• Home
  • Search
  • Text Detection by Faster R-CNN with Multiple Region Proposal Networks
  • Cite Icon38
  • https://doi.org/10.1109/icdar.2017.343Copy DOI Icon

Text Detection by Faster R-CNN with Multiple Region Proposal Networks

  • Nov 1, 2017
  • Yoshito Nagaoka +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

We propose an end-to-end consistently trainable text detection method based on the Faster R-CNN. The original Faster R-CNN is an end-to-end CNN for fast and accurate object detection. By considering the characteristics of texts, a novel architecture that make use of its ability on object detection is proposed. Although the original Faster R-CNN generates region of interests (RoIs) by a region proposal network (RPN) using the feature map of the last convolutional layer, the proposed method generates RoIs by multiple RPNs using the feature maps of multiple convolutional layers. This method uses multiresolution feature maps to detect texts of various sizes simultaneously. To aggregate the RoIs, we introduce RoI-merge layer, and this layer enables to select valid RoIs from multiple RPNs effectively. In addition, a training strategy is proposed for realizing end-to-end training and making each RPN be specialized in text region size. Experimental results using ICDAR2013/2015 RRC test dataset show that the proposed Multi-RPN method improved detection scores and kept almost the same detection speed as compared to the original Faster R-CNN and recent methods.

Similar Papers
  • PDF
  • Research Article
  • Citations29

Anchor Generation Optimization and Region of Interest Assignment for Vehicle Detection.

  • Mar 03, 2019
  • Sensors
  • Ye Wang +2
  • Research Article
  • Citations55620

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.

  • Jun 06, 2016
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Shaoqing Ren +3
  • Book Chapter
  • Citations3

Rich Features and Precise Localization with Region Proposal Network for Object Detection

  • Jan 01, 2017
  • Mengdie Chu +3
  • Conference Article
  • Citations19

Speed-Up of Object Detection Neural Network with GPU

  • Oct 01, 2018
  • Takuya Fukagai +6
  • Research Article
  • Citations13

A Novel Multi-Scale Feature Fusion Method for Region Proposal Network in Fast Object Detection

  • Jul 01, 2020
  • International Journal of Data Warehousing and Mining
  • Gang Liu +1
  • Conference Article
  • Citations1

Research on small target detection based on improved Faster R-CNN depth network method

  • Sep 01, 2020
  • 2020 7th International Forum on Electrical Engineering and Automation (IFEEA)
  • Liu Qinghe +2
  • Research Article
  • Citations45

A quantitative detection algorithm based on improved faster R-CNN for marine benthos

  • Jan 20, 2021
  • Ecological Informatics
  • Yong Liu +1
  • Research Article
  • Citations54

DETECTION AND DIAGNOSIS OF COLITIS ON COMPUTED TOMOGRAPHY USING DEEP CONVOLUTIONAL NEURAL NETWORKS

  • Jul 18, 2017
  • Medical physics
  • Jiamin Liu +8
  • PDF
  • Research Article
  • Citations82

Marine Organism Detection and Classification from Underwater Vision Based on the Deep CNN Method

  • Feb 25, 2020
  • Mathematical Problems in Engineering
  • Fenglei Han +3
  • PDF
  • Research Article

Analisis Efektifitas Inception-EfficientNet Architecture untuk Klasifikasi Identitas Kartu Tanda Mahasiswa dengan Pendekatan OCR dan Faster R-CNN

  • Nov 30, 2023
  • ELECTRON Jurnal Ilmiah Teknik Elektro
  • Richo
  • Conference Article
  • Citations19

Saliency-guided region proposal network for CNN based object detection

  • Oct 01, 2017
  • Ann-Katrin Fattal +3
  • Research Article
  • Citations10

A Multi-strategy Region Proposal Network

  • Jun 28, 2018
  • Expert Systems with Applications
  • Yu-Peng Chen +3
  • Conference Article
  • Citations11

Small Object Detection and Tracking from Aerial Imagery

  • Sep 15, 2021
  • Mustafa Aktas +1
  • Research Article
  • Citations44

An algorithm for automatic identification of multiple developmental stages of rice spikes based on improved Faster R-CNN

  • Jul 19, 2022
  • The Crop Journal
  • Yuanqin Zhang +3
  • Book Chapter
  • Citations1

Text Localization in Scene Images Using Faster R-CNN with Double Region Proposal Networks

  • Jan 01, 2021
  • Pragya Hari +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.