利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

2038 条记录 (耗时 0.029 秒)

    Methods and apparatus for enhancing optical images and parametric databases
    1.
    发明授权
    Methods and apparatus for enhancing optical images and parametric databases 有权

    公开(公告)号：US11967046B2

    公开(公告)日：2024-04-23

    申请号：US17065515

    申请日：2020-10-07

    申请人： Michael Edwin Stewart

    发明人： Michael Edwin Stewart

    IPC分类号： G06T5/00 ,  G06F16/51 ,  H04N1/60

    CPC分类号： G06T5/002 ,  G06F16/51 ,  G06T5/003 ,  G06T5/008 ,  H04N1/6027 ,  G06T2207/20016 ,  G06T2207/20048

    摘要： Methods and apparatus for enhancing optical images and parametric databases are disclosed. In an exemplary embodiment, a method includes identifying an image and deconstructing the image into a frequency-based spatial domain representation utilizing a pyramidal data structure including a plurality of levels on a frequency-by-frequency basis. The method also includes modifying the frequency-based spatial domain representation to generate a modified frequency-based spatial domain representation, reconstructing an enhanced image from the modified frequency-based spatial domain representation, and returning the enhanced image. In an exemplary embodiment, an apparatus includes a deconstructor that deconstructs an image into a frequency-based spatial domain representation utilizing a pyramidal data structure including a plurality of levels on a frequency-by-frequency basis and a modifier that modifies the frequency-based spatial domain representation to generate a modified representation. The apparatus also includes a reconstructor that reconstructs an enhanced image from the modified representation and returns the enhanced image.

    Image processing circuit and associated image processing method
    3.
    发明授权
    Image processing circuit and associated image processing method 有权

    公开(公告)号：US11922608B2

    公开(公告)日：2024-03-05

    申请号：US17013892

    申请日：2020-09-08

    申请人： Realtek Semiconductor Corp.

    发明人： Yu-Shiang Huang

    IPC分类号： G06T5/00 ,  G06T5/50

    CPC分类号： G06T5/008 ,  G06T5/003 ,  G06T5/50 ,  G06T2207/20224

    摘要： The present invention provides an image processing circuit including a receiving circuit, a reference value calculating circuit, a center luminance value calculating circuit and an output circuit. In the operations of the image processing circuit, the receiving circuit receives image data. The reference value calculating circuit determines a first reference value and a second reference value corresponding to a plurality of pixels of the image data. The center luminance value calculating circuit refers to the first reference value and the second reference value to generate a center luminance value. The output circuit determines output luminance values of the plurality of pixel values according to the image data, the first reference value and the second reference value.

    FINDING THE SEMANTIC REGION OF INTEREST IN IMAGES
    4.
    发明公开
    FINDING THE SEMANTIC REGION OF INTEREST IN IMAGES 审中-公开

    公开(公告)号：US20240054748A1

    公开(公告)日：2024-02-15

    申请号：US17884607

    申请日：2022-08-10

    申请人： Avid Technology, Inc.

    发明人： Robert Gonsalves

    IPC分类号： G06V10/25 ,  G06T7/70 ,  G06T7/11 ,  G06T5/00 ,  G06T9/00

    CPC分类号： G06V10/25 ,  G06T7/70 ,  G06T7/11 ,  G06T5/008 ,  G06T9/00 ,  G06V2201/07 ,  G06T2207/10016 ,  G06T2207/20081

    摘要： Objects within an image are assigned a semantic interest that is indicative of their importance to the image as a whole. The objects are detected automatically, and sub-images that span each of the objects are excerpted from the image. An image embedding is determined for each of the sub-images as well as for the whole image by using an image encoder implemented as a trained multi-modal neural network. The degree of similarity between the image embeddings of a sub-image and that of the whole image is used as a measure of the semantic importance of the object portrayed in the sub-image. Objects of high semantic importance comprise the semantic regions of interest of the image. Knowledge of such regions may be used to enhance and improve the efficiency of downstream image-processing tasks, such as image compression, pan and scan, and contrast enhancement.

    Method and apparatus for processing an image
    10.
    发明授权
    Method and apparatus for processing an image 有权

    公开(公告)号：US11816817B2

    公开(公告)日：2023-11-14

    申请号：US17831032

    申请日：2022-06-02

    申请人： SAMSUNG ELECTRONICS CO., LTD.

    发明人： Kyungmin Lim ,  Seunghyun Lee ,  Jaesung Lee ,  Sunil Lee

    IPC分类号： G06T5/00 ,  G06T5/20 ,  G09G3/00

    CPC分类号： G06T5/009 ,  G06T5/008 ,  G06T5/20 ,  G09G3/001 ,  G06T2207/20208 ,  G09G2320/029 ,  G09G2320/0209 ,  G09G2320/0276

    摘要： A method includes: obtaining a plurality of view images; identifying a representative value from among difference values between values of a plurality of sub-pixels corresponding to a first position in the plurality of view images and an intermediate value of a bit range of a display; determining filtering strength corresponding to the representative value, based on a correspondence map indicating a correspondence relationship between filtering strength and a difference value between a value of a sub-pixel and the intermediate value; and applying a filter having the determined filtering strength to the plurality of sub-pixels corresponding to the first position, wherein a value resulting from applying the filter having the determined filtering strength to the plurality of sub-pixels corresponding to the first position is included in a range of sub-pixel values according to the bit range of the display.