each feature-by-feature score. As described above, when each feature-by-feature score is to be calculated, by extracting each feature quantity and obtaining a score from the area of the input image suitable for the feature, it is possible to more appropriately evaluate the input image. The present invention can be applied to an image processing apparatus.

Image processing apparatus and method, and program

The present invention relates to an image processing apparatus and method, and a program that are capable of more easily identifying an area of a subject in an image. A luminance information extraction unitthrough to a motion information extraction unitextract predetermined information from an input image and create an information map indicating feature quantities of features possessed by an area of a subject of the input image. Furthermore, the luminance information extraction unitthrough to the motion information extraction unitsubtract an average value of the pixel values of the pixels of the entire information map from the pixel value of each pixel of the created information map so as to normalize the information map. As a result, the information map can be normalized, and noise can be removed with a simple process when compared to a case in which the information map is normalized using a DOG filter. A subject map creation unitlinearly combines each information map, and creates a subject map indicating the likelihood of an area being a subject in each area of an input image. The present invention can be applied to an image processing apparatus.

The present invention relates to an image processing apparatus and method, and a program that make it possible to more accurately specify a photographic subject in an image. A photographic subject map generating unitgenerates, based on an input image, a photographic subject map indicating the likeliness of each region of the input image being a region of a photographic subject. A gradient map generating unitgenerates a gradient map indicating the degree of change of the likeliness of the photographic subject map being a photographic subject. A threshold processing unitand a threshold processing unitbinarize the gradient map using a high threshold THh and a low threshold TH, and obtain threshold maps. A composite map generating unitgenerates a composite map indicating the likeliness of each region of the input image being a photographic subject by regarding that, among regions specified as being likely to be a photographic subject based on the threshold map of the low threshold TH, a region including a region specified as being likely to be a photographic subject based on the threshold map of the high threshold THh is a region of a photographic subject. The present invention is applicable to an image processing apparatus.

The present invention relates to an image processing apparatus and method, a learning apparatus and method, and a program which allow reliable evaluation of whether or not the subject appears sharp. A subject extraction unituses an input image to generate a subject map representing a region including the subject in the input image, and supplies the subject map to a determination unit. The determination unituses the input image and the subject map from the subject extraction unitto determine the blur extent of the region of the subject on the input image, and calculates the score of the input image on the basis of the blur extent. This score is regarded as an index for evaluating the degree to which the subject appears sharp in the input image. The present invention can be applied to an image capture apparatus.

Image processing apparatus and method, learning apparatus and method, and program

An image processing device includes a subject region detector that detects a subject region from an input image; a cutting unit that cuts an image of the subject region from the input image; a priority calculator that calculates a priority of each of predetermined regions on a boundary with respect to the subject region, for the input image; a retrieval unit that retrieves a region similar to an image of a predetermined region with a top priority from among the priorities, from the input image after the image of the subject region is cut; a recovery unit that recovers the subject region by copying an image of an adjacent region that is adjacent to the region similar to the predetermined region retrieved by the retrieval unit and includes a region corresponding to a region cut as the subject region, and by pasting the image obtained by copying onto the region that is adjacent to the predetermined region with the top priority and cut as the subject region; and a composition unit that combines the image of the subject region cut by the cutting unit with the image with the subject region recovered by the recovery unit.

Growing community of inventors

Tokyo, Japan

Jun Murayama