Machine Learning
Boosting Color Saliency in Image Feature Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Visual Vocabulary for Flower Classification
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Multimodal fusion using learned text concepts for image categorization
MULTIMEDIA '06 Proceedings of the 14th annual ACM international conference on Multimedia
A Novel Algorithm for Text Detection and Localization in Natural Scene Images
DICTA '10 Proceedings of the 2010 International Conference on Digital Image Computing: Techniques and Applications
CCIW'11 Proceedings of the Third international conference on Computational color imaging
Proceedings of the 1st ACM International Conference on Multimedia Retrieval
A Keypoint-Based Approach toward Scenery Character Detection
ICDAR '11 Proceedings of the 2011 International Conference on Document Analysis and Recognition
Combining image and text features: a hybrid approach to mobile book spine recognition
MM '11 Proceedings of the 19th ACM international conference on Multimedia
A codebook-free and annotation-free approach for fine-grained image categorization
CVPR '12 Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Real-time scene text localization and recognition
CVPR '12 Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Measuring the Objectness of Image Windows
IEEE Transactions on Pattern Analysis and Machine Intelligence
Geodesic saliency using background priors
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
Object reading: text recognition for object recognition
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part III
Automatic Egyptian hieroglyph recognition by retrieving images as texts
Proceedings of the 21st ACM international conference on Multimedia
Hi-index | 0.00 |
This paper focuses on fine-grained classification by detecting photographed text in images. We introduce a text detection method that does not try to detect all possible foreground text regions but instead aims to reconstruct the scene background to eliminate non-text regions. Object cues such as color, contrast, and objectiveness are used in corporation with a random forest classifier to detect background pixels in the scene. Results on two publicly available datasets ICDAR03 and a fine-grained Building subcategories of ImageNet shows the effectiveness of the proposed method.