Paper Info
Title
Orientation Robust Text Line Detection in Natural Images
Abstract
In this paper, higher-order correlation clustering (HOCC) is used for text line detection in natural images. We treat text line detection as a graph partitioning problem, where each vertex is represented by a Maximally Stable Extremal Region (MSER). First, weak hypothesises are proposed by coarsely grouping MSERs based on their spatial alignment and appearance consistency. Then, higher-order correlation clustering (HOCC) is used to partition the MSERs into text line candidates, using the hypotheses as soft constraints to enforce long range interactions. We further propose a regularization method to solve the Semidefinite Programming problem in the inference. Finally we use a simple texton-based texture classifier to filter out the non-text areas. This framework allows us to naturally handle multiple orientations, languages and fonts. Experiments show that our approach achieves competitive performance compared to the state of the art.
Year
DOI
Venue
2014
10.1109/CVPR.2014.514
CVPR
Keywords
Field
DocType
pattern clustering,graph partitioning problem,natural images,texton-based texture classifier,hocc,mathematical programming,spatial alignment,semidefinite programming problem,text detection,orientation robust text line detection,regularization method,higher-order correlation clustering,edge detection,mser,filtering theory,long range interactions,maximally stable extremal region,text detection, higher-order correlation clustering,,appearance consistency,vectors,computer vision,correlation,programming
Computer vision,Vertex (geometry),Correlation clustering,Pattern recognition,Texton,Computer science,Inference,Regularization (mathematics),Artificial intelligence,Graph partition,Classifier (linguistics),Semidefinite programming
Conference
ISSN
Citations 
PageRank 
1063-6919
54
1.29
References 
Authors
16
3
Name
Order
Citations
PageRank
Le Kang13069.32
Yi Li258724.04
David Doermann34313312.70