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

Text detection method and device, equipment and storage medium

A text detection and text technology, which is applied in the field of text detection, can solve the problems of long time consumption, slow training speed, and too long model training time, and achieve the effects of reducing training time, fast and efficient detection, and improving training speed

Pending Publication Date: 2022-04-12
南京三百云信息科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the complex calculation of intersection and union ratio will cause the training process to take longer than the horizontal rectangular frame detector, resulting in a decrease in the speed of training iterations; too many anchor boxes will greatly increase the amount of calculation for positive and negative sample matching, resulting in The speed of training iterations drops
Therefore, when the existing model detects objects such as text, the model training time is too long and the training speed is slow, which affects the model's detection of 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 and device, equipment and storage medium
  • Text detection method and device, equipment and storage medium
  • Text detection method and device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] figure 1 A schematic flowchart of a text detection method provided in Embodiment 1 of the present application is given, and the method is suitable for detecting text in pictures. The method can be executed by computer equipment, and the computer equipment can be composed of two or more physical entities, or can be composed of one physical entity. Generally speaking, the computer equipment may be a notebook, a desktop computer, a smart tablet, and the like.

[0034] Such as figure 1 As shown, a text detection method provided in Embodiment 1 specifically includes the following steps:

[0035] S101. Acquire a picture to be detected.

[0036] In this embodiment, the picture to be detected can be specifically understood as a picture with detection requirements. The picture to be detected can include backgrounds such as text, people, trees, and sky, and the picture to be detected can be images such as books, newspapers, and periodicals taken. It can be any image taken, fo...

Embodiment 2

[0046] image 3 It is a flow chart of a text detection method provided by Embodiment 2 of the present invention. The technical solution of this embodiment is further refined on the basis of the above-mentioned technical solution, and specifically mainly includes the following steps:

[0047] S301. Obtain a training sample set including at least one training sample. The training sample includes standard frame information of a standard detection frame. The standard frame information includes standard center point coordinates, standard length, standard width, and standard angle.

[0048] In this embodiment, the training sample set can be specifically understood as a set composed of one or more training samples, and the standard detection frame can be specifically understood as a standard detection frame used as a comparison standard for the prediction result. The standard frame information may specifically be understood as the detection frame information of the standard detectio...

Embodiment 3

[0101] Figure 5 It is a schematic structural diagram of a text detection device provided by Embodiment 3 of the present invention, and the device includes: an image acquisition module 51 , an input module 52 and a detection module 53 .

[0102] Wherein, the picture acquisition module 51 is used to acquire the picture to be detected;

[0103] The input module 52 is used to input the picture to be detected into a predetermined target text detection model, the loss function of the target text detection model is determined according to positive samples, and the positive samples are determined according to angles;

[0104] The detection module 53 is configured to detect the text in the picture to be detected according to the output result of the target text detection model, and obtain a target text box corresponding to the text.

[0105] An embodiment of the present invention provides a text detection device, by acquiring a picture to be detected; inputting the picture to be dete...

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 embodiment of the invention discloses a text detection method and device, equipment and a storage medium. The method comprises the steps of obtaining a to-be-detected picture; the to-be-detected picture is input into a predetermined target text detection model, a loss function of the target text detection model is determined according to a positive sample, and the positive sample is determined according to the angle; and detecting a text in the to-be-detected picture according to an output result of the target text detection model to obtain a target textbox corresponding to the text. Determining a positive sample according to the angle, calculating a loss function of the target text detection model through the positive sample, and then performing text detection on the to-be-detected picture through the target text detection model to obtain the target textbox where the text is located, thereby solving the problems of too long training time and poor text detection accuracy caused by large sample matching calculation amount in the model training process. According to the method, the problems of low training speed and low training speed are solved, the training time is greatly shortened, the training speed is increased, and rapid and efficient text detection is further realized.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of text detection, and in particular, to a text detection method, device, equipment, and storage medium. Background technique [0002] With the rapid development of artificial intelligence technology, artificial neural networks are more and more used in various fields, such as text detection, vehicle detection, person detection, etc., but there are non-level situations in the text, vehicles and other objects in the image. Needed for rotating object detection. In the rotating target detection scene, the detection results of the horizontal frame detector often carry redundant background information. In order to improve the ability of the horizontal frame detector to detect the rotating target, the research of the rotating target detector in academia and industry More and more. In the training optimization of the rotating object detector, since the traditional horizontal anchor box needs...

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): G06V30/40G06N3/04G06N3/08G06V10/22
Inventor 周源赣章水鑫
Owner 南京三百云信息科技有限公司