Automatic detection of text labels in maps is essential for applications requiring automatic map understanding. This task is challenging due to factors such as varying font size and style, slanted words/phrases, and interfering graphics that are similar to text. This paper presents an approach for text detection in indoor floor maps. We exploit the difference in spatial frequency of edge orientations between text and non-text regions through Histogram of Oriented Gradients (HOG) features, and design a gradient-filtered Support Vector Machine (SVM) classifier based on such features. Special care was taken in conditioning the data for proper training of the classifier. The proposed approach was evaluated on a data set that had been collected and manually labeled. Experimental results show that the proposed method attained improved performance, outperforming a couple of reference methods/systems.
There is strong need for standardized data set of maps to ensure appropriate comparison of various methods on a common test set. We created a data set, by collecting floor maps of libraries and manually marking the ground truth. The data set has been created in such a way that it includes diverse images with different variations in structure of the building, image resolution, average text height etc. The current version includes only library floor maps and the dataset may be updated with other types of floor maps in the future. This data set can be downloaded here
If you use this data set, please cite the article mentioned above.
This material may not be redistributed.