TANDEM: A Web-Based Text and Image Data Generator   Kelly Blanchat, Jojo Karlin, Stephen Real, Christopher Vitale DH Praxis Spring 2015   ABSTRACT   TANDEM is a Python-based Django web-application that generates text and image data from files submitted by the user. TANDEM is for scholars seeking quantitative insight into a corpus consisting of picture books, comics, advertisements, and other images with overlaid text. The TANDEM application compiles three existing open source technologies: Tesseract OCR, Open Source Computer Vision (OpenCV), and a natural language processing library called Natural Language Toolkit ... Read more