A cloud service-based attendance system and method

Abstract

The invention discloses an attendance system and method based on cloud services, belonging to the technical field of image recognition; the attendance system includes an image acquisition system, a cloud analysis system, an information storage system, and a statistical system; the method learns human faces through a preset neural network The mapping of the image to the point on the Euclidean space, and then use the Euclidean distance difference to define the candidate set, and calculate the cumulative sum of the differences of each candidate set, and judge the recognition result through the accumulation sum; the present invention improves the recognition efficiency, and the newly defined difference degree λ(x ) is used to effectively measure the degree of similarity within or between classes, which can effectively improve the clarity and accuracy of image recognition, and will not be affected by factors such as lighting and complex backgrounds, making full use of existing cloud storage and cloud analysis technologies , to realize intelligent attendance and automatic statistics; this device has a simple structure, sharing and high storage efficiency, and adopts cloud storage architecture, which is safe and reliable.

Description

technical field [0001] The invention belongs to the technical field of image recognition, in particular to an attendance system and method using image recognition technology based on cloud services. Background technique [0002] Traditional attendance work is mainly carried out manually, which is prone to errors and low efficiency, and the phenomenon of impersonation and substitute attendance is serious. In recent years, with the development of machine learning and deep learning technology, some attendance systems based on face recognition have appeared. Such methods directly use CNN network to extract face features, and then use SVM and other methods to classify, which are easily affected by light changes. , Complex background and other factors lead to the problem of low recognition rate, and the phenomenon of repeated storage is serious, wasting a lot of storage space, and it is difficult to effectively meet actual needs. Especially for the attendance work with a large nu...

AI Technical Summary

Problems solved by technology

[0002] Traditional attendance work is mainly carried out manually, which is prone to errors and low efficiency, and the phenomenon of impersonation and substitute attendance is serious

In recent years, with the development of machine learning and deep learning technology, some attendance systems based on face recognition have appeared. Such methods directly use CNN network to extract face features, and then use SVM and other methods to classify, which are easily affected by light changes. , complex background and other factors lead to the problem of low recognition rate, and the phenomenon of repeated storage is serious, wasting a lot of storage space, it is difficult to effectively meet the actual needs

Especially for attendance work with a large number of people, the existing problems are more prominent

Images