Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Natural scene horizontal character detection method based on deep convolutional neural network

A natural scene and neural network technology, applied in the new application field of deep convolutional neural network, to achieve the effect of improving recall rate and comprehensive evaluation index

Active Publication Date: 2020-10-09
CHONGQING UNIV OF POSTS & TELECOMM
View PDF4 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

A natural scene level text detection method based on deep convolutional neural network is proposed to solve the problem of natural scene level text detection under small data sets, and to overcome the background complexity in natural scenes and the adverse effects of other external factors on text detection.

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
  • Natural scene horizontal character detection method based on deep convolutional neural network
  • Natural scene horizontal character detection method based on deep convolutional neural network
  • Natural scene horizontal character detection method based on deep convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The technical solutions in the embodiments of the present invention will be described clearly and in detail below with reference to the drawings in the embodiments of the present invention. The described embodiments are only some of the embodiments of the invention.

[0048] The technical scheme that the present invention solves the problems of the technologies described above is:

[0049] The invention provides a method for detecting horizontal characters in a natural scene of a small data set based on a deep convolutional neural network. The method comprises the following steps:

[0050] Step 1: Prepare the dataset;

[0051] First obtain a dataset suitable for natural scenes with small datasets. A total of 800 data sets were used, 229 of which were from the ICDAR2013 database. Most of the image data in this library are street view images and street signs, and the images have different shades and fonts. The 271 images were crawled from the Internet, including buildi...

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 provides a natural scene horizontal character detection method based on a deep convolutional neural network. According to the method, deep optimization is carried out on the basis of a TextBoxes network model, a new text prediction convolution group is added, and the network depth is expanded, so that the feature learning of the network for a small data set is more sufficient, and the feature information of a plurality of convolution layers is fully utilized to carry out fusion learning under certain model complexity. After feature learning is performed on original picture data through convolution layers with different receptive fields, a text prediction layer is utilized to return to the position of a textbox and predict a text category. According to the detection method, the influence of factors such as background complexity of a natural scene and insufficient features of a small data set on character detection is effectively solved. Experimental verification is carriedout under a Caffe platform, and results show that the model can effectively improve the recall rate and comprehensive evaluation indexes of natural scene level character detection under a small dataset.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a novel application technology of a deep convolutional neural network for natural scene text detection. Background technique [0002] The large-scale popularization of smart phones and the rapid development of the Internet have brought many new products and intelligent services, which has triggered a huge demand for practical vision technology. Text is one of the most ubiquitous visual objects in natural scenes and is very valuable for various applications in the real world. Therefore, text detection and recognition in natural scenes has become one of the research hotspots in the field of computer vision. In recent years, text detection in natural scenes has become an important research direction in the fields of image processing, computer vision, and natural language processing. [0003] Existing edge-based text detection methods first use edge characteristics to calcu...

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): G06K9/32G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/63G06V30/10G06N3/047G06N3/045G06F18/241G06F18/2415
Inventor 宋清洋孙巍郭志林
Owner CHONGQING UNIV OF POSTS & TELECOMM
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
Eureka Blog
Learn More
PatSnap group products