Scene Text Recognition using Higher Order Language Priors

By Anand Mishra, Alahari Karteek, C. V. Jawahar. 2009

880 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Natural Language Processing

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

In Natural Language Processing

Citations in the corpus

Learning Transferable Visual Models From Natural Language Supervision (2021, background): “Three of these datasets MNIST (LeCun), SVHN (Netzer et al., 2011), and IIIT5K (Mishra et al., 2012) directly check the ability of a model to perform low-level character and word recognition, while Hateful Memes (Kiela et al., 2020) and SST-2 (Socher et al., 2013) check the ability of a model to use ”
Deep Structured Output Learning for Unconstrained Text Recognition (2014, methodology): “IIIT 5k-word (Mishra et al. (2012)) test dataset contains 3000 cropped word images of scene text downloaded from Google image search.”
GIT: A Generative Image-to-text Transformer for Vision and Language (2022, background): “…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 et al., 2013), and CUTE80 (CUTE)…”
Synthetic Data for Text Localisation in Natural Images (2016, methodology): “The colour palette for text is learned from cropped word images in the IIIT5K word dataset [32].”
Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition (2014, methodology): “In contrast to these approaches based on character classification, the work by [7, 17, 21, 24] instead uses the notion of holistic word recognition.”
Reading Text in the Wild with Convolutional Neural Networks (2014, background): “IIIT5k-50 IIIT5k (Mishra et al. 2012) test dataset with fixed lexicon 50 3000”
COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images (2016, methodology): “Other scene text datasets include IIIT 5k-word [13] which contains 3000 cropped word images of scene text downloaded from Google image search as well as Synth90k [5], a dataset of 9 million cropped word images that have been synthetically generated to train systems for character recognition.”
End-to-End Text Recognition with Hybrid HMM Maxout Models (2013, background): “The works of (Neumann & Matas, 2011; Mishra et al., 2012; Novikova et al., 2012) are the only works we know of that show how their meth-ods scale with lexicon size.”
ESIR: End-To-End Scene Text Recognition via Iterative Image Rectification (2018, background): “IIIT5K [30] consists of 2000 training images and 3000 test images that are cropped from scene texts and born-digital images.”
MPDIoU: A Loss for Efficient and Accurate Bounding Box Regression (2023, methodology): “IIIT5k: IIIT5k [12] is one of the popular scene text spotting benchmark with character-level annotations, which contains 5,000 cropped word images collected from the Internet.”
OCR-VQA: Visual Question Answering by Reading Text in Images (2019, background): “The area of OCR has greatly benefited by the availability of public datasets such as MNIST [3], GW [6], IIIT-5K [16], SVT [24], etc.”