Patents by Inventor Paul Brasnett

Paul Brasnett 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).

  • Publication number: 20200265595
    Abstract: A reduced noise image can be formed from a set of images. One of the images of the set can be selected to be a reference image and other images of the set are transformed such that they are better aligned with the reference image. A measure of the alignment of each image with the reference image is determined. At least some of the transformed images can then be combined using weights which depend on the alignment of the transformed image with the reference image to thereby form the reduced noise image. By weighting the images according to their alignment with the reference image the effects of misalignment between the images in the combined image are reduced. Furthermore, motion correction may be applied to the reduced noise image.
    Type: Application
    Filed: May 4, 2020
    Publication date: August 20, 2020
    Inventors: Marc Vivet, Paul Brasnett
  • Patent number: 10679363
    Abstract: A reduced noise image can be formed from a set of images. One of the images of the set can be selected to be a reference image and other images of the set are transformed such that they are better aligned with the reference image. A measure of the alignment of each image with the reference image is determined. At least some of the transformed images can then be combined using weights which depend on the alignment of the transformed image with the reference image to thereby form the reduced noise image. By weighting the images according to their alignment with the reference image the effects of misalignment between the images in the combined image are reduced. Furthermore, motion correction may be applied to the reduced noise image.
    Type: Grant
    Filed: January 23, 2018
    Date of Patent: June 9, 2020
    Assignee: Imagination Technologies Limited
    Inventors: Marc Vivet, Paul Brasnett
  • Publication number: 20190354844
    Abstract: Methods and systems for implementing a traditional computer vision algorithm as a neural network. The method includes: receiving a definition of the traditional computer vision algorithm that identifies a sequence of one or more traditional computer vision algorithm operations; mapping each of the one or more traditional computer vision algorithm operations to a set of one or more neural network primitives that is mathematically equivalent to that traditional computer vision algorithm operation; linking the one or more network primitives mapped to each traditional computer vision algorithm operation according to the sequence to form a neural network representing the traditional computer vision algorithm; and configuring hardware logic capable of implementing a neural network to implement the neural network that represents the traditional computer vision algorithm.
    Type: Application
    Filed: May 21, 2019
    Publication date: November 21, 2019
    Inventors: Paul Brasnett, Daniel Valdez Balderas, Cagatay Dikici, Szabolcs Cséfalvay, David Hough, Timothy Smith, James Imber
  • Publication number: 20190087718
    Abstract: Hardware implementations of DNNs and related methods with a variable output data format. Specifically, in the hardware implementations and methods described herein the hardware implementation is configured to perform one or more hardware passes to implement a DNN wherein during each hardware pass the hardware implementation receives input data for a particular layer, processes that input data in accordance with the particular layer (and optionally one or more subsequent layers), and outputs the processed data in a desired format based on the layer, or layers, that are processed in the particular hardware pass. In particular, when a hardware implementation receives input data to be processed, the hardware implementation also receives information indicating the desired format for the output data of the hardware pass and the hardware implementation is configured to, prior to outputting the processed data convert the output data to the desired format.
    Type: Application
    Filed: September 20, 2018
    Publication date: March 21, 2019
    Inventors: Chris Martin, David Hough, Paul Brasnett, Cagatay Dikici, James Imber, Clifford Gibson
  • Publication number: 20190026857
    Abstract: In an example method and system, image data to an image processing module. Image data is read from memory into a down-scaler, which down-scales the image data to a first resolution, which is stored in a first buffer. A region of image data which the image processing module will request is predicted, and image data corresponding to at least part of the predicted region of image data is stored in a first buffer, in a second resolution, higher than the first. When a request for image data is received, it is then determined whether image data corresponding to the requested image data is in the second buffer, and if so, then image data is provided to the image processing module from the second buffer. If not, then image data from the first buffer is up-scaled, and the up-scaled image data is provided to the image processing module.
    Type: Application
    Filed: September 21, 2018
    Publication date: January 24, 2019
    Inventors: Paul Brasnett, Jonathan Diggins, Steven Fishwick, Stephen Morphet
  • Patent number: 10109032
    Abstract: In an example method and system, image data to an image processing module. Image data is read from memory into a down-scaler, which down-scales the image data to a first resolution, which is stored in a first buffer. A region of image data which the image processing module will request is predicted, and image data corresponding to at least part of the predicted region of image data is stored in a first buffer, in a second resolution, higher than the first. When a request for image data is received, it is then determined whether image data corresponding to the requested image data is in the second buffer, and if so, then image data is provided to the image processing module from the second buffer. If not, then image data from the first buffer is up-scaled, and the up-scaled image data is provided to the image processing module.
    Type: Grant
    Filed: March 13, 2013
    Date of Patent: October 23, 2018
    Assignee: Imagination Technologies Limted
    Inventors: Paul Brasnett, Jonathan Diggins, Steven Fishwick, Stephen Morphet
  • Patent number: 10055639
    Abstract: A data processing system for performing face detection on a stream of frames of image data, the data processing system comprising: a skin patch identifier configured to identify one or more patches of skin color in a first frame and characterize each patch in the first frame using a respective patch construct of a predefined shape; a first search tile generator configured to generate one or more first search tiles from the one or more patch constructs; and a face detector configured to detect faces in the stream by performing face detection in one or more frames of the stream within the first search tiles.
    Type: Grant
    Filed: March 21, 2017
    Date of Patent: August 21, 2018
    Assignee: Imagination Technologies Limited
    Inventors: Szabolcs Cséfalvay, Paul Brasnett
  • Publication number: 20180227465
    Abstract: An interlaced video signal can include content of different types, such as interlaced content and progressive content. The progressive content may have different cadences according to the ratio between the frame rate of the progressive content and the field rate of the interlaced video signal. Cadence analysis is performed to identify the cadence of the video signal and/or to determine field pairings when progressive content is included. As described herein, motion information (e.g. motion vectors) for blocks of fields of a video signal can be used for the cadence analysis. The use of motion information provides a robust method of performing cadence analysis.
    Type: Application
    Filed: April 9, 2018
    Publication date: August 9, 2018
    Inventor: Paul Brasnett
  • Publication number: 20180150959
    Abstract: A reduced noise image can be formed from a set of images. One of the images of the set can be selected to be a reference image and other images of the set are transformed such that they are better aligned with the reference image. A measure of the alignment of each image with the reference image is determined. At least some of the transformed images can then be combined using weights which depend on the alignment of the transformed image with the reference image to thereby form the reduced noise image. By weighting the images according to their alignment with the reference image the effects of misalignment between the images in the combined image are reduced. Furthermore, motion correction may be applied to the reduced noise image.
    Type: Application
    Filed: January 23, 2018
    Publication date: May 31, 2018
    Inventors: Marc Vivet, Paul Brasnett
  • Patent number: 9973661
    Abstract: An interlaced video signal can include content of different types, such as interlaced content and progressive content. The progressive content may have different cadences according to the ratio between the frame rate of the progressive content and the field rate of the interlaced video signal. Cadence analysis is performed to identify the cadence of the video signal and/or to determine field pairings when progressive content is included. As described herein, motion information (e.g. motion vectors) for blocks of fields of a video signal can be used for the cadence analysis. The use of motion information provides a robust method of performing cadence analysis.
    Type: Grant
    Filed: May 1, 2015
    Date of Patent: May 15, 2018
    Assignee: Imagination Technologies Limited
    Inventor: Paul Brasnett
  • Patent number: 9760997
    Abstract: A reduced noise image can be formed from a set of images. One of the images of the set can be selected to be a reference image and other images of the set are transformed such that they are better aligned with the reference image. A measure of the alignment of each image with the reference image is determined. At least some of the transformed images can then be combined using weights which depend on the alignment of the transformed image with the reference image to thereby form the reduced noise image. By weighting the images according to their alignment with the reference image the effects of misalignment between the images in the combined image are reduced. Furthermore, motion correction may be applied to the reduced noise image.
    Type: Grant
    Filed: March 14, 2016
    Date of Patent: September 12, 2017
    Assignee: Imagination Technologies Limited
    Inventors: Marc Vivet, Paul Brasnett
  • Publication number: 20170193281
    Abstract: A data processing system for performing face detection on a stream of frames of image data, the data processing system comprising: a skin patch identifier configured to identify one or more patches of skin colour in a first frame and characterise each patch in the first frame using a respective patch construct of a predefined shape; a first search tile generator configured to generate one or more first search tiles from the one or more patch constructs; and a face detector configured to detect faces in the stream by performing face detection in one or more frames of the stream within the first search tiles.
    Type: Application
    Filed: March 21, 2017
    Publication date: July 6, 2017
    Inventors: Szabolcs Cséfalvay, Paul Brasnett
  • Patent number: 9633249
    Abstract: A data processing system for performing face detection on a stream of frames of image data, the data processing system comprising: a skin patch identifier configured to identify one or more patches of skin color in a first frame and characterize each patch in the first frame using a respective patch construct of a predefined shape; a first search tile generator configured to generate one or more first search tiles from the one or more patch constructs; and a face detector configured to detect faces in the stream by performing face detection in one or more frames of the stream within the first search tiles.
    Type: Grant
    Filed: October 23, 2014
    Date of Patent: April 25, 2017
    Assignee: Imagination Technologies Limited
    Inventors: Szabolcs Cséfalvay, Paul Brasnett
  • Patent number: 9525869
    Abstract: An image processor comprises an image pre-processing block and an encoder processing block for processing and encoding an image. The image pre-processing block receives image data and processes it to provide an image comprising image sections which each comprise pixels. For each of the image sections, the pixels are analyzed to estimate an indication of the complexity of the image section, and metadata is determined based on the estimated complexity indications of the image sections. The metadata is passed to the encoder processing block which uses it to determine a quantization level for use in encoding the image. The encoder processing block can then encode the image using the determined quantization level. Conveniently, the image pre-processing block 106 processes the image data to provide the image, and therefore has access to the image which it can analyze to determine the metadata without requiring a separate read operation of the image.
    Type: Grant
    Filed: April 28, 2014
    Date of Patent: December 20, 2016
    Assignee: Imagination Technologies Limited
    Inventors: Jonathan Diggins, Paul Brasnett
  • Patent number: 9525870
    Abstract: A quantization level is determined for use by an encoder in encoding an image in accordance with a target number of bits. For each section of the image, the pixels are analyzed to estimate the complexity of the image section. For each of a plurality of candidate quantization levels, a relationship and the estimated complexity of the image sections are used to estimate the number of bits that would be generated by encoding the image with the encoder using the respective candidate quantization level, and based thereon one of the candidate quantization levels is selected. The relationship is a function of the quantization level used by the encoder, and is for use in relating the complexity of an image section to the number of bits that would be generated by encoding that image section with the encoder. The encoder uses the selected quantization level in encoding the image.
    Type: Grant
    Filed: April 28, 2014
    Date of Patent: December 20, 2016
    Assignee: Imagination Technologies Limited
    Inventors: Jonathan Diggins, Paul Brasnett
  • Publication number: 20160267640
    Abstract: A reduced noise image can be formed from a set of images. One of the images of the set can be selected to be a reference image and other images of the set are transformed such that they are better aligned with the reference image. A measure of the alignment of each image with the reference image is determined. At least some of the transformed images can then be combined using weights which depend on the alignment of the transformed image with the reference image to thereby form the reduced noise image. By weighting the images according to their alignment with the reference image the effects of misalignment between the images in the combined image are reduced. Furthermore, motion correction may be applied to the reduced noise image.
    Type: Application
    Filed: March 14, 2016
    Publication date: September 15, 2016
    Inventors: Marc Vivet, Paul Brasnett
  • Publication number: 20160267660
    Abstract: A reduced noise image can be formed from a set of images. One of the images of the set can be selected to be a reference image and other images of the set are transformed such that they are better aligned with the reference image. A measure of the alignment of each image with the reference image is determined. At least some of the transformed images can then be combined using weights which depend on the alignment of the transformed image with the reference image to thereby form the reduced noise image. By weighting the images according to their alignment with the reference image the effects of misalignment between the images in the combined image are reduced. Furthermore, motion correction may be applied to the reduced noise image.
    Type: Application
    Filed: March 14, 2016
    Publication date: September 15, 2016
    Inventors: Marc Vivet, Paul Brasnett
  • Patent number: 9430820
    Abstract: A technique is described for combining several image sources into a single output image or video sequence. For a given pixel of the output image, pixel values are received from the image sources, and a matrix of distance measures between the pixel values (e.g. based on their colors) is computed. Clusters of pixel values are formed using the distance measures, and a score determined for each. One of the clusters is selected according to the scores, and used to derive an output pixel value. In an example, the clusters are formed using an iterative process where the closest pairs of pixel values or clusters are merged to form new clusters up to a size threshold. Examples are described for scoring the clusters based on model-based weighting or cluster size. Examples are also described for a rule-based cluster selection system. A composite image generator implementing the technique is also described.
    Type: Grant
    Filed: January 17, 2014
    Date of Patent: August 30, 2016
    Assignee: Imagination Technologies Limited
    Inventors: Paul Brasnett, Jonathan Diggins
  • Patent number: 9349037
    Abstract: A data processing system for performing face detection on a stream of frames of image data, the data processing system comprising: a face detector configured to detect a first face candidate in a first frame by performing face detection within first search tiles defined for the first frame; a color measurement unit configured to calculate a set of color parameters including an average color of the first face candidate expressed according to a predefined color space; a transformation unit configured to: transform a second frame into the predefined color space, one of the axes of the color space being substantially oriented in the direction of maximum variation according to a predetermined distribution of skin color; and form a skin color probability map for the second frame by calculating the probability that a given color is a skin color from a measure of the color space distance of that color from the calculated average color; and a search tile generator configured to generate second search tiles based on th
    Type: Grant
    Filed: October 23, 2014
    Date of Patent: May 24, 2016
    Assignee: Imagination Technologies Limited
    Inventors: Szabolcs Cséfalvay, Paul Brasnett
  • Publication number: 20150319406
    Abstract: An interlaced video signal can include content of different types, such as interlaced content and progressive content. The progressive content may have different cadences according to the ratio between the frame rate of the progressive content and the field rate of the interlaced video signal. Cadence analysis is performed to identify the cadence of the video signal and/or to determine field pairings when progressive content is included. As described herein, motion information (e.g. motion vectors) for blocks of fields of a video signal can be used for the cadence analysis. The use of motion information provides a robust method of performing cadence analysis.
    Type: Application
    Filed: May 1, 2015
    Publication date: November 5, 2015
    Inventor: Paul Brasnett