Skin imaging and analyzing method

Abstract

The invention relates to an imaging and analyzing method and in particular relates to a skin imaging and analyzing method. The skin imaging and analyzing method comprises the following steps of acquiring a first digital image of a human skin part, analyzing the first digital image of the human skin part to position an area containing skin deficient, determining values related to an area containing the skin deficient, and producing a comparison between a value degree severity order and a preset value related to the public. The preset value related to the public is one of the following sets; and the set comprises (a) an age specific value, (b) geographical specific values and (c) ethnic specific values. Skin deficient can be quickly identified in a user-friendly way, so cosmetic or medical treatment can be recommended to users, and improvements and / or deterioration of the areas can be simulated.

Description

technical field [0001] The invention relates to an imaging and analysis method, in particular to a skin imaging and analysis method. Background technique [0002] The automatic recognition method of skin microscopic image symptoms includes two aspects: first, feature parameters are extracted from symptom segmentation images of skin microscopic images, and then classified and identified according to the characteristic parameters, so as to obtain the attributes of skin symptoms. [0003] In the prior art, the extraction of skin symptoms features includes: imitating the method of skin expert visual diagnosis, extracting the size of skin symptoms (represented by diameter or area, also available needle point, needle head, rice grain, mung bean, pea, peanut, longan, litchi , walnuts, eggs, fists, palms, etc.), shape (oval, hemispherical, pointed, flat, polygonal, arc, ring, irregular), color (red, yellow, brown, black, white, normal skin color, etc.), color (such as bright red, l...

AI Technical Summary

Problems solved by technology

This method is more complicated, and it is difficult to accurately grasp the analysis

[0004] There are many methods of image classification, such as statistical pattern classification, structural method, classification tree and neural network, etc., but for high-dimensional and massive classification recognition problems, and without prior knowledge, it is difficult to use these methods to obtain satisfaction. the result of

The artificial neural network method is more effective in small-scale classification, but the artificial neural network learning algorithm has its inherent shortcomings, such as the determination of the network structure has no reliable rules, and it is easy to reach the local optimum

For small-sample, multi-category training sets, the artificial neural network will have a serious over-fitting problem, that is, the problem of good fitting results but poor prediction results.

For multi-category training sets, the artificial neural network will produce serious overfitting, that is, the problem of good fitting results but poor forecasting results

Images