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

A video text recognition method and device

A recognition method and text technology, applied in the field of text recognition, can solve problems such as dependence, inaccurate recognition results, inconvenient management and use, etc., and achieve the effect of realizing recognition and avoiding dependence

Active Publication Date: 2020-01-03
BEIJING QIYI CENTURY SCI & TECH CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the candidate with the most occurrences is not necessarily the correct one, which may lead to inaccurate recognition results obtained by voting-based methods
In addition, the method of correcting by language model is heavily dependent on the composition of the corpus. To obtain accurate correction and recognition results, it is necessary to have a corpus that is consistent with the target domain; Huge corpus, causing inconvenience in management and use

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
  • A video text recognition method and device
  • A video text recognition method and device
  • A video text recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] In order to make the above objects, features and advantages of the present application more clearly understood, the present application will be described in further detail below with reference to the accompanying drawings and specific embodiments.

[0056] refer to figure 1 , which shows a flow chart of the steps of Embodiment 1 of a video text recognition method of the present application, which may specifically include the following steps:

[0057] Step 101, acquiring multiple frames of video images;

[0058] Usually, during the video playback process, the same text may appear in multiple frames of video images, and OCR will recognize the text in each frame of video images respectively. image to get multiple display results of the same text.

[0059] In a preferred embodiment of the present application, the step of acquiring multiple frames of video images may specifically include the following sub-steps:

[0060] Sub-step 1011, acquiring multiple frames of video i...

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 video text recognition method and device, the method comprising: acquiring multiple frames of video images; extracting multiple texts to be recognized from the multiple frames of video images; calculating the multiple texts to be recognized Recognize the edit distance between words; obtain one or more candidates according to the edit distance; identify the current word from the one or more candidates, and can obtain accurate recognition results; and can avoid the corpus Rely on, to realize the recognition of multi-field video text.

Description

technical field [0001] The present application relates to the technical field of text recognition, and in particular, to a video text recognition method and a video text recognition device. Background technique [0002] OCR (Optical Character Recognition) refers to an electronic device (such as a scanner or digital camera) that examines characters printed on paper, determines its shape by detecting dark and light patterns, and then uses character recognition methods to translate the shape into a computer process of writing. That is, for printed characters, the text in the paper document is optically converted into a black and white dot matrix image file, and the text in the image is converted into a text format through recognition software for further editing and processing by word processing software. . Among them, the use of OCR technology to identify video images is one of its important applications. [0003] Video OCR recognition mainly includes three links: front-end...

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): G06K9/20G06K9/00
CPCG06V20/47G06V10/235G06V30/10
Inventor 许鹏
Owner BEIJING QIYI CENTURY SCI & TECH CO LTD