High School Statistic Graphs Recognition Based On Sparse Coding Spatial Pyramid Matching

With the rapid development of artificial intelligence technology, artificial intelligence + education will open a new educational pattern. Applying the new research of artificial intelligence to education is the focus and difficult point of international studies. Humanlike problem solving is one of the main arisen research in the filed of artificial intelligence + education. It is of very important theoretical and practical value for coming true the humanlike problem solving in artificial intelligence+ education. The paper mainly aims at studying to recognizing the high school statistical graphs of humanlike problem solving research. The main work of this paper is as follows:(1) Building high school statistic graphics database. Four typical high school statistic graphs were collected, and this database was constructed to lay the foundation for the follow - up study.(2) Designing the classification method of statistic graphics. That using sparse coding spatial pyramid matching algorithm to extract feature is used to classify the high school statistic graphs. The method can obtain the essential features of the graph,and it is helpful to get the correct classification. The experimental results show that use sparse coding spatial pyramid matching algorithm to extract feature is more stable and the classification accuracy is obtained.(3) Recognizing the question meaning of the typical high school statistic graphs.On the basis of the correct classification, this paper designs a histogram recognition algorithm according to the characteristics of the histogram. Recognizing the information in the histogram, and verifying its validity.