Medical examination report character recognition and correction method
A text recognition and report form technology, applied in the field of text recognition, can solve the problems of high text recognition error rate, table text recognition APP cannot locate text boxes, etc., to achieve accurate text recognition effect and ensure the effect of correct rate
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0044] This embodiment provides a text recognition and correction method for a medical examination report, including:
[0045] S1: Shoot the medical examination report, perform content extraction and perspective transformation on it, and obtain the image of the medical examination report, specifically:
[0046] Take photos of the original medical examination report with various background information, mark the content area of the original medical examination report photo as 1, and mark the background area as 0, and use DeepLab-V3Plus+CRF technology to train the semantic segmentation neural network, so that the semantic segmentation The neural network can accurately extract the content area of the photo of the original medical examination report, use the semantic segmentation neural network to segment the content area of the original medical examination report, and perform perspective transformation through the position information of the segmented content area to correct ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com