ABCNet: Real-Time Scene Text Spotting With Adaptive Bezier-Curve Network

Liu, Yuliang; Chen, Hao; Shen, Chunhua; He, Tong; Jin, Lianwen; Wang, Handong

doi:10.1109/cvpr42600.2020.00983

Cited by 277 publications

(195 citation statements)

References 38 publications

Supporting

Mentioning

195

Contrasting

Order By: Relevance

“…As shown in Fig. 1, in comparison to state-ofthe-art methods [5,6], our NASK achieves tighter and more flexible results, thus more suitable for the arbitrary-shaped text reconstruction.…”

Section: Introductionmentioning

confidence: 86%

See 1 more Smart Citation

All You Need Is a Second Look: Towards Arbitrary-Shaped Text Detection

Cao

Zhang

Yang

et al. 2022

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Arbitrary-shaped text detection is a challenging task since curved texts in the wild are of the complex geometric layouts. Existing mainstream methods follow the instance segmentation pipeline to obtain the text regions. However, arbitraryshaped texts are difficult to be depicted through one single segmentation network because of the varying scales. In this paper, we propose a two-stage segmentation-based detector, termed as NASK (Need A Second looK), for arbitrary-shaped text detection. Compared to the traditional single-stage segmentation network, our NASK conducts the detection in a coarse-to-fine manner with the first stage segmentation spotting the rectangle text proposals and the second one retrieving compact representations. Specifically, NASK is composed of a Text Instance Segmentation (TIS) network (1 stage), a Geometry-aware Text RoI Alignment (GeoAlign) module, and a Fiducial pOint eXpression (FOX) module (2 stage). Firstly, TIS extracts the augmented features with a novel Group Spatial and Channel Attention (GSCA) module and conducts instance segmentation to obtain rectangle proposals. Then, GeoAlign converts these rectangles into the fixed size and encodes RoI-wise feature representation. Finally, FOX disintegrates the text instance into serval pivotal geometrical attributes to refine the detection results. Extensive experimental results on three public benchmarks including Total-Text, SCUT-CTW1500, and ICDAR 2015 verify that our NASK outperforms recent state-of-the-art methods.

show abstract

“…As shown in Fig. 1, in comparison to state-ofthe-art methods [5,6], our NASK achieves tighter and more flexible results, thus more suitable for the arbitrary-shaped text reconstruction.…”

Section: Introductionmentioning

confidence: 86%

“…ABCNet [6] adopts a parameterized Bezier curve to fit arbitrarily-shaped texts. Specifically, it simplifies the detection problem to the control point regression problem, based on which the Bezier curve is generated.…”

Section: B Arbitrary-shaped Text Representationmentioning

confidence: 99%

All You Need Is a Second Look: Towards Arbitrary-Shaped Text Detection

Cao

Zhang

Yang

et al. 2022

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

show abstract

“…The majority of state-of-the-art text detectors such as Deep-text [1], TextBoxes [2], TextBoxes++ [3] and ABCNet [39] use a predefined anchor box, which requires elaborate parameter tuning and complex calculations for box IoUs during training. With no anchor box, the FCOS [22] can predict the 4D vector and class labels for each spatial location on the feature map layer directly.…”

Section: Fcos For Text Detectionmentioning

confidence: 99%

Towards Accurate Scene Text Detection with Bidirectional Feature Pyramid Network

2021

View full text Add to dashboard Cite

Scene text detection, this task of detecting text from real images, is a hot research topic in the machine vision community. Most of the current research is based on an anchor box. These methods are complex in model design and time-consuming to train. In this paper, we propose a new Fully Convolutional One-Stage Object Detection (FCOS)-based text detection method that can robustly detect multioriented and multilingual text from natural scene images in a per pixel prediction approach. Our proposed text detector employs an anchor-free approach, unlike state-of-the-art text detectors that do not rely on a predefined anchor box. In order to enhance the feature representation ability of FCOS for text detection tasks, we apply the Bidirectional Feature Pyramid Network (BiFPN) as the backbone network, enhancing the model learning capacity and increasing the receptive field. We demonstrate the superior performance of our method on multioriented (ICDAR-2015, ICDAR-2017 MLT) and horizontal (ICDAR-2013) text detection benchmark tasks. Moreover, our method has an f-measure of 88.65 and 86.32 for the benchmark datasets ICDAR 2013 and ICDAR 2015, respectively, and 80.75 for the ICDAR-2017 MLT dataset.

show abstract

“…Instead of a 4 point bounding box (rectangular), they detect 14-point polygonal box to locate the text. In [7] Liu et al proposed another approach for curved text detection where the curvature of the text is represented using cubic bezier parameters. ABC-Net (Adaptive Bezier-Curve Network) was proposed to align bezier parameters appended by a recognition network.…”

Section: Related Workmentioning

confidence: 99%

Multi-lingual Indian Text Detector for Mobile Devices

Naosekpam

Kumar

Sahu

2021

Communications in Computer and Information Science

View full text Add to dashboard Cite

Detection of text in natural scene images is a challenging problem owing to its significant variations in the appearance of the texts as well as the background. The task becomes even more difficult for Indian texts, due to the presence of multiple languages and scripts. Most of the recent efficient schemes use very deep CNN which requires large memory and computation. In this paper, we proposed a multi-lingual text detection system based on the compressed versions of an object detection framework called YOLO (You Only Look Once) [13] namely, YOLO v3-Tiny and YOLO v4-Tiny. The aspect ratios of the anchor boxes are calculated using K-means clustering on the ground truth values, so that it can accurately detect words of varying lengths. The text detector has been evaluated on the IndicSceneText2017 [11] data set which consists of three Indian languages along with English. Experimental results prove the efficiency of the proposed scheme, for use in embedded systems and mobile devices due to its fast inference speed and small model size.

show abstract

ABCNet: Real-Time Scene Text Spotting With Adaptive Bezier-Curve Network

Cited by 277 publications

References 38 publications

All You Need Is a Second Look: Towards Arbitrary-Shaped Text Detection

All You Need Is a Second Look: Towards Arbitrary-Shaped Text Detection

Towards Accurate Scene Text Detection with Bidirectional Feature Pyramid Network

Multi-lingual Indian Text Detector for Mobile Devices

Contact Info

Product

Resources

About