Method, device and equipment for text detection and analysis based on depth neural network

A deep neural network, text detection technology, applied in the field of text detection and analysis based on deep neural network, can solve the problems of position offset, text area positioning error, affecting the accuracy of anchor point matching, etc., to improve the recognition rate and accurate detection. Analyze and improve the effect of accuracy

Active Publication Date: 2018-12-25
ZHONGAN INFORMATION TECH SERVICES CO LTD
View PDF7 Cites 68 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The matching of anchor points in the existing methods is based on the traditional image feature matching method, and the brightness, contrast, resolution, etc. of the image will seriously affect the accuracy of the anchor point matching; the matching of the text area in the existing method is through The relative position of the point is used to determine the text area, but handwritten text, dot printing text, etc. will have unpredictable position offsets, and the positioning of the text area is often wrong

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, device and equipment for text detection and analysis based on depth neural network
  • Method, device and equipment for text detection and analysis based on depth neural network
  • Method, device and equipment for text detection and analysis based on depth neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] figure 1 It is a flow chart of the deep neural network-based text detection and analysis method provided by Embodiment 1 of the present invention. Such as figure 1 As shown, the text detection and analysis method based on the deep neural network provided by the embodiment of the present invention includes the following steps:

[0039] 101. Perform template labeling, and generate labeling template information.

[0040] Specifically, the size and relative position of the anchor point and the non-anchor text area of ​​the annotation template, and the mapping relationship between the entity and the anchor point and the non-anchor text area are generated to generate annotation template information. This process is used to mark the position and category of all fields that need to be recognized, including whether it is an anchor point, whether the text line is a date, Chinese character, English, etc. The generated annotation template information is used for subsequent templ...

Embodiment 2

[0064] image 3 It is a schematic flow chart of a text detection and analysis method based on a deep neural network provided in Embodiment 2 of the present invention, as image 3 As shown, the text detection and analysis method based on the deep neural network provided by the embodiment of the present invention includes the following steps:

[0065] 201. Train to obtain a preset deep neural network detection model.

[0066] Specifically, use a sample generation tool to generate a sample;

[0067] use samples for training;

[0068] Obtain a preliminary deep neural network detection model;

[0069] Form data reflux in detection applications to obtain more new samples;

[0070] Fine-tuning on the preliminary deep neural network detection model with new samples.

[0071] In the above process, the text lines in the sample will be classified (including but not limited to the classification of anchor points and non-anchor points), and then the detection model will be trained.

...

Embodiment 3

[0093] Figure 4 It is a schematic structural diagram of a text detection and analysis device based on a deep neural network provided in Embodiment 3 of the present invention, as Figure 4 As shown, the text detection and analysis device based on the deep neural network provided by the embodiment of the present invention includes:

[0094] Annotation module 31 is used to perform template annotation and generate annotation template information; specifically, the size and relative position of the template annotation anchor point and non-anchor text area, and the mapping between entities and the anchor point and non-anchor text area Relationship, generate annotation template information;

[0095] The text area detection module 32 is used to detect and classify the text area of ​​the image to be detected by using the preset deep neural network detection model, and generate text area information with categories; specifically, use the preset deep neural network detection model to d...

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 text detection and analysis method, a device and equipment based on a depth neural network, belonging to the technical field of depth learning and image processing. The method comprises the following steps of: performing template labeling to generate labeling template information; using the preset depth neural network detection model to detect and classify the text regionof the image to be detected, and generating the text region information with categories; template matching being performed according to the label template information and the text area information with categories to generate structured information data. The invention can realize fast and accurate detection and analysis according to various fields in a bill image, has the characteristics of real-time, accuracy, universality, robustness and expandability for the detection and analysis of a document image, and can be widely applied to the field of image text detection, analysis and recognition containing a plurality of texts.

Description

technical field [0001] The present invention relates to the technical field of deep learning and image processing, in particular to a text detection and analysis method, device and equipment based on a deep neural network. Background technique [0002] Object detection is a computer vision (CV) and image processing-related computer technology that detects instances of semantic objects of a specific category (such as humans, buildings, and cars) from digital images and videos. Object detection is relatively well developed in the fields of face detection and pedestrian detection. Object detection has a large number of application scenarios in the field of computer vision, including image retrieval and video surveillance. [0003] Neural Network (Neural Network) is an artificially designed network structure, and its essence is Multi-layer Perceptron (Multi-layer Perceptron). The perceptron is composed of several neurons (Neuron), each neuron receives an input signal from the ...

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): G06K9/20G06K9/34G06K9/62G06N3/04
CPCG06V10/22G06V30/153G06N3/045G06F18/241
Inventor 钱浩然谢畅王恒徐宝函陆王天宇
Owner ZHONGAN INFORMATION TECH SERVICES CO LTD
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