Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for detecting text in natural scene with robust shape

A natural scene, robust technology, applied in the field of deep learning, can solve problems such as inability to separate instances

Inactive Publication Date: 2019-07-12
NANJING UNIV
View PDF7 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when two text instances are very close to each other, such methods cannot successfully separate the instances, because the connection region will merge the two instances into the same text instance

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
  • Method for detecting text in natural scene with robust shape
  • Method for detecting text in natural scene with robust shape
  • Method for detecting text in natural scene with robust shape

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0054] The present invention is a kind of scene text detection method, comprises the following steps:

[0055] Step 1. Preprocess existing public text image datasets, such as: ICDAR 2015, ICDAR 2017 MLT, Total-Text or CTW1500, etc., or collect scene image datasets yourself, and perform data enhancement on training images: (1) Image Random scaling according to the ratio {0.5, 1.0, 2.0, 3.0}; (2) The picture is randomly flipped horizontally and randomly rotated within the range of [-10°, 10°]; (3) Randomly cropped from the picture 640×640 Sample; (4) The picture is normalized using channel mean and standard deviation.

[0056] Step 2, build PSENet (Progressive Scale Expansion Network, progressive scale growth network), PSENet network structure is as follows figure 1 as shown ( figure 1 Among them, Progressive Scale Expansion represents the scale growth...

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 method for detecting a text in a natural scene with a robust shape. The method comprises the following steps: step 1, preprocessing a training picture in a text data set; step 2, establishing a PSENet progressive scale growth network, and finishing feature extraction, feature fusion and segmentation prediction on the training picture by utilizing the progressive scale growth network to obtain segmentation results of a plurality of prediction scales; step 3, carrying out supervised training on the PSENet progressive scale growth network established in the step 2 to obtain a detector model; step 4, detecting the to-be-detected picture; and step 5, obtaining a final detection result by using a scale growth algorithm.

Description

technical field [0001] The invention relates to the field of deep learning technology, in particular to a method for text detection in natural scenes robust to shapes. Background technique [0002] In recent years, text detection in natural scenes has been widely used in many fields such as scene understanding, product recognition, autonomous driving, and object geolocation. However, due to the large scale difference between foreground text blocks and text lines and background objects, and the text is different in shape, color, font, size, and orientation, text detection in natural scenes still faces great challenges. [0003] Currently, the rapid development of convolutional neural networks has made great progress in scene text detection. Existing text detection methods can be roughly divided into two types: methods based on bounding box regression and methods based on object segmentation. Bounding box regression-based methods can locate target text with fixed orientation...

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): G06K9/32G06K9/34G06K9/62G06N3/04
CPCG06V20/63G06V10/267G06N3/044G06N3/045G06F18/253G06F18/214
Inventor 路通侯文博王文海
Owner NANJING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com