A robust arbitrary text detection system for natural scene images

作者：

Highlights：

• 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.

摘要

•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.

论文关键词：Arbitrary text detection,Invariant properties,Symmetry features,Ellipse growing,Text verification,Text restoration

论文评审过程：Available online 17 July 2014.

论文官网地址：https://doi.org/10.1016/j.eswa.2014.07.008