Snoopertext: A multiresolution system for text detection in complex visual scenes
Résumé
Text detection in natural images remains a very challenging task. For instance, in an urban context, the detection is very difficult due to large variations in terms of shape, size, color, orientation, and the image may be blurred or have irregular illumination, etc. In this paper, we describe a robust and accurate multiresolution approach to detect and classify text regions in such scenarios. Based on generation/validation paradigm, we first segment images to detect character regions with a multiresolution algorithm able to manage large character size variations. The segmented regions are then filtered out using shape-based classification, and neighboring characters are merged to generate text hypotheses. A validation step computes a region signature based on texture analysis to reject false positives. We evaluate our algorithm in two challenging databases, achieving very good results.
Mots clés
False positive
Machine-learning
Multi-resolution algorithms
Multi-resolution approach
Multi-resolutions
Natural images
Region signatures
Segmented regions
Shape based
Size variation
Text detection
Text region
Texture analysis
Urban context
Visual scene
Algorithms
Imaging systems
Learning systems
Text processing
Image segmentation