Face_ Attendance statistics of recognition face recognition

The pre condition environment preparation is as follows ：Pycharm+python3.6+sklearn+face_recognition+dlib

Step1：KNN Introduction to the algorithm

K Nearest neighbor (k-Nearest Neighbor,KNN) The core idea of classification algorithm is if a sample is in the feature space k The most similar ( That is, the closest in the feature space ) Most of the samples belong to a certain category , Then the sample also belongs to this category .KNN The algorithm can be used for multi classification ,KNN The algorithm can be used not only for classification , It can also be used for regression . By finding a sample of k The nearest neighbor , Assign the average value of the properties of these neighbors to the sample , As a predictor .

KNeighborsClassifier stay scikit-learn stay sklearn.neighbors In the bag .

KNeighborsClassifier It's easy to use , The three step ：

1） establish KNeighborsClassifier object

2） call fit function

3） call predict Function to predict .

Step2： Look at the directory structure of the project as follows

Step3： Look at the training data

Step4： Look at the test data

Step5： Look at the attendance data calculated by the model

Open as shown in the following figure ：

Step6： Two core py File parsing

KNN_Recognition_easy.py Statistics of attendance through the model py file .

KNN_Train_easy.py Model generation through training data py file . The code is as follows ：

Program entrance ：

call main()

Call down successively ：

predict()

getvalueToKey()

strTotime()

prase_filename_date()

writeExcel()