Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Automatic acne grading method based on deep learning

An automatic grading and deep learning technology, applied in neural learning methods, image analysis, image data processing, etc., to achieve convenience for doctors and patients, and save time for diagnosis and treatment

Pending Publication Date: 2019-07-12
南京所由所以信息科技有限公司
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Traditional acne grading methods require relatively strong professional knowledge and clinical experience, and with the increasing number of acne patients, people began to explore a new automatic grading method

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
  • Automatic acne grading method based on deep learning
  • Automatic acne grading method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] The technical solution of the present invention will be further described in detail below with reference to the drawings and embodiments.

[0016] An automatic classification method of acne severity based on deep learning of the present invention, such as figure 1 As shown, it specifically includes the following steps:

[0017] Step 1: Collect the facial image of the face to be detected. The facial image of the face to be detected includes the left face, the front face and the right face image. The facial feature point detection network is used to detect and extract the positions of several facial feature points and normalize them Processing, according to the location of the feature points, the face image is segmented to obtain the left face part, the right face part, the front face half and the front face bottom half, and the invalid areas such as facial features are removed.

[0018] Step two, stitch the four partial images obtained by segmentation according to their positi...

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 invention relates to an acne severity automatic grading method based on deep learning, and the method comprises the following steps: S1, manufacturing a human face sample data set, and training adeep convolutional neural network grading model; S2, collecting a to-be-detected face image, identifying face feature points in the image by utilizing a face feature point detection network, carryingout region cutting, and removing invalid regions at the same time; and S3, splicing the cut images to obtain a skin region image, and inputting the skin region image into the deep convolutional neuralnetwork classification model to obtain a classification result. The face images of the front face, the left face and the right face of the patient are obtained through the camera. A computer automatically conducts severity grading on the face acne through a pre-trained deep convolutional neural network grading model, and accurate auxiliary information is provided for diagnosis of the disease condition of the patient.

Description

Technical field [0001] The invention relates to the technical field of skin acne detection, in particular to an automatic acne grading method based on deep learning. Background technique [0002] Acne is a chronic inflammatory skin disease of the hair follicle sebaceous gland unit. It mainly occurs in adolescents and has a great impact on the psychology and social life of adolescents, but it can often be relieved or healed naturally after puberty. The clinical manifestations are characterized by pleomorphic skin lesions, such as acne, papules, pustules, and nodules that occur on the face. Acne grading is the classification of the severity of acne according to the type of skin lesions on the patient's face and the number of skin lesions. Different acne severity levels can be treated clinically with different treatment plans. At present, the more common classification methods in hospitals generally divide acne into four levels: mild (level 1): only acne; moderate (level 2): ​​infl...

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): G06K9/00G06K9/34G06N3/04G06N3/08G06T7/00
CPCG06N3/08G06T7/0012G06T2207/10004G06T2207/30088G06T2207/30201G06T2207/20081G06T2207/20084G06V40/172G06V40/168G06V10/267G06N3/045
Inventor 张守纳
Owner 南京所由所以信息科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com