Abstract
Recognizing mind maps written on a whiteboard is a challenging task due to the unconstrained handwritten text and the different graphical elements — i.e. lines, circles and arrows — available in a mind map. In this paper we propose a prototype system to recognize and visualize such mind maps written on whiteboards. After the image acquisition by a camera, a binarization process is performed, and the different connected components are extracted. Without presuming any prior knowledge about the document, its style, layout, etc., the analysis starts with connected components, labeling them as text, lines, circles or arrows based on a neural network classifier trained on some statistical features extracted from the components. Once the text patches are identified, word detection is performed, modeling the text patches by their gravity centers and grouping them into possible words by density based clustering. Finally, the grouped connected components are recognized by a Hidden Markov Model based recognizer. The paper also presents a software tool integrating all these processing stages, allowing a digital transcription of the mind map and the interaction between the user, the mind map, and the whiteboard.Keywordswhiteboard readingunconstrained document layout analysishandwriting recognition
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have