Quick text detection method for natural scene

A technology for natural scene and text detection, applied in the new application technology field of convolutional neural network, can solve problems such as slow speed

Active Publication Date: 2018-02-13
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF3 Cites 31 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] At present, there are some text detection works based on deep convolutional networks, such as: the algorithm combining LSTM with Faster-RCNN, the algorithm combining RPN with Fast-RNN, these algorithms have good detection effect, but the speed is slow

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Quick text detection method for natural scene
  • Quick text detection method for natural scene
  • Quick text detection method for natural scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] First of all, the training data in several public databases—ICDAR2013, HUST-TR400, and SVT were collected, and about 800 training pictures were obtained, and about 2,000 image samples with different backgrounds, lighting, and fonts were taken and collected from the Internet. Afterwards, 2916 training samples were manually labeled. It is carried out on the authoritative public database ICDAR2013 test set. Normalize the sample size to 448*448 during training.

[0027] The present invention can be mainly divided into two parts of learning and testing of the convolutional neural network, and the whole work can be divided into the following 5 steps:

[0028] Step 1. Feature extraction network pre-training: pre-train the designed feature extraction small network on the ImageNet database. Due to the large number of network parameters and the small number of samples, in order to avoid overfitting, the image is randomly cropped from 300*300 to 224*224 during training for netwo...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a quick text detection method for a natural scene, and relates to the field of image processing, in particular to a novel application technology of a convolutional neural network for text detection. The method is characterized in that a quick feature extraction small network is proposed, an inception module is used, and a small convolution kernel is adopted, so that the number of parameters is reduced, the network is reduced, and the operation speed is accelerated; by additionally arranging a deconvolution layer to integrate multi-scale information, the detection accuracy is improved; a detection framework based on SSD (single shot multibox detector) is adopted in the detection phase, the width-to-height ratio of a preset framework is improved, and the ratio suitable for the text features is adopted. The method provided by the invention has the advantages that the testing is performed on a public dataset, and the validity and real-time property of the method areverified.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a novel application technology of a convolutional neural network for text detection. Background technique [0002] Texts have always played an important role in people's lives. The rich and precise information contained in text is very important for vision-based applications, such as: image retrieval, object localization, human-computer interaction, robot navigation, and industrial automation, etc. Automatic text detection provides a way to acquire and utilize text information in images and videos, and thus becomes a hot research topic in the fields of computer vision and document analysis. [0003] In the field of computer vision, there are many methods that can be used for text detection. Traditional text detection methods are usually based on texture and connected domain information, the most commonly used methods are Stroke Width Transform (SWT), Stroke Feature Transform (SF...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/32G06K9/20G06N3/04
CPCG06V10/23G06V20/62G06V20/63G06N3/045
Inventor 李宏亮方清陈雅丽杨燕平姚晓宇
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap