Artificial intelligence big homework - face recognition system (1): completion process

1. Self-introduction
　　I am a computer major student of Zhejiang Normal University. The reason for opening csdn to write is mainly inspired by this artificial intelligence course. I want to simply share my experience with you. I hope everyone will encounter the same problem. Provides a solution to the problem. Afterwards, I will continue to share a series of experiments and works in the university. I also hope that in this way, I can sort out and summarize the experience of my freshman and sophomore years. If you like it or have any questions, you can leave a message in the comment area, if you don’t like it, don’t spray it, thank you!
2. Job requirements
　　Basic tasks: To develop a face recognition system, it is required to use the ORL face database as the experimental data to construct a complete face recognition system, which requires an interface, and can choose to input a single image and display the image, and then Realize the recognition of the image, and output the corresponding recognition result image. Five photos of each person in the database are required as a training set, and the other 5 photos are used as a test set, and the correct rate of recognition is counted. (The program language used in the experiment is not limited, and the face recognition algorithm is not limited)
Extended tasks: 1. Implement a complete face recognition system, collect photos by yourself, require more than 30 people, and realize two modes of cameras and photos as input people For face detection and recognition, the accuracy rate must be more than 95%. 2. Realize a complete multi-person face recognition system, collect photos by yourself, require more than 30 people, realize multi-face detection and recognition with camera and photo as input, and the accuracy rate requires more than 95%.
3.
　　In fact, there was no idea at the beginning of the bitter journey. It was completely crossing the river by feeling the stones, searching for information while realizing it, and then gradually shifting from obsession to final realization. The completion cycle is about a week, of which 3-4 days are basically They always stay up late every day, and one time the most intense liver was at 4 o'clock, and then the bug was still not solved, and he vomited blood. I got up the next day and looked at the program and changed my mind to realize it, so I remind everyone to finish the homework early in the final exam month and do it early, and don’t delay until the final deadline, or you will really die.
　　Speaking of the project, at the beginning, some big guys said that it can be realized by using opencv, so I tried it, and it did achieve certain effects (we will elaborate on what was realized later), but in the end I gave up this direction (but it should be possible It has been realized, and some students have also completed this project by using this), because I think it is too troublesome to learn that set of models for expansion here, so I abandoned this idea and only stopped at a small demo (but this Realization does get me). The other direction I know is to use some modules and tools of C++ and matlab, because I am not very familiar with it and I am not willing to learn it, so I don't think about it.
　　The master plan I adopted is to useface_recognitionModule to achieve, the final interface is to usetkintermodule is implemented.
4. Display of the final results

5. The next preview
Use opencv to realize simple face detection