ICDAR 2015 competition on Robust Reading

By Dimosthenis Karatzas, Lluis Gomez i Bigorda, Anguelos Nicolaou, Suman K. Ghosh, Andrew D. Bagdanov, Masakazu Iwamura, Jiri Matas, Lukás Neumann, Vijay Ramaseshan Chandrasekhar, Shijian Lu and 3 more. 2015

1,578 citations recorded by the source corpus.

Results of the ICDAR 2015 Robust Reading Competition are presented. A new Challenge 4 on Incidental Scene Text has been added to the Challenges on Born-Digital Images, Focused Scene Images and Video Text. Challenge 4 is run on a newly acquired dataset of 1,670 images evaluating Text Localisation, Word Recognition and End-to-End pipelines. In addition, the dataset for Challenge 3 on Video Text has been substantially updated with more video sequences and more accurate ground truth data. Finally, tasks assessing End-to-End system performance have been introduced to all Challenges. The competition took place in the first quarter of 2015, and received a total of 44 submissions. Only the tasks newly introduced in 2015 are reported on. The datasets, the ground truth specification and the evaluation protocols are presented together with the results and a brief summary of the participating methods.

Subfields: 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 Computer Vision and Pattern Recognition

Citations in the corpus

TAP: Text-Aware Pre-training for Text-VQA and Text-Caption (2020, methodology): “The ST-VQA dataset [8] contains 21,892 images from multiple sources including ICDAR 2013 [27], ICDAR 2015 [26], ImageNet [13], VizWiz [18], IIIT STR [39], Visual Genome [29], and COCO-Text [54].”
Towards VQA Models That Can Read (2019, background): “Several existing datasets study text detection and/or parsing in natural everyday scenes: COCO-Text [43], Street-View text [44] IIIT-5k [33] and ICDAR 2015 [22].”
GIT: A Generative Image-to-text Transformer for Vision and Language (2022, methodology): “Following the established setup, we evaluate on six standard benchmarks, including ICDAR 2013 (IC13) (Karatzas et al., 2013), ICDAR 2015 (IC15) (Karatzas et al., 2015), IIIT 5K-Words (IIIT) (Mishra et al., 2012), Street View Text (SVT) (Wang et al., 2011), Street View Text-Perspective (SVTP) (Phan…”
COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images (2016, methodology): “We analyze COCO-Text and compare it to other popular scene text datasets, in particular, with ICDAR 03 [11] and ICDAR 15 [9].”
Scene Text Visual Question Answering (2019, methodology): “For the strongly contextualised task (1), following the standard practice used for end-to-end word spotting [27, 26, 55], we create a dictionary per image that contains the words that appear in the answers defined for questions on that image, along with a series of distractors.”
ASTER: An Attentional Scene Text Recognizer with Flexible Rectification (2019, background): “ICDAR 2015 Incidental Text (IC15) is the Challenge 4 of the ICDAR 2015 Robust Reading Competition [31].”
Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges (2021, background): “It is worthwhile to note that although objects in scene text detection [83] and face detection [60]”
Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition (2021, positive): “We test the trained model on six benchmarks including three regular scene-text datasets, i.e. , IC-DAR2013 (Karatzas et al. 2013), IIIT5K (Mishra, Alahari, and Jawahar 2012), SVT (Wang, Babenko, and Belongie 2011), and three irregular text datasets, i.e. , ICDAR2015 (Karatzas et al. 2015), SVTP (Pha”
Efficient and Accurate Arbitrary-Shaped Text Detection With Pixel Aggregation Network (2019, methodology): “To show the effectiveness of our proposed PAN, we conduct extensive experiments on four challenging benchmark datasets including CTW1500 [31], Total-Text [2], ICDAR 2015 [22] and MSRA-TD500 [51].”
Improving patch-based scene text script identification with ensembles of conjoined networks (2016, methodology): “In the SIW-13 dataset the proposed method significantly outperforms the best performing method known up to date by more than 4 percentual points.”
TextBoxes++: A Single-Shot Oriented Scene Text Detector (2018, methodology): “We have tested its performance on two datasets including oriented text: ICDAR 2015 Incidental Text (IC15) dataset [48] and COCO-Text dataset [49].”
TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes (2018, background): “ICDAR 2015 is proposed as the Challenge 4 of the 2015 Robust Reading Competition [14] for incidental scene text detection.”
CORD: A Consolidated Receipt Dataset for Post-OCR Parsing (2019, background): “Over the past few years, a few post-OCR parsing datasets have been made public through post OCR challenges [5].”