TextProposals: A text-specific selective search algorithm for word spotting in the wild
By Lluís Gómez, Dimosthenis Karatzas. 2016
113 citations recorded by the source corpus.
Motivated by the success of powerful while expensive techniques to recognize words in a holistic way, object proposals techniques emerge as an alternative to the traditional text detectors. In this paper we introduce a novel object proposals method that is specifically designed for text. We rely on a similarity based region grouping algorithm that generates a hierarchy of word hypotheses. Over the nodes of this hierarchy it is possible to apply a holistic word recognition method in an efficient way. Our experiments demonstrate that the presented method is superior in its ability of producing good quality word proposals when compared with class-independent algorithms. We show impressive recall rates with a few thousand proposals in different standard benchmarks, including focused or incidental text datasets, and multi-language scenarios. Moreover, the combination of our object proposals with existing whole-word recognizers shows competitive performance in end-to-end word spotting, and, in some benchmarks, outperforms previously published results. Concretely, in the challenging ICDAR2015 Incidental Text dataset, we overcome in more than 10 percent f-score the best-performing method in the last ICDAR Robust Reading Competition. Source code of the complete end-to-end system is available at this https URL
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Computer Vision and Pattern Recognition
Citations in the corpus
- Recent advances in convolutional neural networks (2015, background): “Recently, object proposal based methods attract a lot of interests and are widely studied in the literature [185, 193, 200, 201].”
- Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes (2018, unknown): “7 - - TextProposals + DictNet [17], [31] 56.”
- Rotation-Sensitive Regression for Oriented Scene Text Detection (2018, methodology): “Different from scene text proposal methods [17, 2] which mainly concern the recall, scene text detection methods output much less output bounding boxes, considering the tradeoff between recall and precision.”
- TextBoxes: A Fast Text Detector with a Single Deep Neural Network (2016, unknown): “After that, the detected characters are grouped by an exhaustive search method; 2) Word-based: Words are directly hit with the similar manner of general object detection (Jaderberg et al. 2016; Zhong et al. 2016; Gomez-Bigorda and Karatzas 2016).”
- Integrating Scene Text and Visual Appearance for Fine-Grained Image Classification (2017, methodology): “Recently, following the popular general object detection approaches such as RCNN [52], Faster RCNN [53], YOLO [54], and SSD [55], the scheme of end-to-end word proposal generation followed by proposal classification has been a trend for word recognition in natural images [4], [37], [38], [44], [46].”
- Deep TextSpotter: An End-to-End Trainable Scene Text Localization and Recognition Framework (2017, methodology): “and state-of-the-art recognition methods [6, 4].”
- A Multi-Object Rectified Attention Network for Scene Text Recognition (2019, background): “With the development of scene text detection methods [11, 26, 46, 56], scene character recognition has emerged at the forefront of this research topic and is regarded as an open and very challenging research problem [45].”
- TextBoxes++: A Single-Shot Oriented Scene Text Detector (2018, background): “Other popular examples of this type are the works in [19]–[23]; 2) Word-based: Words are directly extracted in the similar manner as general object detection [8], [24]–[26].”
- Scene Text Detection and Recognition: The Deep Learning Era (2018, unknown): “77 TextProposals+DictNet [37], [60] 56.”