公开(公告)号：US20250069427A1

公开(公告)日：2025-02-27

申请号：US18766583

申请日：2024-07-08

Applicant: ADVANCED VIEW INC.

Inventor： CHUNG-HSING CHEN

IPC: G06V30/19 ,  G06V10/82 ,  G06V30/148 ,  G06V30/162 ,  G06V30/166 ,  G06V30/18

Abstract: The invention provides an English word image recognition method, mainly loading a to-be-recognized image and performing a one-dimensional convolutional neural network operation and a fully connected operation processing to generate a feature map, outputting the feature map by a bidirectional long short-term memory (LSTM) network and performing a fully connected operation to generate a feature map, then performing a probability recognition and outputting a probabilistic string, and then recognizing the probabilistic string and outputting a word recognition result to solve the problem of producing a large amount of operation in the conventional two-dimensional recognition operation, thereby achieving efficacies of reducing costs of recognition equipment and enabling fast and accurate recognition.

公开(公告)号：US12230045B2

公开(公告)日：2025-02-18

申请号：US17901538

申请日：2022-09-01

Applicant: ADVANCED VIEW INC.

Inventor： Chung-Hsing Chen

IPC: G06V30/19 ,  G06T7/12 ,  G06T7/66 ,  G06T7/73 ,  G06V10/82

Abstract: The invention provides an English char image recognition method mainly generating a rectangular coordinate frame from a loaded English character image, finding a gravity center in the rectangular coordinate frame, obtaining feature points on the rectangular coordinate frame and around the gravity center, performing one-dimensional convolutional operation and processing on the feature points to generate six layer feature maps, and generating a character recognition result from the six layer feature maps to solve the problem of generating a large amount of computation in conventional two-dimensional recognition operation, thereby achieving an efficacy of reducing recognition equipment costs and enabling fast and accurate recognition.

公开(公告)号：US20230146241A1

公开(公告)日：2023-05-11

申请号：US17901538

申请日：2022-09-01

Applicant: ADVANCED VIEW INC.

Inventor： CHUNG-HSING CHEN

IPC: G06V30/19 ,  G06T7/12 ,  G06V10/82 ,  G06T7/66 ,  G06T7/73

CPC classification number: G06V30/19127 ,  G06T7/12 ,  G06T7/66 ,  G06T7/73 ,  G06V10/82 ,  G06V30/19173 ,  G06T2207/20021 ,  G06T2207/20076 ,  G06T2207/20084

Abstract: The invention provides an English char image recognition method mainly generating a rectangular coordinate frame from a loaded English character image, finding a gravity center in the rectangular coordinate frame, obtaining feature points on the rectangular coordinate frame and around the gravity center, performing one-dimensional convolutional operation and processing on the feature points to generate six layer feature maps, and generating a character recognition result from the six layer feature maps to solve the problem of generating a large amount of computation in conventional two-dimensional recognition operation, thereby achieving an efficacy of reducing recognition equipment costs and enabling fast and accurate recognition.