Method for detecting image spam email by picture character and local invariant feature
A local invariant feature, spam technology, applied in computer parts, electrical components, digital transmission systems, etc., can solve the problems of disadvantage, large amount of calculation, high algorithm time complexity, save program operation time and space, The effect of improving precision and recall
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0030] Image spam is detected based on local invariant features of pictures, using VC++6.0 as the development tool, in which opencv1.0 open source library is used to process image features, and MFC class library is used to extract text in pictures. The detailed steps are as follows:
[0031] 1. Training phase: Obtain junk pictures and normal pictures to form a training set, and train to form a stack classifier.
[0032] a) Text feature extraction stage:
[0033] Step 1) To recognize the characters in the graphics, use the optical character recognition technology module provided by Microsoft Corporation. We have made many improvements to the interface of this module for use in our invention: it has been improved to enable batch processing of data sets, and some unrecognizable special symbols in the extracted text have been removed;
[0034] Step 2) improve the optical character recognition module, and store the pictures that can be accurately extracted and the words that cann...
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