18 Hits in 2.1 sec

DeepText: A Unified Framework for Text Proposal Generation and Text Detection in Natural Images [article]

Zhuoyao Zhong, Lianwen Jin, Shuye Zhang, Ziyong Feng
2016 arXiv   pre-print
In this paper, we develop a novel unified framework called DeepText for text region proposal generation and text detection in natural images via a fully convolutional neural network (CNN).  ...  Our approach achieves an F-measure of 0.83 and 0.85 on the ICDAR 2011 and 2013 robust text detection benchmarks, outperforming previous state-of-the-art results.  ...  In this paper, inspired by [21] , our motivation is to design a unified framework for text characteristic region proposal generation and text detection in natural images.  ... 
arXiv:1605.07314v1 fatcat:wtrqnd3cdrdjlk6fnqqgtszoey

Towards Accurate Scene Text Detection with Bidirectional Feature Pyramid Network

Dongping Cao, Jiachen Dang, Yong Zhong
2021 Symmetry  
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.  ...  The authors sincerely thank Teddy Zhang who provided valuable comments in writing this article. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/sym13030486 fatcat:haqr7qo4braw5obsyrhjgvyira

Deep Scene Text Detection with Connected Component Proposals [article]

Fan Jiang, Zhihui Hao, Xinran Liu
2017 arXiv   pre-print
A growing demand for natural-scene text detection has been witnessed by the computer vision community since text information plays a significant role in scene understanding and image indexing.  ...  We evaluate the proposed network on public benchmark datasets and show it can detect arbitrary-orientation scene text with a finer output boundary.  ...  Conclusions In this paper, we propose a deep neural network for scene text detection.  ... 
arXiv:1708.05133v1 fatcat:rlja477sxrgofnbyr3qyvy44wq

Deep Residual Text Detection Network for Scene Text [article]

Xiangyu Zhu, Yingying Jiang, Shuli Yang, Xiaobing Wang, Wei Li, Pei Fu, Hua Wang, Zhenbo Luo
2017 arXiv   pre-print
Scene text detection is a challenging problem in computer vision. In this paper, we propose a novel text detection network based on prevalent object detection frameworks.  ...  Our approach evaluated on ICDAR2013 dataset achieves F-measure of 0.91, which outperforms previous state-of-the-art results in scene text detection.  ...  INTRODUCTION Text detection is an important part of text content analysis, especially for reading natural text in the wild.  ... 
arXiv:1711.04147v1 fatcat:vxf7uiwdkfc45bpkux56ccqhem

Feature Enhancement Network: A Refined Scene Text Detector [article]

Sheng Zhang, Yuliang Liu, Lianwen Jin, Canjie Luo
2017 arXiv   pre-print
In this paper, we propose a refined scene text detector with a novel Feature Enhancement Network (FEN) for Region Proposal and Text Detection Refinement.  ...  Therefore, we design a new FEN network with task-specific, low and high level semantic features fusion to improve the performance of text detection.  ...  Text Detection Refinement Although the text proposal generation stage can recall almost all text regions, it will have a much lower precision for text detection.  ... 
arXiv:1711.04249v1 fatcat:ofw3ocp7xvfcfjcifbyiiarrfq

Detecting Multi-Oriented Text with Corner-based Region Proposals [article]

Linjie Deng, Yanxiang Gong, Yi Lin, Jingwen Shuai, Xiaoguang Tu, Yufei Zhang, Zheng Ma, Mei Xie
2018 arXiv   pre-print
Previous approaches for scene text detection usually rely on manually defined sliding windows.  ...  The proposals generated by CRPN are geometry adaptive, which makes our method robust to various text aspect ratios and orientations.  ...  Experiments Datasets SynthText in the Wild(SynthText) [7] is a dataset of 800,000 images generated via blending natural images with artificial text rendered with random fonts, sizes, orientations and  ... 
arXiv:1804.02690v1 fatcat:nwhnrnwqhjdvpild3awgmb4k7m

R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection [article]

Yingying Jiang, Xiangyu Zhu, Xiaobing Wang, Shuli Yang, Wei Li, Hua Wang, Pei Fu, Zhenbo Luo
2017 arXiv   pre-print
In this paper, we propose a novel method called Rotational Region CNN (R2CNN) for detecting arbitrary-oriented texts in natural scene images. The framework is based on Faster R-CNN [1] architecture.  ...  At last, we use an inclined non-maximum suppression to get the detection results. Our approach achieves competitive results on text detection benchmarks: ICDAR 2015 and ICDAR 2013.  ...  DeepText generates word region proposals via Inception-RPN and then scores and refines each word proposal using the text detection network [7] .  ... 
arXiv:1706.09579v2 fatcat:sqqikbnrivbh3cpeztipemf2da

Arbitrary-Oriented Scene Text Detection via Rotation Proposals

Jianqi Ma, Weiyuan Shao, Hao Ye, Li Wang, Hong Wang, Yingbin Zheng, Xiangyang Xue
2018 IEEE transactions on multimedia  
This paper introduces a novel rotation-based framework for arbitrary-oriented text detection in natural scene images.  ...  We conduct experiments using the rotation-based framework on three real-world scene text detection datasets and demonstrate its superiority in terms of effectiveness and efficiency over previous approaches  ...  There are 229 natural images for training and 233 natural images for testing.  ... 
doi:10.1109/tmm.2018.2818020 fatcat:gqpkriqes5adpkrkmxkvpr3hbq

Semi-automatic Generation of Multilingual Datasets for Stance Detection in Twitter

Elena Zotova, Rodrigo Agerri, German Rigau
2021 Expert systems with applications  
This paper presents a method to obtain multilingual datasets for stance detection in Twitter.  ...  While interactions in social media such as Twitter occur in many natural languages, research on stance detection (the position or attitude expressed with respect to a specific topic) within the Natural  ...  de Investigación Científica 2018 (BigKnowledge), and DeepText (KK-2020/00088), funded by the Basque Government.  ... 
doi:10.1016/j.eswa.2020.114547 fatcat:ej4fykkhnjbhdcwocwah3meedq

Deep reinforcement learning using compositional representations for performing instructions

Mohammad Ali Zamani, Sven Magg, Cornelius Weber, Stefan Wermter, Di Fu
2018 Paladyn: Journal of Behavioral Robotics  
To show the effectiveness of our approach, the Tell-Me-Dave corpus is used to train an intention detection model and in a second step an RL agent generates the sequences of actions towards the detected  ...  A novel contribution in this paper is the use of symbolic representations for both input and output of a neural Deep Q-network (DQN), which enables it to be used in a hybrid system.  ...  Figure 1 : 1 The modular approach using intention detection and reinforcement learning trained for each objective to generate the sequence of actions.  ... 
doi:10.1515/pjbr-2018-0026 fatcat:hzgtrjuhlrfjbdyn3qbfnhd7j4

LIPIcs : an Open-Access Series for International Conference Proceedings

Marc Herbstritt, Wolfgang Thomas
2016 ERCIM News  
Scientists write in narrative text, with embedded data and images and no thought for computer processing. Most text is born digital (Word, TeX) and straightforward to process but turned into PDF.  ...  This is a text-based (CESAER) has asked us to submit a proposal for their 50 universities to make this possible.  ...  This calls for approaching security in a holistic manner.  ... 
doi:10.18154/rwth-2018-223393 fatcat:ddo7qz65l5b7peuksw2amaoxai

SparCE: Sparsity aware General Purpose Core Extensions to Accelerate Deep Neural Networks [article]

Sanchari Sen, Shubham Jain, Swagath Venkataramani, Anand Raghunathan
2017 arXiv   pre-print
Accelerating DNNs on these low-power systems, comprising of mainly the general-purpose processor (GPP) cores, requires new approaches.  ...  We model SparCE using the gem5 architectural simulator, and evaluate our approach on 6 image-recognition DNNs in the context of both training and inference using the Caffe framework.  ...  INTRODUCTION Deep neural networks (DNNs) have revitalized the field of machine learning by achieving accuracy levels beyond human perception in a variety of image, video, text and speech processing tasks  ... 
arXiv:1711.06315v2 fatcat:vckqomokmfbkxendwvzmbxa4sq

Impact of Social Media on Geopolitics and Economic Growth: Mitigating the Risks by Developing Artificial Intelligence and Cognitive Computing Tools

M. M. Kamruzzaman, Jun Ye
2022 Computational Intelligence and Neuroscience  
But it decreases the productivity level of the individuals; on the other hand, it does contain the potential to create a participatory economy, which can be beneficial for a particular country.  ...  Social media is one of the most revolutionary innovations in computer science that facilitates connecting people in the world to share information, ideas, and thoughts.  ...  DeepText software uses an AI algorithm to learn such words instead of a database for referencing [37] .  ... 
doi:10.1155/2022/7988894 pmid:35602647 pmcid:PMC9117062 fatcat:f2jxei73wfexxpplyjbgj36gki

Reconstruction of training samples from loss functions [article]

Akiyoshi Sannai
2018 arXiv   pre-print
This paper presents a new mathematical framework to analyze the loss functions of deep neural networks with ReLU functions.  ...  Namely, if we have all input and output of a loss function (or equivalently all possible learning process), for all input of each training sample x_i ∈R^n, we can obtain vectors x'_i∈R^n satisfying x_i  ...  The author was partially supported by JSPS Grant-in-Aid for Young Scientists (B) 16K17581.  ... 
arXiv:1805.07337v1 fatcat:xd4yowpcujb5no5qytturcuzmi

Advances in Emerging Memory Technologies: From Data Storage to Artificial Intelligence

Gabriel Molas, Etienne Nowak
2021 Applied Sciences  
Then, the progress of emerging memory technologies (based on filamentary, phase change, magnetic, and ferroelectric mechanisms) is presented with a review of the major demonstrations in the literature.  ...  computing tasks, and also enlarges the range of required specifications at the device level due to the exponential number of new systems and architectures.  ...  , especially for datacentric applications such as realtime image recognition and natural language processing.  ... 
doi:10.3390/app112311254 fatcat:pg4iqzg4yfc2vb2lh2mgkyqafq
« Previous Showing results 1 — 15 out of 18 results