COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images
Research output: Working paper › Preprint › Research
Standard
COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images. / Belongie, Serge; Veit, Andreas; Matera, Tomáš; Neumann, Lukas; Matas, Jiri.
2016.Research output: Working paper › Preprint › Research
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - UNPB
T1 - COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images
AU - Belongie, Serge
AU - Veit, Andreas
AU - Matera, Tomáš
AU - Neumann, Lukas
AU - Matas, Jiri
PY - 2016/6/19
Y1 - 2016/6/19
N2 - This paper describes the COCO-Text dataset. In recent years large-scale datasets like SUN and Imagenet drove the advancement of scene understanding and object recognition. The goal of COCO-Text is to advance state-of-the-art in text detection and recognition in natural images. The dataset is based on the MS COCO dataset, which contains images of complex everyday scenes. The images were not collected with text in mind and thus contain a broad variety of text instances. To reflect the diversity of text in natural scenes, we annotate text with (a) location in terms of a bounding box, (b) fine-grained classification into machine printed text and handwritten text, (c) classification into legible and illegible text, (d) script of the text and (e) transcriptions of legible text. The dataset contains over 173k text annotations in over 63k images. We provide a statistical analysis of the accuracy of our annotations. In addition, we present an analysis of three leading state-of-the-art photo Optical Character Recognition (OCR) approaches on our dataset. While scene text detection and recognition enjoys strong advances in recent years, we identify significant shortcomings motivating future work.
AB - This paper describes the COCO-Text dataset. In recent years large-scale datasets like SUN and Imagenet drove the advancement of scene understanding and object recognition. The goal of COCO-Text is to advance state-of-the-art in text detection and recognition in natural images. The dataset is based on the MS COCO dataset, which contains images of complex everyday scenes. The images were not collected with text in mind and thus contain a broad variety of text instances. To reflect the diversity of text in natural scenes, we annotate text with (a) location in terms of a bounding box, (b) fine-grained classification into machine printed text and handwritten text, (c) classification into legible and illegible text, (d) script of the text and (e) transcriptions of legible text. The dataset contains over 173k text annotations in over 63k images. We provide a statistical analysis of the accuracy of our annotations. In addition, we present an analysis of three leading state-of-the-art photo Optical Character Recognition (OCR) approaches on our dataset. While scene text detection and recognition enjoys strong advances in recent years, we identify significant shortcomings motivating future work.
UR - https://vision.cornell.edu/se3/wp-content/uploads/2016/01/1601.07140v1.pdf
U2 - https://doi.org/10.48550/arXiv.1601.07140
DO - https://doi.org/10.48550/arXiv.1601.07140
M3 - Preprint
BT - COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images
ER -
ID: 307528242