Video text recognition using sequential Monte Carlo and error voting methods
Pattern Recognition Letters
Detecting text in video frames
SPPR'07 Proceedings of the Fourth conference on IASTED International Conference: Signal Processing, Pattern Recognition, and Applications
Fast and robust text detection in images and video frames
Image and Vision Computing
Detecting text in video frames
SPPRA '07 Proceedings of the Fourth IASTED International Conference on Signal Processing, Pattern Recognition, and Applications
Automatic segmentation of natural scene images based on chromatic and achromatic components
MIRAGE'07 Proceedings of the 3rd international conference on Computer vision/computer graphics collaboration techniques
A two-stage scheme for text detection in video images
Image and Vision Computing
A skeleton-based method for multi-oriented video text detection
DAS '10 Proceedings of the 9th IAPR International Workshop on Document Analysis Systems
A novel approach for text detection in images using structural features
ICAPR'05 Proceedings of the Third international conference on Advances in Pattern Recognition - Volume Part I
A new video images text localization approach based on a fast hough transform
ICIAR'06 Proceedings of the Third international conference on Image Analysis and Recognition - Volume Part I
Detection of text region and segmentation from natural scene images
ISVC'05 Proceedings of the First international conference on Advances in Visual Computing
A framework for improved video text detection and recognition
Multimedia Tools and Applications
| Hi-index | 0.01 |
In this paper an approach to automatic text location and identification on colored book and journal covers is proposed. To reduce the amount of small variations in color, a clustering algorithm is applied in a preprocessing step.Two methods have been developed for extracting text hypotheses. One is based on a top-down analysis using successive splitting of image regions. The other is a bottom-up region growing algorithm. The results of both methods are combined to robustly distinguish between text and non-text elements. Text elements are binarized using automatically extracted information about text color. The binarized text regions can be used as input for a conventional OCR module. Results are shown for parts of book and journal covers of different complexity. The proposed method is not restricted to cover pages, but can be applied to the extraction of text from other types of color images as well.