Using Artificial Intelligence Systems for Autonomous Visual Comprehension and Handwriting Generation

Overview

Objectives/Goals Our object is to see if multiple neural networks can be used in a pipeline to parse various types of offline math problems and generate a handwritten answer as well as a human would (with at least 95% accuracy). Note: offline here means as an array of pixels, while online means as a collection of points and strokes. Methods/Materials Laptop and C++ compiler suite along with libraries for image processing and neural networks. We also used a lot of different openly published training data sets. The pipeline process an image of a worksheet taken from a webcam in a series of five steps: division, identification, parsing, solving, and finally writing the answer. Results We found the accuracy of our pipeline to be difficult to measure, as even though all the components are above 90% accurate on tests sets, the actual input of the pipeline is a real-world image which can vary greatly in quality, readability, and style. Thus, further testing is required to analyze its specific accuracy. Conclusions/Discussion While the scope and breadth of our pipeline does not greatly improve on previous equation recognizers#especially online ones#our applications are not deeply rooted in equation parsing, and thus many of the same concepts can be used to solve other difficult tasks such as grading simple free-response tests.

Awards (1)

• Honorable Mention

Competition history

• CSEF 2016 Mathematics & Computer Science · Entry S1405

Resources

• CSEF project summary ↗

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Browse more like this

• All Computational Sciences projects
• CSEF Computational Sciences projects
• Every CSEF 2016 project