Method for omnidirectional processing of 2D images including recognizable characters
a 2d image and character technology, applied in the field of optical readers, can solve the problems of poorly equipped ocr readers for recognizing characters obliquely in captured images, and achieve the effect of improving the accuracy of ocr readers
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Examples
Embodiment Construction
[0022]A flow diagram of the main character recognition algorithm of the present invention for locating and recognizing recognizable characters is shown in FIG. 1a. At block 12 searching for a pixel grouping in a captured image proceeds according to a starburst pattern. According to a starburst search, a reader polls pixels at positions of generally increasing distances from a starburst center position in varying directions from a center position until a first pixel grouping is found at block 14. When a first pixel grouping is found, the reader subjects the pixel grouping to an edge length determining edge crawling process for estimating the size of the grouping based on the length of the pixel grouping's edge. The reader at block 18 then determines if the pixel grouping's edge is of sufficient length to represent a potentially recognizable character. Pixel groupings having edges of length sufficient to potentially represent a recognizable character are referred to herein as “globule...
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