Container intelligent OCR identification method based on cloud processing

A recognition method and container technology, applied in character recognition, image data processing, neural learning methods, etc., can solve problems such as waste of human resources, low labor efficiency, and low efficiency, and achieve the effect of accelerating management efficiency

Pending Publication Date: 2020-05-08
上海箱云物流科技有限公司
View PDF5 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This not only wastes a lot of human resources, but also is inefficient for large-scale container management, so improving the efficiency of container digital management has become an urgent problem to be solved
[0004] With the development of technology, there is now a method of automatic big data management through container OCR recognition, through container photos taken from different angles, the OCR area of ​​the container is automatically extracted for artificial intelligence recognition, and automated according to keywords Matching analysis, and finally manage the container number and its matching information through the cloud for big data management, completely solving the problem of low efficiency of traditional labor and waste of human resources

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Container intelligent OCR identification method based on cloud processing
  • Container intelligent OCR identification method based on cloud processing
  • Container intelligent OCR identification method based on cloud processing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0049] see Figure 1-5 , the present invention provides a technical solution: a container intelligent OCR identification method based on cloud processing, comprising the following steps:

[0050] Step 1: Make image quality assessment sample set and label container OCR recognition sample set;

[0051] In this example, the image collected on the spot of the container is used as the original image. For the incomplete or low brightness of the OCR area, the sample t...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an intelligent container OCR (Optical Character Recognition) method based on cloud processing. The intelligent container OCR method comprises the following steps: step 1, making an image quality evaluation sample set and labeling a container OCR sample set; 2, constructing a depth image quality evaluation network, training the network by using the data of the image qualityevaluation sample set, and storing the trained network model; 3, constructing a deep text detection network, training an OCR region recognition neural network by using data of the OCR recognition sample set, and storing the trained network model; and 4, constructing a deep text recognition network, training an OCR content recognition neural network by using the data of the OCR recognition sample set, and storing the trained network model. According to the invention, digital management can be effectively carried out on the container, container data acquisition and analysis can be rapidly carried out, database docking can be automatically carried out, and the container management efficiency is improved.

Description

technical field [0001] The invention relates to the technical field of computer digital image processing and pattern recognition technology, in particular to a container intelligent OCR recognition method based on cloud processing. Background technique [0002] Container refers to a large-scale loading container with certain strength, rigidity and specifications specially used for turnover. Using containers to transship goods can be directly loaded in the consignor's warehouse and unloaded in the consignee's warehouse. When changing vehicles or ships midway, there is no need to take out the goods from the box for repacking. So the container is a great invention. The greatest success of the container lies in the standardization of its products and the entire transportation system established thereby. It is indeed worthy of the standardization of a behemoth with a load of tens of tons, and based on this, the gradual realization of a global logistics system for ships, ports, ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & AuthorityApplications(China)
IPC IPC(8): G06T7/00G06T7/11G06K9/00G06N3/04G06N3/08G06K9/62
CPCG06T7/0002G06T7/11G06N3/08G06T2207/30168G06V30/40G06V30/10G06N3/045G06F18/214
Inventor曹生华钱学明王萱
Owner上海箱云物流科技有限公司