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

Hair image recognition method based on dermatoscope, computer device and storage medium

An image recognition and dermoscopy technology, applied in the field of image processing, can solve the problems of high error rate, low work efficiency, missed hair detection and false detection, etc., to achieve low missed detection rate, avoid low efficiency and high error rate. Effect

Active Publication Date: 2021-07-13
GUANGZHOU UNIVERSITY
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to artificial low efficiency and high error rate, the recognition of mature hair and immature hair is inefficient and error-prone, which further leads to low efficiency and poor effect of subsequent recognition results.
Even with the help of an instrument for observation, because the image taken by the instrument is prone to interference factors such as uneven illumination, noise and blur, it is easy to cause missed and false detection of hair
The results of manual recognition can only be recorded manually, which is difficult to record in an intuitive way, which is not conducive to later viewing and inspection

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
  • Hair image recognition method based on dermatoscope, computer device and storage medium
  • Hair image recognition method based on dermatoscope, computer device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] In this example, refer to figure 1 , a hair image recognition method based on dermatoscopy, comprising the following steps:

[0041] S1. Acquiring the image to be recognized collected by the dermatoscope;

[0042] S2. Preprocessing the image to be recognized; the preprocessing is used to repair and enhance the image to be recognized;

[0043] S3. Binarize the image to be recognized;

[0044] S4. Perform hair recognition on the image to be recognized, so as to determine the region where hair exists in the image to be recognized;

[0045] S5. Perform hair discrimination on the image to be recognized, so as to determine the mature hair area and immature hair area;

[0046] S6. Identify the hairs located in the mature hair region and satisfying the pixel mean threshold value as mature hairs, and identify other hairs as immature hairs.

[0047] In step S1, the image to be recognized can be an image taken by a dermatoscope with exposed skin areas including the head, arms,...

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 discloses a hair image recognition method based on a dermatoscope, a computer device and a storage medium, and the method comprises the steps: obtaining a to-be-recognized image collected by the dermatoscope, carrying out preprocessing, binarization processing, hair recognition and hair discrimination of the to-be-recognized image, determining a mature hair region and a young hair region, identifying the hair which is located in the mature hair area and meets the pixel mean threshold condition as mature hair, and identifying other hair as young hair. The dermatoscope image does not need to be observed by naked eyes, low efficiency and high error rate of manual identification are avoided, and compared with the technology of manual observation through an instrument, computer graphic processing is introduced, so that the efficiency is greatly improved. The image quality reduction caused by interference factors such as miscellaneous points and blurring caused by uneven illumination, scalp oil stain reflection, skin color and the like can be effectively dealt with, and a high recall ratio and a low omission ratio are maintained. The invention is widely applied to the technical field of image processing.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a dermatoscope-based hair image recognition method, a computer device and a storage medium. Background technique [0002] Classifying human hair into mature hair and immature hair is an important means in the fields of medicine, makeup, and cosmetology. In the prior art, it mainly relies on manual identification through instruments or even naked eye observation. Due to artificial low efficiency and high error rate, the recognition of mature hair and immature hair is inefficient and error-prone, which further leads to low efficiency and poor effect of subsequent work relying on the recognition results. Even with the help of an instrument for observation, because the image taken by the instrument is prone to interference factors such as uneven illumination, noise and blur, it is easy to cause missed and false detection of hair. The results of manual recognition can only ...

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): G06K9/00G06K9/38G06K9/46
CPCG06V20/693G06V20/698G06V10/28G06V10/56
Inventor 郭四稳钟正希曾嘉晋叶文迪
Owner GUANGZHOU UNIVERSITY
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