The Document and Pattern Recognition Lab (dprl) explores ways to improve the algorithms and tools used for
automatic recognition and retrieval of information in documents.
- (Mar.) Kenny Davila has released his collection of isolated handwritten math symbol classifiers under GNU GPL v.3 (available here). In benchmarking experiments, the best classifiers (using an SVM with RBF kernel) have recognition rates that match or exceed the best published rates for the MathBrush handwritten symbol data set.
- (Dec.) Keita Del Valle Wangari has successfully defended her HCI MSc thesis, Discovering real-world usage scenarios for a multimodal math search interface.
- (Dec.) The lab welcomes Zack Miller to the lab. For his MSc project, Zack will be working on keyword spotting in audio for the AccessMath project.
- (Dec.) The lab welcomes Nidhin Pattaniyil to the lab. Nidhin will working on combined text and math search for his MSc project.
- (Nov) Siyu Zhu has successfully defended his PhD dissertation proposal. Well done, Siyu!
- (Nov) Lei Hu has successfully defended his PhD dissertation proposal. Congratulations, Lei!