Sorry, you need to enable JavaScript to visit this website.

PhD Student Publishes State-of-the-Art Technique for Finding Text in Images at Top-Tier Conference

PhD Student Publishes State-of-the-Art Technique for Finding Text in Images at Top-Tier Conference

Siyu Zhu (PhD student, Imaging Science) and Dr. Richard Zanibbi recently had a paper on finding text in images accepted at CVPR, the leading international computer vision conference (http://cvpr2016.thecvf.com). Their paper, "A Text Detection System for Natural Scenes with Convolutional Feature Learning and Cascaded Classification," describes a new technique that obtains state-of-the-art results for the ICDAR 2015 Focused Scene Text Localization task, a standard benchmark. Previously, the best results had been obtained by a commercial system.