Unlock instant, AI-driven research and patent intelligence for your innovation.

Text detection method, device, electronic device and computer storage medium

A text detection and text technology, applied in the computer field, can solve the problems of cost, time-consuming, large computing resources, etc.

Active Publication Date: 2021-04-30
BEIJING YIZHEN XUESI EDUCATION TECH CO LTD
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of this, the embodiments of the present application provide a text detection method, device, electronic equipment, and computer storage medium to overcome the defects in the prior art that consume a large amount of computing resources and take a long time when detecting text

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
  • Text detection method, device, electronic device and computer storage medium
  • Text detection method, device, electronic device and computer storage medium
  • Text detection method, device, electronic device and computer storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] Embodiment 1 of the present application provides a text detection method, such as figure 1 as shown, figure 1 It is a flow chart of a text detection method provided in the embodiment of the present application, and the text detection method includes the following steps:

[0035] Step 101, perform feature extraction on the text image to be detected, and obtain a real text probability map and at least one pixel class probability map corresponding to the text image to be detected.

[0036] It should be noted that the text detection method in the embodiment of the present application is applicable to text detection with various text densities, including but not limited to regular density text, dense density text, sparse density text, especially dense density text. Among them, specific indicators for determining whether a certain text is a dense text can be appropriately set by those skilled in the art according to the actual situation, including but not limited to: accordi...

Embodiment 2

[0052] Optionally, in an embodiment of the present application, step 103 may further include step 103a and step 103b.

[0053] Step 103a, according to at least one pixel class probability map, determine the pixel class of each pixel in the text image to be detected.

[0054] Take a text image to be detected that includes pixels of four pixel categories as an example. The probability map of each pixel category indicates the probability that each pixel in the text image to be detected belongs to the category. For example, the pixel to be detected The text image includes 200 pixels, and the first type pixel class probability map indicates the probability that 200 pixel points belong to the first type pixel point, that is, the probability that these 200 pixel points are located in a non-overlapping area. Similarly, the second to fourth pixel category probability maps represent the probabilities of 200 pixels belonging to the second to fourth categories of pixels respectively. Tha...

Embodiment 3

[0061] Optionally, in an embodiment of the present application, step 105 may further include step 105a1-step 105a3.

[0062] Step 105a1: Calculate connected domains for at least one pixel-type binary image except for the reference pixel-type binary image to obtain at least one candidate connected domain.

[0063] Taking the binary image of four pixel categories as an example, a binary image of a pixel category contains at least one text area, and the remaining binary images of the second to fourth pixel categories are all connected domains , the second to fourth connected domains can be obtained, and the second to fourth connected domains are used as connected domains to be selected, that is, at least one connected domain includes the second connected domain, the third connected domain and the fourth connected domain Class connected domain. In step 105a1, when obtaining at least one connected domain to be selected, it can be processed in parallel, that is, to obtain the conne...

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

Embodiments of the present application provide a text detection method, device, electronic equipment, and computer storage medium. When performing text detection, first perform feature extraction on the text image to be detected, and obtain a real text probability map corresponding to the text image to be detected and at least one A pixel class probability map; then binarize the real text probability map to obtain a real text binary map, and generate at least one pixel class binary map according to the real text binary map and at least one pixel class probability map; Determine the reference pixel class binary map from at least one pixel class binary map, and calculate a plurality of reference connected domains corresponding to the reference pixel class binary map; according to multiple reference connected domains and at least one pixel class binary By removing the binary image of the reference pixel category binary image in the figure, the coordinates of each real text region in the text image to be detected can be obtained, and the text detection result of the text image to be detected can be obtained. Through the above method, the speed and efficiency of text detection are improved.

Description

technical field [0001] The embodiments of the present application relate to the field of computer technologies, and in particular to a text detection method, device, electronic equipment, and computer storage medium. Background technique [0002] Text detection is a technology that detects text regions in images and marks their bounding boxes. Text detection has a wide range of applications and is a pre-step for many computer vision tasks, such as image search, text recognition, identity authentication, and visual navigation. [0003] The main purpose of text detection is to locate the position of a text line or character in an image. Currently, a popular text detection method is a text detection method based on a sliding window. Based on the idea of ​​general target detection, this method sets a large number of anchor boxes with different aspect ratios and different sizes, and uses these anchor boxes as sliding windows to perform convolution operations on the image or the f...

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 Patents(China)
IPC IPC(8): G06K9/32G06K9/46G06K9/34
CPCG06V20/62G06V10/267G06V10/44G06V30/10
Inventor 秦勇李兵
Owner BEIJING YIZHEN XUESI EDUCATION TECH CO LTD