Camera Text Recognition based on Perspective Invariants

by Shijian Lu , Chew Lim Tan

Citations:

4 - 4 self

Datum	Value	Source
TITLE	Camera Text Recognition based on Perspective Invariants	SVM HeaderParse 0.2
AUTHOR NAME	Shijian Lu	SVM HeaderParse 0.2
AUTHOR AFFIL	Department of Computer Science; National University of Singapore, Kent Ridge	SVM HeaderParse 0.2
AUTHOR ADDR	117543	SVM HeaderParse 0.2
AUTHOR NAME	Chew Lim Tan	SVM HeaderParse 0.2
AUTHOR AFFIL	Department of Computer Science; National University of Singapore, Kent Ridge	SVM HeaderParse 0.2
AUTHOR ADDR	117543	SVM HeaderParse 0.2
ABSTRACT	As camera resolution increases, high-speed non-contact text capture through a digital camera is opening up a new channel for document capture and understanding. Unfortunately, perspective and geometric distortions in camera image of documents make it hard to recognize the document content properly. In this paper, we propose a character recognition technique, which is capable of recognizing camera text lying over a planar or smoothly curved surface in perspective views. In our proposed method, a few perspective invariants including character ascender and descender, centroid intersection numbers, and water reservior are first detected. Camera texts are then recognized using a classification and regression tree (CART) structure. Experimental results show our method is fast and improves recognition performance greatly. 1	SVM HeaderParse 0.2
CITATIONS	9 found	ParsCit 1.0