1. Application of Forgery Localization in Overlay Text Detection
- Author
-
Amit Hooda, Madhur Kathuria, and Vinod Pankajakshan
- Subjects
Information retrieval ,business.industry ,Computer science ,Colour filter array ,Search engine indexing ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,Computer vision ,Image forensics ,Artificial intelligence ,Text detection ,Overlay ,business ,Image (mathematics) - Abstract
Detection of text embedded in images and videos is very useful in applications like indexing and retrieval of multimedia content. There exist very few techniques which can differentiate between overlay text which is embedded artificially and scene text which occurs naturally in images. This paper proposes an efficient method for detection and localization of overlay text from still images. By using colour filter array(CFA)-based forgery localization method, the proposed technique successfully removes any scene text present in the image. Experimental results on a database of 315 images demonstrate the efficiency of the proposed method.
- Published
- 2014