Symbol recognition in natural scenes by shape matching across multi-scale segmentations

Authors:
Ruimin Guan;Su Yang;Yuanyuan Wang
Affiliations:
Computer College of Computer Science and Technology, Fudan University, China;Computer College of Computer Science and Technology, Fudan University, China;Department of Electronic Engineering, Fudan University, China
Venue:
GREC'11 Proceedings of the 9th international conference on Graphics Recognition: new trends and challenges
Year:
2011

Citing 7
Cited 0

Shape Matching and Object Recognition Using Shape Contexts

IEEE Transactions on Pattern Analysis and Machine Intelligence
Symbol Recognition via Statistical Integration of Pixel-Level Constraint Histograms: A New Descriptor

IEEE Transactions on Pattern Analysis and Machine Intelligence
Camera-Based Graphical Symbol Detection

ICDAR '07 Proceedings of the Ninth International Conference on Document Analysis and Recognition - Volume 02
Detection and classification of road signs in natural environments

Neural Computing and Applications
Traffic sign recognition using evolutionary adaboost detection and forest-ECOC classification

IEEE Transactions on Intelligent Transportation Systems
An optimization on pictogram identification for the road-sign recognition task using SVMs

Computer Vision and Image Understanding
Distance sets for shape filters and shape recognition

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Symbol recognition in natural scenes plays an important role in a variety of applications such as driver assistance and environment awareness. We propose a solution including 3 phases: (1) Image segmentation, (2) component-level shape matching, and (3) structure matching. To improve the robustness, we alter the parameters to obtain image segmentation at multiple scales and perform component-level template matching across the image segmentation results obtained at all scales. By means of such exhaustive search across all possible segmentations, the chance to obtain finely matched components is increased. Some initial experimental results are obtained, which are encouraging.