METHOD FOR INTELLIGENT RECOGNITION OF SHIP OUTFITTING ITEMS, AND COMPUTER DEVICE

WIPO Patent Application WO/2024/078112

A1

The present invention provides a method, directed at ship outfitting warehouses, for the intelligent recognition of ship outfitting items. The recognition method comprises: an image acquisition step: acquiring a large number of images containing or not containing a target object; an image preprocessing step: processing the acquired images using image linear operations, image logic operations, image spatial operations and image transformations, so as to form input sample tensor data; a sample data set acquisition step: simplifying the received input sample tensor data, integrating same into input sample data, and dividing into a training set data sample and a test set data sample which are obtained from the acquired images; a feature extraction step: establishing a convolutional neural network model for training and evaluation, to obtain a convolutional neural network model matching the training set data sample; a model calibration step: optimizing training to improve accuracy; and an image recognition step: recognizing the target object. The present invention can, within an extremely short time, accurately recognize whether an image contains a target object.

ZHEN XIJIN (CN)
XU AIMIN (CN)
ZHANG YINGBIN (CN)
GUO WEI (CN)
MING XING (CN)
LUO XIAOMENG (CN)

PCT/CN2023/112528

April 18, 2024

August 11, 2023

Click for automatic bibliography generation  

SHIPBUILDING TECH RESEARCH INSITITUTE NO 11 INSTITUTE OF CSSC (CN)

G06V20/50; G06N3/04; G06N3/08; G06V10/774; G06V10/82

CN115565115A	2023-01-03
CN112766232A	2021-05-07
CN112906795A	2021-06-04
CN114926691A	2022-08-19

SHANGHAI SHIYUAN INTELLECTUAL PROPERTY AGENCY CO., LTD. (CN)

View/Download PDF      PDF Help

Previous Patent: INTERFACE RENDERING METHOD AND ELECTRONIC DEVICE

Next Patent: PERMANENT MAGNET-ASSISTED SYNCHRONOUS RELUCTANCE MOTOR AND COMPRESSOR