Movatterモバイル変換


[0]ホーム

URL:


Skip to content

Navigation Menu

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up

Atuomated attendance system which takes video input of entire class and uses face recognition to create database of present students at end of lecture

NotificationsYou must be signed in to change notification settings

bharshal/BE_Project

Repository files navigation

This code is designed to create database of attendance for classroom from live video feed in real time.

It doesn't require any input/intervention after code is run.

It will take periodic frames from video feed and run face detection and recognition on those frames.

As lecture is going on all students won't be recognised every time, hence it keeps record of each student in each frame and calculates number of times he/she was recognised.

This also takes care of false positives and makes sure student is present throughout the lecture.

At the end of the lecture it uses a threshold value to select which students should be marked present in the final database

Rundatabase.py to get final output

This is the confidence when tested on set of 15 students.

01234567891011121314
0000000000000000
10160301020002001
20011100010000011
30012800040022000
40201151101421000
50001014000100000
60000011200000000
7000120060002001
80001000012030000
9000002100800001
100000000000130000
110120000120123010
12000000000000600
13002000000001040
140000000000000016

You will need to paste these 2 files in the utils folder(1)shape_predictor_68_face_landmarks.dat(2)recog.ymlThey are too large to be uploaded to github.

You can download them from following link and paste them in utils folder:Link

Code is under Apache 2.0 licenceThe code uses Google's Tensorflow object detection api for face detection. Please refer to the license of tensorflow.

About

Atuomated attendance system which takes video input of entire class and uses face recognition to create database of present students at end of lecture

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages


[8]ページ先頭

©2009-2025 Movatter.jp