Identification processing method and device for medical image

Abstract

The invention discloses an identification processing method and device for a medical image. The method comprises the following steps that: detecting a medical image, and screening the character area of the medical image; carrying out distribution statistics on the pixel of the character area, and selecting a plurality of key information points according to gradient change; adopting the plurality of key information points to construct and clip an external matrix corresponding to the character area; converting the clipped external matrix into a grayscale image; and carrying out picture identification on the grayscale image, and automatically extracting information into a text box. Through the technical scheme provided by the invention, information extraction accuracy can be improved, and inquiry efficiency is improved.

Description

Technical field [0001] The present invention relates to the field of communications, and in particular to a method and device for identifying and processing medical image pictures. Background technique [0002] With the rapid development of science and technology, the high popularity of the Internet has greatly shortened the distance and time of interaction between people, thus driving the rise of Internet hospitals. Internet hospitals have brought us a lot of convenience, benefiting the public, especially in relatively remote and backward areas, so that the public can consult famous experts and professors in Beijing, Shanghai, Guangzhou and other regions without leaving home; not only saves the public travel expenses, but also The important thing is to shorten the speed of patients' visits and medical treatment, and bring convenience to many patients' timely medical treatment. [0003] Internet hospitals mean networked consultations, including the electronicization of examination...

AI Technical Summary

Problems solved by technology

[0005] The main purpose of the present invention is to disclose a method and device for identifying and processing medical images, so as to at least solve the problem that laboratory tests and medical records in related technologies are all based on physical documents of primary hospitals, and are uploaded by the staff of the Internet hospital platform. The pictures of medical records and other information provided by the grassroots are manually entered to realize electronicization, and the inspection pictures such as test sheets are manually reviewed by doctors from both sides, which takes a long time and reduces the efficiency of consultation.

Images