I. Project introduction
This internship program is designed for students who plan to apply for computer science and technology, digital image processing, and automated pattern recognition. Students will work with the Chinese Academy of Sciences instructors to learn the basics of pattern recognition, machine learning techniques, and finally complete a complete face recognition program. After the internship, the tutor will issue a letter of recommendation based on the student's performance.
Second, the project content
The project name is a face recognition study based on PCA and SVM. The face recognition problem involves digital image processing technology, pattern recognition technology, statistics, programming and other knowledge. It is a classic computational science problem. More importantly, the problem stems from life and can go into life. The starting point of the solution can be very intuitive. After the in-depth, you need to master very difficult knowledge and technology. The primary method can get good results and want to do it. To the extreme, there are huge challenges. This project takes a medium-difficult solution as an example. It systematically introduces the ins and outs of face recognition problems and extends it to more general statistical machine learning problems, and finally completes a complete face recognition program.
Third, the project teacher background
The instructor teaches at the intelligent information processing laboratory of a well-known research institute. Co-authors with the Scripps Research Institute and Stanford University in the United States published more than 10 SCI papers, including the first author with an impact factor greater than 7, and the first author's impact factor greater than 5, participating in several national 973, 863 projects. . He is a reviewer for several SCI international journals.
Fourth, enrollment objects and requirements
Excellent undergraduates and some excellent high school students, who plan to apply for computer science and technology, digital image processing, automatic pattern recognition and other related majors, in order to allow students to better complete research projects, the project team will take the form of written test and interview. Screen students.
The remote research and guidance project lasts for one month, and the specific time can be arranged according to the needs of the students and the appropriate time. The advantage of this project is that for students with long enough application time, the tutor can help students to complete one or several professional research tasks in a deeper, more comprehensive and systematic manner, so that students can participate in the whole process of scientific research projects. Experience the sense of accomplishment in solving scientific problems, and at the same time let students know the background and frontier dynamics of the field. In addition to regular research project discussion courses, students can ask relevant questions at any time during the project cycle, and get professional guidance from the instructors, so that students can experience the real work and life status of a researcher in advance. After the project is over, the instructor will issue a letter of recommendation based on the student's performance. The specific course schedule is as follows:
|the first week||Overview of face recognition; master the basic knowledge of digital image processing; use matlab to complete the basic operation of the image.|
|the second week||Learning pattern recognition basic knowledge; establishing a face database; completing preprocessing of face images;|
|The third week||Learn the basics of PCA and SVM; write related program modules;|
|the fourth week||System integration, performance optimization, results testing; completion of research reports; review of students' full performance; introduction of relevant knowledge.|