PixLabeler: User Interface for Pixel-Level Labeling of Elements in Document Images
Authors:
- Eric SaundESEric Saund
- Jing LinJLJing Lin
- Prateek SarkarPSPrateek Sarkar
- 1 January 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15205363,p. 646-650
Abstract
We present a user interface design for labeling elements in document images at a pixel level. Labels are represented by overlay color, which might map to such terms as ldquohandwritingrdquo, ldquomachine printrdquo, ldquographicsrdquo, etc. The primary purpose is to streamline processes for manual production of ground truth data, which is necessary for training algorithms and evaluating performance. Unlike general paint-type programs, the UI design is targeted specifically toward selection of collections of foreground pixels that are likely to be meaningful elements in a document image analysis context. Our implementation, called PixLabeler, is available for download and allows customized plug-ins for bootstrapping according to the labeling task.Keywords
This publication has 17 references indexed in Scilit:
- Segmentation and labeling of documents using conditional random fields2007
- Pixel-Accurate Representation and Evaluation of Page Segmentation in Document Images2006
- A scale space approach for automatically segmenting words from historical handwritten documentsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2005
- Machine-Printed from Handwritten Text Discrimination2004
- Machine printed text and handwriting identification in noisy document imagesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- Document image ground truth generation from electronic text2004
- Perceptually-supported image editing of text and graphics2003
- A system for machine-written and hand-written character distinction2002
- Automatic ground-truth generation for skew-tolerance evaluation of document layout analysis methods2002
- A protocol for performance evaluation of line detection algorithmsMachine Vision and Applications, 1997