220 likes | 356 Views
International Doctorate school on Information and Communication Technologies English for academic purposes I. “Inside the Bible” Segmentation, annotation and retrieval for a new browsing experience. Daniele Borghesani. Goals Text segmentation Picture segmentation Results Conclusions.
E N D
International Doctorate school on Information and Communication Technologies English for academic purposes I “Inside the Bible”Segmentation, annotation and retrieval for a new browsing experience Daniele Borghesani
Goals Text segmentation Picture segmentation Results Conclusions Overview
Goals Text segmentation Picture segmentation Results Conclusions Overview
Dataset description • Holy Bible of Borsod’Este (1450-1471 d.C.) • Illuminated manuscript • A lot of illustrations (biblical episodes, animals, symbols, court life scenes…) • 1200+ high resolution pages
CBIR User interface Images database Our project Preprocessing Texture analysis Annotation database Text Illustrations Illustrations classification Text recognition Feature annotation Decorated initials Decoration Picture
Our project • Automatic analysis of Bible pages • Extraction of valuable pictures • Addition of translations, commentaries, references… • Finally, media station with an appealing user interface (museums) Obscura HP Multi-Touch Video Wall
Goals Text segmentation Picture segmentation Results Conclusions Overview
Text Segmentation • Block analysis with autocorrelation • Directional histogram • Sum of pixel along each direction • Modeling with mixtures of Von Mises distributions • Very good for handling of angular data • Compact representation (5 values for a mixture of two Von Mises distributions)
Text Segmentation !Text Text
Goals Text segmentation Picture segmentation Results Conclusions Overview
Picture Segmentation Preprocess to focus on most important blobs of pixels (1) Original image (2) Background suppression and Labeling (fast) (4) Blob filling (3) Morphology
Picture Segmentation Block analysis • SVM learning with a training set of positive and negative samples ... ... Features: color (HSV and RGB histogram), texture (gradients), low frequency coefficients • SVM classification on the pages…
Goals Text segmentation Picture segmentation Results Conclusions Overview
Conclusions • We are studying a set of techniques in order to analyze the Holy Bible of Borsod’Este • Our goal is to produce a media station, available both locally (museums) and remotely (web app), to “touch” this untouchable masterpiece