Quick Start - OCR Demo
This example is intended to demonstrate how to develop an OCR model on the official website's workbench.
The OCR model is used to detect different types of characters in various scenarios, including numbers, letters, and other special characters. It achieves fast and high-precision recognition of characters in complex environments.
There are 7 steps in OCR model development: Create Model - Upload Images - Label Images - Train Model - Test Images - Export Model - Download SDK.
The following example is an OCR detection example for pharmaceutical box imprints. The goal is to extract the production date, batch number, and expiration date from the pharmaceutical box. The expected result of character extraction is as follows:
The specific steps for model development are as follows:
1.Create Model
Click on "Create a model".
Enter the Model name (up to 20 characters), select the Model type as "OCR", and click "Confirm" to create the model.
2.Upload Images
Click on "Dataset" to upload images. Click on "Upload Image".
Check the requirements for uploading images, click on "Upload now", select the images, and upload them.
Batch uploading is supported.
After the upload is complete, the upload results will be displayed, and you can see that all the images have been successfully uploaded. This completes the image uploading process.
If you want to upload locally labeled images,click here for more information! Upload img+LBL
3.Label Images
Enter the Labeling interface where you can label the images. The red box in the image represents the toolbar.
On the left side of the toolbar is the labeling area. The first tool is a rectangular box that can be used to enclose characters. In the middle of the toolbar, you can zoom in and out of the image (you can also use the mouse scroll wheel to zoom). On the right side of the toolbar, there are some advanced features.
The OCR annotation process mainly consists of two steps:
1. Use the rectangular box tool in the toolbar to enclose individual characters.
2. Type the label for each character.
For detailed label rules and examples, please refer to "More" -> "Label Examples".
4.Train Model
Enter the "Training" interface and click on "Start Training".
The following screen will appear, indicating that the task is in the queue. Please wait.
Then the model will start training, which will take approximately 10 minutes.
If you want to check if the generated model performs well , click here for more information! Average dectetion rate
5.Test Images
Enter the Test page and click on "Start Testing" to perform model testing.
Once the testing is complete, the following message will appear, indicating that the testing is finished. If you want to view the testing results, click on "View Test Results".
The character recognition results will appear in the upper left corner of the region, and the predicted results will be displayed on the original image.
If you want to obtain a large number of pre-labeled images but label few picture , click here for more information! Test result transfer
If you want to know how confident the model's prediction results are, click here for more information! Show confidence level
6.Export Model
Enter the download page, select "Current Model" and corresponding GPU, and click on "Export Model".
If you want know the Inference Time of using the model on your GPU, click here.
7.Download SDK
On the download page, select "C++ V1.0". Click on "Download SDK".
Still have a question?
Each section should be concise, user-friendly, and direct users to additional resources or documentation when necessary.