Patents by Inventor Yuki TOKIZAKI
Yuki TOKIZAKI has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11436706Abstract: Provided is an image processing apparatus that includes an image processing section that executes filter processing using a filter coefficient. The filter coefficient is set at least on the basis of a detection result for details based on a first image and a detection result of detection of a disturbance performed on a second image.Type: GrantFiled: December 7, 2018Date of Patent: September 6, 2022Assignee: SONY CORPORATIONInventors: Yuki Tokizaki, Satoshi Kawata
-
Patent number: 11325520Abstract: A transmittance estimation unit estimates a transmittance for each of regions from a captured image. The transmittance estimation unit estimates the transmittance for each pixel, using, for example, dark channel processing. A transmittance detection unit detects a transmittance of haze at the time of imaging of the captured image, using the transmittance estimated for each pixel by the transmittance estimation unit and depth information for each pixel. The transmittance detection unit detects the transmittance of the haze on the basis of, for example, a logarithm average value of the transmittances in the whole or a predetermined portion of the captured image, and an average value of depths indicated by the depth information.Type: GrantFiled: July 12, 2018Date of Patent: May 10, 2022Assignee: SONY CORPORATIONInventors: Satoshi Kawata, Kazunori Kamio, Yuki Tokizaki
-
Patent number: 11030723Abstract: There is provided an apparatus and a method that perform a process of improving the quality of a low-quality image such as a far-infrared image. The apparatus includes an image correction unit that repeatedly performs an image correction process using a plurality of processing units in at least two stages. The image correction unit inputs a low-quality image to be corrected and a high-quality image which is a reference image. Each of the processing units in each stage performs a correction process for the low-quality image, using a class correspondence correction coefficient corresponding to a feature amount extracted from a degraded image of the high-quality image. A processing unit in a previous stage performs the correction process, using a class correspondence correction coefficient corresponding to a feature amount extracted from an image which has a higher degradation level than that in a processing unit in a subsequent stage.Type: GrantFiled: December 1, 2017Date of Patent: June 8, 2021Assignee: SONY CORPORATIONInventors: Kazunori Kamio, Takahiro Nagano, Yuki Tokizaki, Yiwen Zhu, Satoshi Kawata
-
Publication number: 20210042886Abstract: An image processing apparatus includes an image processing section configured to execute filter processing using a filter coefficient set at least on the basis of a detection result for details based on a first image and a detection result of detection of a disturbance performed on a second image.Type: ApplicationFiled: December 7, 2018Publication date: February 11, 2021Inventors: YUKI TOKIZAKI, SATOSHI KAWATA
-
Patent number: 10880498Abstract: An image processing apparatus includes a first combination unit that receives a far-infrared image and multiple reference images obtained by capturing the same object as that of the far-infrared image and generates a first composite signal which is a composite signal of the multiple reference images and a second combination unit that combines the far-infrared image and the first composite signal to generate a quality-improved image of the far-infrared image. The first combination unit generates the first composite signal on the basis of a visible image-far-infrared image correlation amount and a near-infrared image-far-infrared image correlation amount. The first combination unit sets a contribution ratio of a reference image, which has a larger amount of correlation with the far-infrared image, of the two reference images, that is, the visible image and the near-infrared image to a large value and generates the first composite signal.Type: GrantFiled: February 14, 2018Date of Patent: December 29, 2020Assignee: SONY CORPORATIONInventors: Yuki Tokizaki, Kazunori Kamio, Toshiyuki Sasaki
-
Patent number: 10853926Abstract: A device includes a feature amount calculating unit for receiving an infrared light image and a visible light image and extracting a feature amount from at least one of the images and an image correcting unit for executing pixel value correction processing on the infrared light image on the basis of a reference area and a correction parameter determined depending on the feature amount. The device further includes a tap selection unit for determining the reference area used for the pixel value correction on the basis of the feature amount and a correction parameter calculating unit for determining the correction parameter used for the pixel value correction on the basis of the feature amount. The image correcting unit executes the pixel value correction processing in which a tap determined by the tap selection unit and the correction parameter determined by the correction parameter calculating unit are applied.Type: GrantFiled: January 25, 2017Date of Patent: December 1, 2020Assignee: SONY CORPORATIONInventors: Yuki Tokizaki, Kazunori Kamio, Yiwen Zhu, Takahiro Nagano
-
Publication number: 20200290503Abstract: A transmittance estimation unit estimates a transmittance for each of regions from a captured image. The transmittance estimation unit estimates the transmittance for each pixel, using, for example, dark channel processing. A transmittance detection unit detects a transmittance of haze at the time of imaging of the captured image, using the transmittance estimated for each pixel by the transmittance estimation unit and depth information for each pixel. The transmittance detection unit detects the transmittance of the haze on the basis of, for example, a logarithm average value of the transmittances in the whole or a predetermined portion of the captured image, and an average value of depths indicated by the depth information.Type: ApplicationFiled: July 12, 2018Publication date: September 17, 2020Applicant: SONY CORPORATIONInventors: Satoshi KAWATA, Kazunori KAMIO, Yuki TOKIZAKI
-
Publication number: 20200053297Abstract: Provided are an apparatus and a method that perform a process of improving the quality of a far-infrared image. An image processing apparatus includes: a first combination unit that receives a far-infrared image and multiple reference images obtained by capturing the same object as that of the far-infrared image and generates a first composite signal which is a composite signal of the multiple reference images; and a second combination unit that performs a process of combining the far-infrared image and the first composite signal to generate a quality-improved image of the far-infrared image. The reference images are, for example, a visible image and a near-infrared image. The first combination unit generates the first composite signal on the basis of a visible image-far-infrared image correlation amount and a near-infrared image-far-infrared image correlation amount.Type: ApplicationFiled: February 14, 2018Publication date: February 13, 2020Inventors: YUKI TOKIZAKI, KAZUNORI KAMIO, TOSHIYUKI SASAKI
-
Publication number: 20190355097Abstract: There is provided an apparatus and a method that perform a process of improving the quality of a low-quality image such as a far-infrared image. The apparatus includes an image correction unit that repeatedly performs an image correction process using a plurality of processing units in at least two stages. The image correction unit inputs a low-quality image to be corrected and a high-quality image which is a reference image. Each of the processing units in each stage performs a correction process for the low-quality image, using a class correspondence correction coefficient corresponding to a feature amount extracted from a degraded image of the high-quality image. A processing unit in a previous stage performs the correction process, using a class correspondence correction coefficient corresponding to a feature amount extracted from an image which has a higher degradation level than that in a processing unit in a subsequent stage.Type: ApplicationFiled: December 1, 2017Publication date: November 21, 2019Applicant: SONY CORPORATIONInventors: Kazunori KAMIO, Takahiro NAGANO, Yuki TOKIZAKI, Yiwen ZHU, Satoshi KAWATA
-
Patent number: 10467728Abstract: A first-color-space converting unit 223 receives the image signal of first color space from a signal processing unit 222 and converts the received image signal into the image signal of second color space which is suitable for conversion into the image signal of third color space as specified. A thinning processing unit 226 performs thinning process on the converted image signal representing each color component of the second color space for each pixel so as to correspond to a processor unit 30 which generates the image signal representing each color component from the image signal representing one color component of color space for each pixel and output the image signal of the third color space, thereby turning it into the image signal representing one color component of the second color space for each pixel.Type: GrantFiled: March 1, 2016Date of Patent: November 5, 2019Assignee: SONY CORPORATIONInventors: Yuki Tokizaki, Noriaki Takahashi
-
Publication number: 20190102870Abstract: Provided is a device and a method for executing image quality improvement processing of an infrared light image. Included are: a feature amount calculating unit for receiving an infrared light image and a visible light image and extracting a feature amount from at least one of the images; and an image correcting unit for executing pixel value correction processing on the infrared light image on the basis of a reference area and a correction parameter determined depending on the feature amount. Further included are: a tap selection unit for determining the reference area used for the pixel value correction on the basis of the feature amount; and a correction parameter calculating unit for determining the correction parameter used for the pixel value correction on the basis of the feature amount.Type: ApplicationFiled: January 25, 2017Publication date: April 4, 2019Inventors: YUKI TOKIZAKI, KAZUNORI KAMIO, YIWEN ZHU, TAKAHIRO NAGANO
-
Publication number: 20180293704Abstract: A first-color-space converting unit 223 receives the image signal of first color space from a signal processing unit 222 and converts the received image signal into the image signal of second color space which is suitable for conversion into the image signal of third color space as specified. A thinning processing unit 226 performs thinning process on the converted image signal representing each color component of the second color space for each pixel so as to correspond to a processor unit 30 which generates the image signal representing each color component from the image signal representing one color component of color space for each pixel and output the image signal of the third color space, thereby turning it into the image signal representing one color component of the second color space for each pixel.Type: ApplicationFiled: March 1, 2016Publication date: October 11, 2018Inventors: YUKI TOKIZAKI, NORIAKI TAKAHASHI
-
Patent number: 9071832Abstract: Provided is an image processing device including a congruence degree detecting unit which detects a degree of congruence of each of multiple scenes with respect to an input image made of a two-dimensional image, a depth image generating unit which generates, with respect to the input image, depth images each obtained by a technique corresponding to each of the scenes, a blending unit which blends the depth images, which are generated by the depth image generating unit and each generated by a technique corresponding to each of the scenes, at a blending ratio based on the degree of congruence of each of the scenes, to generate a blended depth image, and a three-dimensional image generating unit which generates a three-dimensional image, which can be viewed three-dimensionally, made of a left-eye image and a right-eye image generated by shifting each pixel of the input image using the blended depth image.Type: GrantFiled: July 5, 2012Date of Patent: June 30, 2015Assignee: Sony CorporationInventors: Nobuo Ueki, Hironori Mori, Takashi Kojima, Yuki Tokizaki, Kazuhiko Nishibori, Seiji Kimura
-
Publication number: 20140055634Abstract: There is provided an image processing device including a prediction tap acquisition unit that acquires, as prediction taps, values of a plurality of pixels decided according to a pixel of interest from a plurality of input images which are formed by pixels each having a single color component and have different array forms of the pixels, a coefficient data storage unit that stores data of coefficients multiplied by the respective acquired prediction taps, and a prediction calculation unit that computes, through calculation using the prediction taps and the coefficients, a value of the pixel of interest in an output image formed by pixels having a plurality of color components, which is an image obtained by demosaicing the input images.Type: ApplicationFiled: July 2, 2013Publication date: February 27, 2014Inventors: Yuki TOKIZAKI, Keisuke Chida
-
Publication number: 20130063424Abstract: Provided is an image processing device including a congruence degree detecting unit which detects a degree of congruence of each of multiple scenes with respect to an input image made of a two-dimensional image, a depth image generating unit which generates, with respect to the input image, depth images each obtained by a technique corresponding to each of the scenes, a blending unit which blends the depth images, which are generated by the depth image generating unit and each generated by a technique corresponding to each of the scenes, at a blending ratio based on the degree of congruence of each of the scenes, to generate a blended depth image, and a three-dimensional image generating unit which generates a three-dimensional image, which can be viewed three-dimensionally, made of a left-eye image and a right-eye image generated by shifting each pixel of the input image using the blended depth image.Type: ApplicationFiled: July 5, 2012Publication date: March 14, 2013Inventors: Nobuo UEKI, Hironori MORI, Takashi KOJIMA, Yuki TOKIZAKI, Kazuhiko NISHIBORI, Seiji KIMURA