Text Recognition in the Wild: A Survey

Chen, Xiaoxue; Jin, Lianwen; Zhu, Yuanzhi; Luo, Canjie; Wang, Tianwei

doi:10.48550/arxiv.2005.03492

Cited by 9 publications

(15 citation statements)

References 182 publications

(358 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…STR models using deep learning [39,3,42,5,25] have superseded the performance of algorithms with handcrafted features [30,38]. Chen et al [7] presented a comprehensive review and analysis of different STR methods. The problem with deep learning models is that they require a large amount of data to automatically learn features.…”

Section: Related Workmentioning

confidence: 99%

Data Augmentation for Scene Text Recognition

Atienza¹

2021

Preprint

View full text Add to dashboard Cite

Scene text recognition (STR) is a challenging task in computer vision due to the large number of possible text appearances in natural scenes. Most STR models rely on synthetic datasets for training since there are no sufficiently big and publicly available labelled real datasets. Since STR models are evaluated using real data, the mismatch between training and testing data distributions results into poor performance of models especially on challenging text that are affected by noise, artifacts, geometry, structure, etc. In this paper, we introduce STRAug which is made of 36 image augmentation functions designed for STR. Each function mimics certain text image properties that can be found in natural scenes, caused by camera sensors, or induced by signal processing operations but poorly represented in the training dataset. When applied to strong baseline models using RandAugment, STRAug significantly increases the overall absolute accuracy of STR models across regular and irregular test datasets by as much as 2.10% on Rosetta, 1.48% on R2AM, 1.30% on CRNN, 1.35% on RARE, 1.06% on TRBA and 0.89% on GCRNN. The diversity and simplicity of API provided by STRAug functions enable easy replication and validation of existing data augmentation methods for STR. STRAug is available at https://github.com/roatienza/straug.

show abstract

Section: Related Workmentioning

confidence: 99%

Data Augmentation for Scene Text Recognition

Atienza¹

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In the last decade, the advent of deep learning has led to substantial advancements in STR. Earlier methods were segmentation-based methods [4] that aimed to locate the characters, use character classifier to recognize the characters, and then group characters into text lines. PhotoOCR [5] was one such segmentation-based method that used a deep neural network trained on the extracted histogram of oriented gradient (HOG) features for character classification.…”

Section: Related Workmentioning

confidence: 99%

STRIDE : Scene Text Recognition In-Device

Munjal,

Prabhu,

Arora

et al. 2021

Preprint

View full text Add to dashboard Cite

Optical Character Recognition (OCR) systems have been widely used in various applications for extracting semantic information from images. To give the user more control over their privacy, an on-device solution is needed. The current state of the art models are too heavy and complex to be deployed on-device. We develop an efficient lightweight scene text recognition (STR) system, which has only 0.88M parameters and performs real-time text recognition. Attention modules tend to boost the accuracy of STR networks but are generally slow and not optimized for device inference. So, we propose the use of convolution attention modules to the text recognition networks, which aims to provide channel and spatial attention information to the LSTM module by adding very minimal computational cost. It boosts our word accuracy on ICDAR 13 dataset by almost 2%. We also introduce a novel orientation classifier module, to support the simultaneous recognition of both horizontal and vertical text.The proposed model surpasses on-device metrics of inference time and memory footprint and achieves comparable accuracy when compared to the leading commercial and other open-source OCR engines. We deploy the system on-device with an inference speed of 2.44 ms per word on the Exynos 990 chipset device and achieve an accuracy of 88.4% on ICDAR-13 dataset.

show abstract

“…The STR systems have been extensively and successfully utilized in various applications, such as image retrieval, driver-assisted systems, recognition of personal cards and related documents, etc. [1][2]. The STR systems often include two main procedures: Text detection and recognition.…”

Section: Introductionmentioning

confidence: 99%

“…Much of the work reported in the literature regarding the STR was motivated by the challenges from unstructured texts such as unknown layout, complex background, various view angles, illumination, etc. [1][2]. We should consider the following fundamental research issues to design a realistic system: Feature extraction, classifier, and language model.…”

Section: Introductionmentioning

confidence: 99%

An improved CRNN for Vietnamese Identity Card Information Recognition

Dat¹,

Dang²,

Truong³

et al. 2022

Computer Systems Science and Engineering

View full text Add to dashboard Cite

This paper proposes an enhancement of an automatic text recognition system for extracting information from the front side of the Vietnamese citizen identity (CID) card. First, we apply Mask-RCNN to segment and align the CID card from the background. Next, we present two approaches to detect the CID card's text lines using traditional image processing techniques compared to the EAST detector. Finally, we introduce a new end-to-end Convolutional Recurrent Neural Network (CRNN) model based on a combination of Connectionist Temporal Classification (CTC) and attention mechanism for Vietnamese text recognition by jointly train the CTC and attention objective functions together. The length of the CTC's output label sequence is applied to the attention-based decoder prediction to make the final label sequence. This process helps to decrease irregular alignments and speed up the label sequence estimation during training and inference, instead of only relying on a data-driven attention-based encoder-decoder to estimate the label sequence in long sentences. We may directly learn the proposed model from a sequence of words without detailed annotations. We evaluate the proposed system using a real collected Vietnamese CID card dataset and find that our method provides a 4.28% in WER and outperforms the common techniques.

show abstract

Text Recognition in the Wild: A Survey

Cited by 9 publications

References 182 publications

Data Augmentation for Scene Text Recognition

Data Augmentation for Scene Text Recognition

STRIDE : Scene Text Recognition In-Device

An improved CRNN for Vietnamese Identity Card Information Recognition

Contact Info

Product

Resources

About