Overview
This is a repackaged open source software product wherein additional charges apply for support with Hanwei.
This product has created a web page,You can use the corresponding intranet IP to access the web page file for more convenient operation
EASYOCR is an open source Python optical character recognition (OCR) library that supports text recognition in more than 80 languages. It is easy to use and can implement OCR functions with just a few lines of code. It provides pre-trained deep learning models that can efficiently and accurately recognize various characters, and supports custom configuration to meet the needs of different projects. EASYOCR is lightweight and high-performance, making it very suitable for rapid integration into various application scenarios, such as document digitization, license plate recognition, etc. As an open source project, it also has active community support, and users can freely modify and expand its functions.
Highlights
- Multi-language support: Supports text recognition in more than 80 languages, covering a wide range of character sets, including Latin characters, Chinese characters, Arabic, etc., suitable for global projects.
- Ease of use: The API design is simple, and users only need a few lines of code to implement OCR functions, which is very suitable for rapid integration into various applications.
- Lightweight and efficient: With a lightweight installation package and efficient processing speed, it can run efficiently in resource-constrained environments, such as mobile devices or embedded systems.
Details
Typical total price
$0.121/hour
Pricing
- ...
Instance type | Product cost/hour | EC2 cost/hour | Total/hour |
---|---|---|---|
t2.nano | $0.10 | $0.006 | $0.106 |
t2.micro AWS Free Tier | $0.10 | $0.012 | $0.112 |
t2.small | $0.10 | $0.023 | $0.123 |
t2.medium | $0.10 | $0.046 | $0.146 |
t2.large | $0.10 | $0.093 | $0.193 |
t2.xlarge | $0.10 | $0.186 | $0.286 |
t2.2xlarge | $0.10 | $0.371 | $0.471 |
t3.nano | $0.10 | $0.005 | $0.105 |
t3.micro AWS Free Tier | $0.10 | $0.01 | $0.11 |
t3.small Recommended | $0.10 | $0.021 | $0.121 |
Additional AWS infrastructure costs
Type | Cost |
---|---|
EBS General Purpose SSD (gp2) volumes | $0.10/per GB/month of provisioned storage |
Vendor refund policy
no refunds
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
Updated to the latest
Additional details
Usage instructions
Connect to the public IP of the instance via SSH, log in with the username: ec2-user, and then upload the corresponding encrypted file to log in successfully. Use sudo -s to enter the root user mode
This product has created a web page, and the OCR recognition function of this product has been made into a system service, and it starts automatically when the computer is turned on. The service name of this OCR function is: ocr-app.service NGINX service has also been set to start automatically when the computer is turned on
The following is a tutorial:
- Use the ip addr command on the WebUI interface to view the intranet IPv4 address of the OCR host, then use remote desktop to log in on another EC2 Windows version host, and enter http://[host-ip] in the browser
Note: [host-ip] is the intranet IPv4 address of the OCR host, that is, the address queried after using the ip addr command. You can also view the private IPv4 address in the corresponding OCR instance interface of AWS
- If there is no Windows host, this product also has a shell usage method. First enter the root user mode and enter 'python'. After entering python, enter the following command import easyocr reader = easyocr.Reader(['ch_sim','en']) # this needs to run only once to load the model into memory result = reader.readtext('abcd.jpg', detail = 0)
Note:
-
abcd.jpg in the command needs to be replaced with an absolute path, such as /root/abcd.jpg.
-
liunx can use some image upload tools to upload to the OCR host and use shell for recognition, but it is more recommended to use windows to access the page, which will be more convenient.
-
If you cannot access it, please pay attention to whether the firewall of the OCR host allows port 80 or port 443 and port 5000 to pass, whether SElinux is set to disabled, and whether the security group corresponding to the OCR host has opened ports 22, 80, 443 and 5000
Resources
Vendor resources
Support
Vendor support
For product technical support, please contact prosupport@hanweie.com
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.