Text image recognition method and device
By analyzing and clustering the coordinate information of the text in the text image, the accuracy problem of OCR technology when identifying abnormal line-breaking text is solved, and more accurate text recognition and output is achieved.
CN112507782BActive Publication Date: 2025-04-01GUANGDONG PLANNING & DESIGNING INST OF TELECOMM
4 Cites 0 Cited by
Patent Information
- Application Number
- CN202011138322.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-10-22
- Publication Date
- 2025-04-01
- Estimated Expiration
- 2040-10-22
AI Technical Summary
Technical Problem
When the existing OCR technology recognizes text images, it is easy to reduce the recognition accuracy due to abnormal line-breaking text, resulting in incorrect output text information.
Method used
By analyzing the coordinate information of each text in the text image, clustering all texts, dividing the text on the same line into a clustering set, and determining the text recognition results of the text image based on the text recognition results, coordinate information and the clustering set to which it belongs.
Benefits of technology
Improves the accuracy of the recognition of text in text images, ensuring that text on the same line is correctly output to the same line when output.
✦ Generated by Eureka AI based on patent content.
Abstract
The present invention discloses a text image recognition method and device, including: preprocessing a text image carrying a target text to obtain a model input image; inputting the model input image into a predetermined text detection model for analysis to obtain a text detection result of the text image; clustering all bounding boxes according to the coordinate information of each bounding box to obtain at least one bounding box clustering set; inputting the image in the target image area selected by each bounding box into a predetermined text recognition model for analysis to obtain a text recognition result of the bounding box; determining the text recognition result of the text image according to the text recognition result, coordinate information and bounding box clustering set of each bounding box. It can be seen that the present invention can improve the recognition accuracy of text in a text image, and ensure that when outputting the text recognition result, the text in the same line in the target text is output as the same line of text.
Need to check novelty before this filing date? Find Prior Art