公开(公告)号：US11651495B2

公开(公告)日：2023-05-16

申请号：US17123228

申请日：2020-12-16

Applicant: REALTEK SEMICONDUCTOR CORP.

Inventor： Yang-Ting Chou ,  Tsung-Hsuan Li ,  Shih-Tse Chen

IPC: G06T5/00 ,  G06T5/20 ,  G06T7/00 ,  G06T7/11 ,  G06T7/90

CPC classification number: G06T7/11 ,  G06T5/008 ,  G06T5/20 ,  G06T7/0002 ,  G06T7/90 ,  G06T2207/10024 ,  G06T2207/30168

Abstract: A method and a system for image correction are provided. The system includes an image processor that performs the method for image correction when receiving an input image. In the method, an overexposed area within the image is determined. The channel values of pixels in the overexposed area are applied with corresponding weights. An automatic white balance process is performed on the channel values of pixels in the overexposed area according to an expectation of low saturation in the overexposed area. Besides a first channel value of each of the pixels, a second channel value and a third channel value of the pixel can be estimated according to the channel values of periphery pixels. A correction value overexposed of the first channel value of the current pixel can be calculated according to the corresponding weights of the pixels in the overexposed area.

公开(公告)号：US11275966B2

公开(公告)日：2022-03-15

申请号：US16790979

申请日：2020-02-14

Applicant: REALTEK SEMICONDUCTOR CORP.

Inventor： Chun-Chang Wu ,  Shih-Tse Chen

IPC: G06K9/62 ,  G06K9/54 ,  G06N3/04

Abstract: A calculation method using pixel-channel shuffle convolutional neural network is provided. In the method, an operating system receives original input data. The original input data is pre-processed by a pixel shuffle process to be separated into multiple groups in order to minimize dimension of the data. The multiple groups of data are then processed by a channel shuffle process so as to form multiple groups of new input data selected for convolution operation. The unselected data are abandoned. Therefore, the dimension of the input data can be much effectively minimized. A multiplier-accumulator of the operating system is used to execute convolution operation using a convolution kernel and the multiple new groups of input data. Multiple output data are then produced.

公开(公告)号：US11200422B2

公开(公告)日：2021-12-14

申请号：US16929189

申请日：2020-07-15

Applicant: REALTEK SEMICONDUCTOR CORP.

Inventor： Wan-Ju Tang ,  Tsung-Hsuan Li ,  Shih-Tse Chen

IPC: G06K9/00 ,  G06K9/62 ,  G06T7/20 ,  G06F9/54 ,  G06K9/40

Abstract: A method and a system for pixel channel imbalance compensation for an image sensing circuit are provided. The system includes an image acquisition circuit having a lens, a color filter and an image sensor and a processing circuit. In the method performed by the processing circuit, a second frame image is retrieved from a motion image, and a first frame image that has undergone noise reduction can be retrieved from a memory. Motion detection is performed between the frames by comparing the first frame image and the second frame image. The motion detection is referred to as a reference for determining how to perform 3D noise reduction. A compensation value for channel imbalance between the adjacent channels can be estimated based on the image under noise reduction in a same buffer. While the pixel channel imbalance is compensated, the image is then restored by an interpolation method.

公开(公告)号：US11062429B2

公开(公告)日：2021-07-13

申请号：US16749688

申请日：2020-01-22

Applicant: REALTEK SEMICONDUCTOR CORP.

Inventor： Wan-Ju Tang ,  Tsung-Hsuan Li ,  Shih-Tse Chen

IPC: G06T5/00 ,  G06T5/10 ,  G10L21/0232 ,  G06T5/20

Abstract: A denoising method based on a signal-to-noise ratio (SNR), which includes: obtaining a current input coefficient; obtaining a current noise standard deviation by querying a first relationship table; querying a second relationship table according to the current noise standard deviation and the current input coefficient to obtain a current slope corresponding to the current input coefficient; generating a current output coefficient by multiplying the current input coefficient and a compression magnification function; and calculating the current output coefficient by substituting the current noise standard deviation, the current input coefficient, and the current slope.

公开(公告)号：US20210182588A1

公开(公告)日：2021-06-17

申请号：US16865409

申请日：2020-05-03

Applicant: Realtek Semiconductor Corp.

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

IPC: G06K9/20 ,  G06K9/62

Abstract: An object detection method and an associated electronic device are provided, wherein the object detection method includes: utilizing an image processing circuit to determine whether motion occurs in an image to generate a determination result; selectively utilizing a specific bounding box to identify a target object to generate an identification result according to the determination result, wherein the specific bounding box represents a location of the target object in a previous image; and selectively updating information of the specific bounding box according to the identification result.

公开(公告)号：US20210074001A1

公开(公告)日：2021-03-11

申请号：US16744208

申请日：2020-01-16

Applicant: Realtek Semiconductor Corp.

Inventor： Shang-Lun Chan ,  Chao-Hsun Yang ,  Chun-Chang Wu ,  Shih-Tse Chen

IPC: G06T7/215 ,  G06T7/70 ,  G06T7/194 ,  G06T5/30 ,  G06T7/60 ,  G06T3/40

Abstract: A motion detection method includes acquiring a raw image, detecting a motion object image according to the raw image by using a motion detector, cropping the raw image to generate a sub-image according to the motion object image, and inputting the sub-image to a processor for determining if a motion object of the sub-image matches with a detection category. The processor includes a neural network. The shape of the sub-image is a polygonal shape.

公开(公告)号：US20200097761A1

公开(公告)日：2020-03-26

申请号：US16407200

申请日：2019-05-09

Applicant: Realtek Semiconductor Corp.

Inventor： Chun-Chang Wu ,  Shih-Tse Chen

IPC: G06K9/62

Abstract: An image processing circuit includes a receiving circuit, a feature fetching module and a decision circuit. In the operations of the image processing circuit, the receiving circuit is configured to receive image data. The feature fetching module is configured to use a multi-topological-convolutional network to fetch the features of the image data, to generate a plurality of image features determined by the characteristics and weights of the convolution filter, where the image features may be smooth features or edge features. In the present invention, the convolution filters used by the feature fetching module are not limited by a square convention filter, and the convolution filters may include the multiple topological convolutional network having non-square convolution filters. By using the multiple topological convolutional network of the present invention, the feature fetching module can fetch the rich image features for identifying the contents of the image data.

公开(公告)号：US20150373235A1

公开(公告)日：2015-12-24

申请号：US14748248

申请日：2015-06-24

Applicant: Realtek Semiconductor Corp.

Inventor： Hao-Tien Chiang ,  Shih-Tse Chen

IPC: H04N5/213 ,  H04N5/235

CPC classification number: H04N5/213 ,  G06T5/002 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/20182 ,  H04N5/21 ,  H04N5/217 ,  H04N5/2352

Abstract: A decryption engine includes an update circuit, a key generator, a decryption circuit and a detection circuit. The update circuit generates a first updating information based on a premise of that a currently received frame is encrypted, and generates a second updating information based on a premise of that the currently received frame is non-encrypted. The key generator produces a first key according to the first updating information, and produces a second key according to the second updating information. The decryption circuit generates a first decrypted frame according to the first key and the currently received frame, and generates a second decrypted frame according to the second key and the currently received frame. The detection circuit detects whether the currently received frame is decrypted according to the first decrypted frame and the second decrypted frame, to generate an encryption detection result.

Abstract translation: 解密引擎包括更新电路，密钥生成器，解密电路和检测电路。 更新电路基于当前接收到的帧被加密的前提产生第一更新信息，并且基于当前接收到的帧未被加密的前提生成第二更新信息。 密钥发生器根据第一更新信息产生第一密钥，并根据第二更新信息产生第二密钥。 解密电路根据第一密钥和当前接收到的帧生成第一解密帧，并根据第二密钥和当前接收的帧生成第二解密帧。 检测电路根据第一解密帧和第二解密帧来检测当前接收到的帧是否被解密，以产生加密检测结果。

公开(公告)号：US09008421B2

公开(公告)日：2015-04-14

申请号：US14148676

申请日：2014-01-06

Applicant: Realtek Semiconductor Corp.

Inventor： Shih-Tse Chen ,  Wen-Tsung Huang

IPC: G06K9/00 ,  G06T5/20 ,  G06T7/00

CPC classification number: G06T5/20 ,  H04N9/045 ,  H04N9/646

Abstract: An image processing method includes: receiving image data from a frame buffer, wherein each pixel of the image data has only one color information; estimating four second color information corresponding to up, down, left, and right sides of the target pixel respectively according to a first color information of the target pixel per se and color information of the neighboring pixels for a target pixel of the image data; calculating four color difference gradients corresponding to up, down, left, and right sides of the target pixel respectively according to the four second color information of the target pixel; determining an edge texture characteristic of the target pixel according to the four color difference gradients of the target pixel; and determining whether to modify the bit value of the first color information of the target pixel stored in a frame buffer according to an edge texture characteristic of the target pixel.

Abstract translation: 图像处理方法包括：从帧缓冲器接收图像数据，其中图像数据的每个像素仅具有一个颜色信息; 根据目标像素本身的第一颜色信息分别对应于目标像素的上，下，左和右侧的四个第二颜色信息，以及针对图像数据的目标像素的相邻像素的颜色信息; 根据目标像素的四个第二颜色信息分别计算与目标像素的上，下，左和右两侧对应的四个色差梯度; 根据目标像素的四个色差梯度确定目标像素的边缘纹理特征; 以及根据所述目标像素的边缘纹理特性来确定是否修改存储在帧缓冲器中的所述目标像素的所述第一颜色信息的比特值。

公开(公告)号：US20140198985A1

公开(公告)日：2014-07-17

申请号：US14148676

申请日：2014-01-06

Applicant: Realtek Semiconductor Corp.

Inventor： Shih-Tse Chen ,  Wen-Tsung Huang

IPC: G06T5/20 ,  G06T7/00

CPC classification number: G06T5/20 ,  H04N9/045 ,  H04N9/646

Abstract: An image processing method includes: receiving image data from a frame buffer, wherein each pixel of the image data has only one color information; estimating four second color information corresponding to up, down, left, and right sides of the target pixel respectively according to a first color information of the target pixel per se and color information of the neighboring pixels for a target pixel of the image data; calculating four color difference gradients corresponding to up, down, left, and right sides of the target pixel respectively according to the four second color information of the target pixel; determining an edge texture characteristic of the target pixel according to the four color difference gradients of the target pixel; and determining whether to modify the bit value of the first color information of the target pixel stored in a frame buffer according to an edge texture characteristic of the target pixel.

Abstract translation: 图像处理方法包括：从帧缓冲器接收图像数据，其中图像数据的每个像素仅具有一个颜色信息; 根据目标像素本身的第一颜色信息分别对应于目标像素的上，下，左和右侧的四个第二颜色信息，以及针对图像数据的目标像素的相邻像素的颜色信息; 根据目标像素的四个第二颜色信息分别计算与目标像素的上，下，左和右两侧对应的四个色差梯度; 根据目标像素的四个色差梯度确定目标像素的边缘纹理特征; 以及根据所述目标像素的边缘纹理特性来确定是否修改存储在帧缓冲器中的所述目标像素的所述第一颜色信息的比特值。