Model Files can be donwloaded from BaiduNetDisk：
Link：https://pan.baidu.com/s/1Y-hDUL2TNdzx8S3RjyATdg?pwd=lhu8
Extract Code：lhu8
- Face recognition: identify the identity and select the face.
- Expression recognition: Using a pre-trained model, it was able to recognize seven different expressions: angry, disgusted, fearful, happy, sad, surprised, and neutral.
- Webcam recognition in real time.
- Grab the top left corner of the screen for real-time recognition.
- Take a picture (screenshot).
The system has good completeness, large workload and rich functions, which can realize single and multi-person recognition of members of the test team, and can sensitively identify the real-time expressions of current characters. The system has a self-designed graphical interactive interface. At the same time, its functions are powerful, the interface is simple and clear, and the mobility is excellent.
Face recognition is a kind of biometric identification technology based on facial features. It mainly uses camera or screen video stream to collect face information, and automatically tracks faces for recognition.
In recent years, with the development of artificial intelligence and the needs of national economic development and security defense, China's face recognition market continues to expand, the technical level continues to improve, and it has achieved the world's leading position in algorithms.
With the continuous development of artificial intelligence and the quiet arrival of the intelligent era, biometric technology represented by face recognition is becoming more and more popular. From security, payment, finance to education, medical care and transportation. "Using your face" has increasingly become the norm, bringing a lot of intelligence, safety and convenience to people's production and life.
Convolutional neural network (CNN) is a kind of feedforward neural network, which includes convolutional computation and has a deep structure, and is one of the representative algorithms of deep learning. With the continuous advancement of technology, people were inspired to create neural networks while studying the human brain.
Neural networks are composed of many interconnected neurons, and signals can be enhanced or suppressed between different neurons by adjusting the weight factor x that transmits the connections between them. In short, Convolutional Neural Networks are deep learning models that resemble the multi-layered perceptrons of artificial neural networks and are commonly used to analyze images and videos.
With the development of society, the progress of science and technology, the pace of life is gradually accelerating, which will expose many problems, and there are more and more people suffering from depression. So "Real-time Face Monitoring and Expression Recognition System Based On CNN" came into being.
Through real-time monitoring and collection of patients' facial feature information, the system can play a role in recognizing the facial expressions of portraits and characters after effective training, which is so convenient for patient monitoring and treatment. When negative emotions, such as sad, appear on the monitor screen, the patient is immediately identified and treated. In this way, the real-time monitoring of the hospital is convenient, and the process of treatment is accelerated, which is conducive to the recovery of patients, and will prevent patients from excessive behavior to harm themselves and others.
-
Create a virtual environment with Python 3.7
-
Install related libraries.
pip install -r requirements.txt
Run run_me.py
Done!
