中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

50 records (took 0.017 seconds)

    Method for processing image using fully connected convolutional neural network and circuit system
    21.
    发明授权
    Method for processing image using fully connected convolutional neural network and circuit system 有权

    公开(公告)号：US11423635B2

    公开(公告)日：2022-08-23

    申请号：US16876294

    申请日：2020-05-18

    Applicant: REALTEK SEMICONDUCTOR CORP.

    Inventor： Chun-Chang Wu ,  Shih-Tse Chen

    IPC: G06V10/44 ,  G06K9/62 ,  G06T3/40 ,  G06T7/60

    Abstract: A method for processing image using fully connected convolutional neural network and a circuit system are provided. The method is operated using fully connected convolutional neural network (CNN) and performed by the circuit system. In the method, an image with a length, a width and an aspect ratio is obtained. A reference image closest to the input image can be obtained by querying a lookup table that records multiple reference images with various sizes to be adapted to the fully connected CNN. The input image can be resized as the closest reference image. A convolution operation is then performed onto the resized image, and a feature cube is formed after multiple operations of convolution. The feature cube is transformed to one-dimensional feature values that are configured to be inputted to a fully connected layer for fully connected operation. An output value of the fully connected CNN is generated.

    Consecutive thin edge detection system and method for enhancing a color filter array image
    23.
    发明授权
    Consecutive thin edge detection system and method for enhancing a color filter array image 有权
    连续薄边检测系统和增强滤色器阵列图像的方法

    公开(公告)号：US09147257B2

    公开(公告)日：2015-09-29

    申请号：US14489908

    申请日：2014-09-18

    Applicant: Realtek Semiconductor Corp.

    Inventor： Shih-Tse Chen ,  Wen-Tsung Huang

    IPC: G06K9/00 ,  G06K9/32 ,  G06T7/00 ,  G06K9/46

    CPC classification number: G06T7/0085 ,  G06K9/4604 ,  G06T7/13 ,  G06T2207/10024

    Abstract: A consecutive thin edge detection system and method for enhancing color filter array image is disclosed in the present invention. The consecutive thin edge detection system includes a consecutive thin edge detector, a color gradient estimator and a direction indicator. The consecutive thin edge detector receives a color pixel array including a plurality of color pixels and alternately sets each color pixel as a target pixel. The consecutive thin edge detector detects a difference value between a plurality of first green pixels and a plurality of second green pixels nearby a target pixel, and determines whether the target pixel comprises a consecutive thin edge feature or not according to the difference value. The plurality of first green pixels are in red pixel rows which comprises a plurality red pixels and the plurality of first green pixels, and the plurality of second green pixels are in a blue pixel row which comprises blue pixels and the plurality of second green pixels.

    Abstract translation: 在本发明中公开了连续的薄边缘检测系统和用于增强滤色器阵列图像的方法。 连续的薄边缘检测系统包括连续的薄边缘检测器，颜色梯度估计器和方向指示器。 连续薄边缘检测器接收包括多个彩色像素的彩色像素阵列，并且交替地将每个彩色像素设置为目标像素。 连续的薄边缘检测器检测多个第一绿色像素与目标像素附近的多个第二绿色像素之间的差值，并根据差值来确定目标像素是否包括连续的薄边缘特征。 多个第一绿色像素是包括多个红色像素和多个第一绿色像素的红色像素行，并且多个第二绿色像素处于包括蓝色像素和多个第二绿色像素的蓝色像素行中。

    IMAGE CORRECTION METHOD USING APPROXIMATELY NON-LINEAR REGRESSION APPROACH AND RELATED IMAGE CORRECTION CIRCUIT
    24.
    发明申请
    IMAGE CORRECTION METHOD USING APPROXIMATELY NON-LINEAR REGRESSION APPROACH AND RELATED IMAGE CORRECTION CIRCUIT 有权
    使用非线性回归方法和相关图像校正电路的图像校正方法

    公开(公告)号：US20140193079A1

    公开(公告)日：2014-07-10

    申请号：US13858101

    申请日：2013-04-08

    Applicant: REALTEK SEMICONDUCTOR CORP.

    Inventor： Shih-Tse Chen ,  Hao-Tien Chiang

    IPC: G06K9/52

    CPC classification number: G06T5/006

    Abstract: An image correction method arranged for processing an original image to obtain a corrected image includes steps: receiving the original image from an image sensor; regarding each pixel of the original image, calculating a horizontal distance and a vertical distance between the pixel and a reference point in the original image; determining a horizontal ratio parameter and a vertical ratio parameter according to the horizontal distance and the vertical distance between the pixel and the reference point in the original image; and performing an approximately non-linear regression calculation on the horizontal ratio parameter, the vertical ratio parameter and a coordinate of the pixel to obtain a position of the pixel in the corrected image.

    Abstract translation: 一种布置用于处理原始图像以获得校正图像的图像校正方法，包括以下步骤：从图像传感器接收原始图像; 关于原始图像的每个像素，计算原始图像中的像素和参考点之间的水平距离和垂直距离; 根据原始图像中的像素与参考点之间的水平距离和垂直距离确定水平比参数和垂直比率参数; 并且对水平比参数，垂直比参数和像素的坐标执行近似非线性回归计算，以获得校正图像中的像素的位置。

    Processing circuit and processing method applied to face recognition system
    27.
    发明授权
    Processing circuit and processing method applied to face recognition system 有权

    公开(公告)号：US11734956B2

    公开(公告)日：2023-08-22

    申请号：US17523930

    申请日：2021-11-11

    Applicant: Realtek Semiconductor Corp.

    Inventor： Chien-Hao Chen ,  Chao-Hsun Yang ,  Shih-Tse Chen

    IPC: G06K9/62 ,  G06V40/16 ,  G06F18/22 ,  G06V10/74

    CPC classification number: G06V40/172 ,  G06F18/22 ,  G06V10/761

    Abstract: The present invention provides a processing circuit applied to a face recognition system, which includes a characteristic value calculation module, a determination circuit and a threshold value calculation module. The characteristic value calculation module is used to receive an image and process the image to generate a specific characteristic value; when the face recognition system operates in a face recognition phase, the determination circuit calculates multiple differences each between the specific characteristic value and one of multiple reference characteristic values, and determines whether at least one of the multiple differences is lower than a threshold value to generate a determination result; and when the face recognition system operates in a face registration phase, the threshold value calculation module determines a new threshold value according to differences between the specific characteristic value and the multiple reference values, for updating the threshold value used by the determination circuit.

Patent Agency Ranking