公开(公告)号：US20210117683A1

公开(公告)日：2021-04-22

申请号：US16655212

申请日：2019-10-16

Applicant: Realtek Singapore Private Limited

Inventor： Tien Ping Chua ,  Zhengyu Li ,  Ruchi Mangesh Dhamnaskar ,  Chen-Feng Kuo

IPC: G06K9/00 ,  G06T7/246 ,  G06T7/254 ,  H04N19/587 ,  H04N19/132

Abstract: An object localization system including an object detection module configured to detect an object in a current frame with reference to a preceded frame, and an object localization module configured to identify a location of the object according to the segment. The object detection module includes a difference module for computing differences between the preceded frame and the current frame at a same location to generate a difference frame, a selected block detection module for identifying a selected block of the difference frame according to a predetermined minimum difference, a segment generation module for generating a segment of the current frame.

公开(公告)号：US11188756B2

公开(公告)日：2021-11-30

申请号：US16655212

申请日：2019-10-16

Applicant: Realtek Singapore Private Limited

Inventor： Tien Ping Chua ,  Zhengyu Li ,  Ruchi Mangesh Dhamnaskar ,  Chen-Feng Kuo

IPC: G06K9/00 ,  G06T7/246 ,  G06T7/254 ,  H04N19/132 ,  H04N19/587

Abstract: An object localization system including an object detection module configured to detect an object in a current frame with reference to a preceded frame, and an object localization module configured to identify a location of the object according to the segment. The object detection module includes a difference module for computing differences between the preceded frame and the current frame at a same location to generate a difference frame, a selected block detection module for identifying a selected block of the difference frame according to a predetermined minimum difference, a segment generation module for generating a segment of the current frame.

公开(公告)号：US20230206699A1

公开(公告)日：2023-06-29

申请号：US17695196

申请日：2022-03-15

Applicant: Realtek Singapore Private Limited

Inventor： Tien-Ping Chua ,  Chen-Feng Kuo ,  Ruchi Mangesh Dhamnaskar

IPC: G06V40/40 ,  G06V40/16 ,  G06T7/246 ,  G06T3/60

CPC classification number: G06V40/40 ,  G06V40/168 ,  G06T7/248 ,  G06T3/608 ,  G06T2207/30201

Abstract: A liveness detection method includes: obtaining multiple first feature points and multiple second feature points according to a first image, a second image, and a feature point process, wherein the first feature points include two first fixed feature points and at least one first variable feature point, and the second feature points include two second fixed feature points and at least one second variable point; obtaining a first transform function according to the first fixed feature points and the second fixed feature points; obtaining at least one check feature point according to the first transform function and the first variable feature point(s); and determining whether the second image is a spoofing image according to the check feature point(s) and the second variable point(s).

公开(公告)号：US11527057B2

公开(公告)日：2022-12-13

申请号：US17037705

申请日：2020-09-30

Applicant: Realtek Singapore Private Limited

Inventor： Tien Ping Chua ,  Chen-Feng Kuo ,  Ruchi Mangesh Dhamnaskar ,  Zhengyu Li ,  Sin Yi Heung

IPC: G06V10/00 ,  G06V10/75 ,  G06K9/62 ,  G06T7/194 ,  G06V20/62 ,  G06V30/10

Abstract: A license plate recognition system includes an image capturing module, a license plate detection module, a segment extraction module, a character classification module, and a character recognition module. The image capturing module is for capturing an image. The license plate detection module is for receiving the image and to identify a license plate in the image. The segment extraction module is for extracting a sequence of character segments on the license plate. The character classification module is for computing a probability of each possible character in each character segment. The character recognition module is for identifying permissible characters for the each character segment according to a syntax of the sequence of character segments, and to identify a character having a highest probability among the permissible characters as a selected character for the each character segment.

公开(公告)号：US20220101037A1

公开(公告)日：2022-03-31

申请号：US17037705

申请日：2020-09-30

Applicant: Realtek Singapore Private Limited

Inventor： Tien Ping Chua ,  Chen-Feng Kuo ,  Ruchi Mangesh Dhamnaskar ,  Zhengyu Li ,  Sin Yi Heung

IPC: G06K9/62 ,  G06T7/194

Abstract: A license plate recognition system includes an image capturing module, a license plate detection module, a segment extraction module, a character classification module, and a character recognition module. The image capturing module is for capturing an image. The license plate detection module is for receiving the image and to identify a license plate in the image. The segment extraction module is for extracting a sequence of character segments on the license plate. The character classification module is for computing a probability of each possible character in each character segment. The character recognition module is for identifying permissible characters for the each character segment according to a syntax of the sequence of character segments, and to identify a character having a highest probability among the permissible characters as a selected character for the each character segment.