Method, device and apparatus for processing portrait based on weight value

Abstract

The invention discloses a portrait processing method, a device and an apparatus based on a weight value, wherein the method comprises the following steps: acquiring characteristic data of each portrait and calculating saturation of the characteristic data; According to the saturation degree, the characteristic data which accords with the sample rule is selected as the sample data. Using Logistic Regression Algorithm to Calculate Sample Weights of Sample Data; Extracting a sample portrait corresponding to each sample weight value, and storing the sample weight value and the sample portrait in adatabase corresponding to each sample weight value; The sample portrait is selected or classified according to the sample weight value in the database, and the result is displayed on the display screen. Adoption of the above programme, regardless of whether the saturation value of the portrait feature data is high or low, Logistic regression algorithm can be used to calculate the corresponding weight values of each portrait, so that the portrait can be selected and classified according to these weight values, thus reducing the situation that the accuracy of portrait selection and classification decreases due to the data loss of low saturation portrait.

Description

technical field [0001] The present application relates to the technical field of image processing, in particular to a method, device and equipment for image processing based on weight values. Background technique [0002] With the improvement of people's living standards, there are more and more industries serving the masses, and some service companies have more and more employees. In order to facilitate company management, it has become an important part of the company to select or classify these employees according to their portraits. question. [0003] At present, the characteristics of employee portraits are generally used to select and classify. The existing methods use the saturation of the portraits to fill in the low-saturation features or discard them through binary classification. Then screen the required employee portraits according to the degree of saturation, or classify the employee portraits, and then complete the screening and classification of employees. ...

AI Technical Summary

Problems solved by technology

The main purpose is to solve the technical problem that the selection of portrait features is not accurate enough, which may easily cause errors in low-saturation portrait features or fail to obtain low-saturation portrait features, which affects the screening and classification of portraits.

Images