A robust arbitrary text detection system for natural scene images

•We explore the property that pattern in both Sobel and Canny share the same feature.•New invariant symmetric features to classify text and non-text pixels correctly.•We exploit SIFT features to eliminate non-text components.•Ellipse growing to extract curved text lines using text representatives.•N...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Expert systems with applications Jg. 41; H. 18; S. 8027 - 8048
Hauptverfasser: Risnumawan, Anhar, Shivakumara, Palaiahankote, Chan, Chee Seng, Tan, Chew Lim
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Amsterdam Elsevier Ltd 15.12.2014
Elsevier
Schlagworte:
Applied sciences
Arbitrary text detection
Artificial intelligence
Computer science; control theory; systems
Ellipse growing
Exact sciences and technology
Expert systems
Image detection
Invariant properties
Orientation
Pattern recognition. Digital image processing. Computational geometry
Pixels
Symmetry
Symmetry features
Text restoration
Text verification
Texts
Invariant properties
Symmetry features
Ellipse growing
Text restoration
Arbitrary text detection
Text verification
Invariant
Nearest neighbour
Computer vision
Information retrieval
Text
Cluttered environment
Experimental study
Symmetry group
Spatial distribution
Image matching
Scene analysis
Natural scenes
Curvature
Edge detection
Symmetry
ISSN:0957-4174, 1873-6793
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:•We explore the property that pattern in both Sobel and Canny share the same feature.•New invariant symmetric features to classify text and non-text pixels correctly.•We exploit SIFT features to eliminate non-text components.•Ellipse growing to extract curved text lines using text representatives.•New objective heuristics to eliminate false positives. Text detection in the real world images captured in unconstrained environment is an important yet challenging computer vision problem due to a great variety of appearances, cluttered background, and character orientations. In this paper, we present a robust system based on the concepts of Mutual Direction Symmetry (MDS), Mutual Magnitude Symmetry (MMS) and Gradient Vector Symmetry (GVS) properties to identify text pixel candidates regardless of any orientations including curves (e.g. circles, arc shaped) from natural scene images. The method works based on the fact that the text patterns in both Sobel and Canny edge maps of the input images exhibit a similar behavior. For each text pixel candidate, the method proposes to explore SIFT features to refine the text pixel candidates, which results in text representatives. Next an ellipse growing process is introduced based on a nearest neighbor criterion to extract the text components. The text is verified and restored based on text direction and spatial study of pixel distribution of components to filter out non-text components. The proposed method is evaluated on three benchmark datasets, namely, ICDAR2005 and ICDAR2011 for horizontal text evaluation, MSRA-TD500 for non-horizontal straight text evaluation and on our own dataset (CUTE80) that consists of 80 images for curved text evaluation to show its effectiveness and superiority over existing methods.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0957-4174
1873-6793
DOI:10.1016/j.eswa.2014.07.008