Mobile Phone Camera-Based Video Scanning of Paper Documents

Muhammad Muzzamil Luqman (1) , Petra Gomez-Krämer (1) , Jean-Marc Ogier (1)

1 L3I - Laboratoire Informatique, Image et Interaction - EA 2118

Mobile phone camera-based document video scanning is an interesting research problem which has entered into a new era with the emergence of widely used, processing capable and motion sensors equipped smartphones. We present our ongoing research on mobile phone camera-based document image mosaic reconstruction method for video scanning of paper documents. In this work, we have optimized the classic keypoint feature descriptor-based image registration method, by employing the accelerometer and gyroscope sensor data. Experimental results are evaluated using optical character recognition (OCR) on the reconstructed mosaic from mobile phone camera-based video scanning of paper documents.

Mots clés: Camera-based document image analysis Document image mosaicing Image registration

Domaines: Informatique [cs]; Vision par ordinateur et reconnaissance de formes [cs.CV]; Traitement des images [eess.IV]; Informatique mobile; Traitement du signal et de l'image [eess.SP]; Traitement du texte et du document

Muhammad Muzzamil Luqman, Petra Gomez-Krämer, Jean-Marc Ogier. Mobile Phone Camera-Based Video Scanning of Paper Documents. Masakazu Iwamura ; Faisal Shafait. Camera-Based Document Analysis and Recognition, 8357, Springer International Publishing, pp 164-178, 2014, Volume 8357 of the series Lecture Notes in Computer Science, 978-3-319-05167-3. ⟨10.1007/978-3-319-05167-3_13⟩. ⟨hal-01330116⟩