Text recognition method and device for medical data pictures

A text recognition and optical character recognition technology, applied in the field of text recognition for medical data pictures, to achieve the effect of improving the division accuracy and improving the user experience
CN107315989AActive Publication Date: 2017-11-03天方创新(北京)信息技术有限公司
5 Cites 10 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
天方创新(北京)信息技术有限公司
Publication Date
2017-11-03

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a text recognition method and device for medical data pictures. The method comprises steps of based on an optical character recognition OCR algorithm, carrying out text region division on a to-be-recognized medical data picture so as to obtain multiple sub-blocks; determining position information and type information of the sub-blocks and acquiring multiple to-be-combined sub-blocks from the sub-blocks according to the position information and the type information; recognizing text contents of the to-be-combined sub-blocks; and according to the text contents of the to-be-combined sub-blocks, combining the to-be-combined sub-blocks. According to the invention, a problem of inaccurate division of a text region of a picture caused by inconsistent represent forms of the picture can be effectively avoided; division precision of the text region of the picture is improved; and user experience is improved.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the medical field, in particular to a text recognition method and device for medical data pictures. Background technique

[0002] In the related art, a traditional optical character recognition (Optical Character Recognition, OCR) algorithm may be used to divide the text area of ​​the picture. In particular, it is particularly obvious to divide the text area of ​​a picture containing various contents. However, the traditional OCR algorithm may cause inaccurate division of text regions due to different representations of images. For example, when dividing the text areas of different forms of medical information pictures issued by different medical institutions, the problem of dividing the information of the same inspection item into another text area may occur, specifically as figure 1 shown. Contents of the invention

[0003] The present invention aims to solve one of the technical problems in the related art at least to a...

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