Curly text image preprocessing method and lottery ticket scanning recognition method
A text image and recognition method technology, which is applied in the field of image processing, can solve the problems of unrecognizable documents, difficult to correct curly text image recognition text information, etc., and achieve the effect of improving recognition accuracy and reducing false recognition rate
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0031] In this embodiment, the curly text image preprocessing is to convert the captured text image into an image that can be recognized by the OCR recognition engine unit, and the process includes the following steps:
[0032] A. Scale the text image. Since the current camera pixels are relatively high, the processing speed can be increased by reducing the pixels by scaling the image; the scaled text image can be grayscaled to increase the processing speed.
[0033] B. Stretch the text image in grayscale and enhance the edge effect.
[0034] C. Binarize the text image after grayscale stretching to improve processing speed and facilitate subsequent edge extraction.
[0035] D. Perform edge extraction on the binarized text image. Find the edge of the text image through the connected area method, first-order derivation or second-order derivation; for example, Robert operator, sobel operator, prewitt operator, kirsch operator, laplacian operator, canny operator, Log (laplacian ...
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