Wacnet: Word Segmentation Guided Characters Aggregation Net for Scene Text Spotting With Arbitrary Shapes

Gao, Yuting; Huang, Zheng; Dai, Yuchen; Chen, Kai; Guo, Jie; Qiu, Weidong

doi:10.1109/icip.2019.8803529

Cited by 4 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different convolutional deep learning neural network based methods have recently been used as feature backbone to extract features in order to appropriately handle the text of different scales (Gao et al, 2019; S. Qin, Bissacco, et al, 2019). Features have been extracted by using the output of one or more of the hidden layers in CNN (Gao et al, 2019; X. Qin, Zhou, et al, 2019). Sharing features extracted from CNN has also been used to extend a character classification method to character detection and bigram classification.…”

Section: Spotting ‐Based Mining Approachesmentioning

confidence: 99%

“…Learning based methods for text spotting can be divided into two different categories: conventional machine learning, and deep learning based approaches. The conventional machine learning based methods have longer history in the literature of word spotting compared with the deep learning methods (Gao et al, 2019), whereas deep learning based methods are more advanced and recently attracted many researchers (B. Bazazian et al, 2018a; Jaderberg et al, 2014).…”

Section: Spotting ‐Based Mining Approachesmentioning

confidence: 99%

“…An end‐to‐end trainable framework called Word Segmentation Guided Characters Aggregation Net (WAC‐Net) has further been developed to spot arbitrary shape text of different scripts in scene images (Gao et al, 2019). A shared convolutional backbone and the word‐level instance‐aware segmentation network (WSN) and the char‐level detection and recognition network (CDRN) work together to spot texts in one single forward pass.…”

Section: Spotting ‐Based Mining Approachesmentioning

confidence: 99%

“…A shared convolutional backbone and the word‐level instance‐aware segmentation network (WSN) and the char‐level detection and recognition network (CDRN) work together to spot texts in one single forward pass. The WSN and CDRN must jointly be trained by multitask learning (Gao et al, 2019). Moreover, a trainable neural network called Mask TextSpotter has been presented to achieve both detection and recognition in text multiscript instances of irregular shapes directly from two‐dimensional (2D) space via semantic segmentation.…”

Section: Spotting ‐Based Mining Approachesmentioning

confidence: 99%

See 3 more Smart Citations

Mining text from natural scene and video images: A survey

Shivakumara

Alaei

Pal

2021

WIREs Data Min & Knowl

View full text Add to dashboard Cite

In computer terminology, mining is considered as extracting meaningful information or knowledge from a large amount of data/information using computers. The meaningful information can be extracted from normal text, and images obtained from different resources, such as natural scene images, video, and documents by deriving semantics from text and content of the images. Although there are many pieces of work on text/data mining and several survey/review papers are published in the literature, to the best of our knowledge there is no survey paper on mining textual information from the natural scene, video, and document images considering word spotting techniques. In this article, we, therefore, provide a comprehensive review of both the non‐spotting and spotting based mining techniques. The mining approaches are categorized as feature, learning and hybrid‐based methods to analyze the strengths and limitations of the models of each category. In addition, it also discusses the usefulness of the methods according to different situations and applications. Furthermore, based on the review of different mining approaches, this article identifies the limitations of the existing methods and suggests new applications and future directions to continue the research in multiple directions. We believe such a review article will be useful to the researchers to quickly become familiar with the state‐of‐the‐art information and progresses made toward mining textual information from natural scene and video images. This article is categorized under: Algorithmic Development > Text Mining

show abstract

Section: Spotting ‐Based Mining Approachesmentioning

confidence: 99%

Section: Spotting ‐Based Mining Approachesmentioning

confidence: 99%

Section: Spotting ‐Based Mining Approachesmentioning

confidence: 99%

Section: Spotting ‐Based Mining Approachesmentioning

confidence: 99%

See 2 more Smart Citations

Mining text from natural scene and video images: A survey

Shivakumara

Alaei

Pal

2021

WIREs Data Min & Knowl

View full text Add to dashboard Cite

show abstract

“…The labeling of locations of characters is not needed. WACNET [12] applies a shared convolutional backbone between word-level segmentation and char-level detection and recognition. ASTS [74] customizes the mask R-CNN [75] to exploit the holistic-level semantics and pixel-level semantics for text spotting, simultaneously.…”

Section: Scene Text Spottingmentioning

confidence: 99%

Cluttered TextSpotter: An End-to-End Trainable Light-Weight Scene Text Spotter for Cluttered Environment

2020

View full text Add to dashboard Cite

Scene text spotting aims at simultaneously localizing and recognizing text instances, symbols, and logos in natural scene images. Scene text detection and recognition approaches have received immense attention in computer vision research community. The presence of partial occlusion or truncation artifact due to the cluttered background of scene images creates an obstacle in perceiving the text instances, which makes the process of spotting very complex. In this paper, we propose a lightweight scene text spotter that can address the issue of cluttered environment of scene images. It is an end-to-end trainable deep neural network that uses local part information, global structural features, and context cue information of oriented region proposals for spotting text instances. It helps to localize in scene images with background clutters, where partially occluded text parts, truncation artifacts, and perspective distortions are present. We mitigate the problem of misclassification caused by inter-class interference by exploring inter-class separability and intra-class compactness. We also incorporate multi-language character segmentation and word-level recognition in a lightweight recognition module. We have used six publicly available benchmark datasets in different smart devices to illustrate the efficacy of the network.

show abstract

Customized mask region based convolutional neural networks for un-uniformed shape text detection and text recognition

Chennegowda¹,

Karthik²,

Srinivasaiah³

et al. 2023

IJECE

View full text Add to dashboard Cite

<p><span lang="EN-US">In image scene, text contains high-level of important information that helps to analyze and consider the particular environment. In this paper, we adapt image mask and original identification of the mask region based convolutional neural networks (R-CNN) to allow recognition at 3 levels such as sequence, holistic and pixel-level semantics. Particularly, pixel and holistic level semantics can be utilized to recognize the texts and define the text shapes, respectively. Precisely, in mask and detection, we segment and recognize both character and word instances. Furthermore, we implement text detection through the outcome of instance segmentation on 2-D feature-space. Also, to tackle and identify the text issues of smaller and blurry texts, we consider text recognition by attention-based of optical character recognition (OCR) model with the mask R-CNN at sequential level. The OCR module is used to estimate character sequence through feature maps of the word instances in sequence to sequence. Finally, we proposed a fine-grained learning technique that trains a more accurate and robust model by learning models from the annotated datasets at the word level. Our proposed approach is evaluated on popular benchmark dataset ICDAR 2013 and ICDAR 2015.</span></p>

show abstract

Wacnet: Word Segmentation Guided Characters Aggregation Net for Scene Text Spotting With Arbitrary Shapes

Cited by 4 publications

References 19 publications

Mining text from natural scene and video images: A survey

Mining text from natural scene and video images: A survey

Cluttered TextSpotter: An End-to-End Trainable Light-Weight Scene Text Spotter for Cluttered Environment

Customized mask region based convolutional neural networks for un-uniformed shape text detection and text recognition

Contact Info

Product

Resources

About