Rooms with Text: A Dataset for Overlaying Text Detection
This work addresses the specific challenge of text detection in cluttered indoor scenes for computer vision applications, but it is incremental as it builds on existing text detection frameworks.
The authors tackled the problem of detecting overlaying text in room interior images by introducing a new dataset of 4,836 annotated images across 25 product categories and proposing a baseline method that achieves a 0.95 F1 score with low error rates.
In this paper, we introduce a new dataset of room interior pictures with overlaying and scene text, totalling to 4836 annotated images in 25 product categories. We provide details on the collection and annotation process of our dataset, and analyze its statistics. Furthermore, we propose a baseline method for overlaying text detection, that leverages the character region-aware text detection framework to guide the classification model. We validate our approach and show its efficiency in terms of binary classification metrics, reaching the final performance of 0.95 F1 score, with false positive and false negative rates of 0.02 and 0.06 correspondingly.