Arbitrary Shape Text Detection using Transformers

Raisi, Zobeir; Younes, Georges; Zelek, John

doi:10.1109/icpr56361.2022.9956488

Cited by 12 publications

(8 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This broader scope allows for the detection of more complex behaviors. In addition, the exploration of alternative approaches to object detection and tracking, such as those based on vision transformers, represents another promising direction for advancing our analytic capabilities and improving the accuracy of anomaly detection algorithms [76,77]. These efforts will contribute to a more robust and sophisticated system for monitoring and securing museum environments.…”

Section: Future Workmentioning

confidence: 99%

Deep-Learning-Based Action and Trajectory Analysis for Museum Security Videos

Di Maio,

Nunziati,

Mecocci

2024

Electronics

View full text Add to dashboard Cite

Recent advancements in deep learning and video analysis, combined with the efficiency of contemporary computational resources, have catalyzed the development of advanced real-time computational systems, significantly impacting various fields. This paper introduces a cutting-edge video analysis framework that was specifically designed to bolster security in museum environments. We elaborate on the proposed framework, which was evaluated and integrated into a real-time video analysis pipeline. Our research primarily focused on two innovative approaches: action recognition for identifying potential threats at the individual level and trajectory extraction for monitoring museum visitor movements, serving the dual purposes of security and visitor flow analysis. These approaches leverage a synergistic blend of deep learning models, particularly CNNs, and traditional computer vision techniques. Our experimental findings affirmed the high efficacy of our action recognition model in accurately distinguishing between normal and suspicious behaviors within video feeds. Moreover, our trajectory extraction method demonstrated commendable precision in tracking and analyzing visitor movements. The integration of deep learning techniques not only enhances the capability for automatic detection of malevolent actions but also establishes the trajectory extraction process as a robust and adaptable tool for various analytical endeavors beyond mere security applications.

show abstract

Section: Future Workmentioning

confidence: 99%

Deep-Learning-Based Action and Trajectory Analysis for Museum Security Videos

Di Maio,

Nunziati,

Mecocci

2024

Electronics

View full text Add to dashboard Cite

show abstract

“…ABCNet fits directional or curved text with parametric Bezier curves and introduces only a small computational load. Using Bezier curves to express text boxes has also been widely used in other studies [27][28][29]. Bezier curves significantly enhance text detection's flexibility, but their computational process is not conducive to high detection speed.…”

Section: Related Workmentioning

confidence: 99%

A real-time arbitrary-shape text detector

Lu,

Li,

Chen

2024

PLoS ONE

View full text Add to dashboard Cite

It is challenging to detect arbitrary-shape text accurately and effectively in natural scenes. While many methods have been implemented for arbitrary-shape text detection, most cannot achieve real-time detection or meet practical needs. In this work, we propose a YOLOv6-based detector that can effectively implement arbitrary-shape text detection and achieve real-time detection. We include two additional branches in the neck part of the YOLOv6 network to adapt the network to text detection, and the output side uses the pixel aggregation (PA) algorithm to decouple the PA output to use it as the detection head of the model. Experiments on benchmark Total-Text, CTW1500, ICDAR2015, and MSRA-TD500 showed that the proposed method outperformed competing methods in terms of detection accuracy and running time. Specifically, our method achieved an F-measure of 84.1% at 291.8 FPS for 640 × 640 Total-Text images and an F-measure of 81.5% at 199.6 FPS for 896 × 896 ICDAR2015 incidental text images.

show abstract

“…Location and Shape Decoupling Module Previous works [47,56] use a single feed-forward neural network (FFN) to predict the control points in image space and train the network by applying L1 loss on the control points. However, as shown in Sec.…”

Section: Unified Detection Of Text Line and Paragraphmentioning

confidence: 99%

“…Notably, we find that the conventional way of training Bezier Curve polygon prediction head, i.e. applying L1 losses on control points directly [30,47,56], fails to capture text shapes accurately on highly diverse dataset such as Hi-erText [34]. Hence, we propose a novel Location and Shape Decoupling Module (LSDM) which decouples the representation learning of location and shape.…”

Section: Introductionmentioning

confidence: 99%

Towards End-to-End Unified Scene Text Detection and Layout Analysis

Qin

Panteleev

Bissacco

et al. 2022

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

We organize a competition on hierarchical text detection and recognition. The competition is aimed to promote research into deep learning models and systems that can jointly perform text detection and recognition and geometric layout analysis. We present details of the proposed competition organization, including tasks, datasets, evaluations, and schedule. During the competition period (from January 2nd 2023 to April 1st 2023), at least 50 submissions from more than 20 teams were made in the 2 proposed tasks. Considering the number of teams and submissions, we conclude that the HierText competition has been successfully held. In this report, we will also present the competition results and insights from them.

show abstract

Arbitrary Shape Text Detection using Transformers

Cited by 12 publications

References 32 publications

Deep-Learning-Based Action and Trajectory Analysis for Museum Security Videos

Deep-Learning-Based Action and Trajectory Analysis for Museum Security Videos

A real-time arbitrary-shape text detector

Towards End-to-End Unified Scene Text Detection and Layout Analysis

Contact Info

Product

Resources

About