A document skew detection method using run-length encoding and the Hough transform
Document image analysis
Algorithm for text page up/down orientation determination
Pattern Recognition Letters
Cryptological Mathematics
Blobworld: Image Segmentation Using Expectation-Maximization and Its Application to Image Querying
IEEE Transactions on Pattern Analysis and Machine Intelligence
Projection profile based skew estimation algorithm for JBIG compressed images
ICDAR '97 Proceedings of the 4th International Conference on Document Analysis and Recognition
A shape and image merging technique to solve jigsaw puzzles
Pattern Recognition Letters
Document Skew Detection Using Minimum-Area Bounding Rectangle
ITCC '00 Proceedings of the The International Conference on Information Technology: Coding and Computing (ITCC'00)
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
Color segmentation for text extraction
International Journal on Document Analysis and Recognition
A Generic Method for Determining the Up/Down Orientation of Text in Roman and Non-roman Scripts
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Color Text Extraction from Camera-based Images the Impact of the Choice of the Clustering Distance
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Text line segmentation of historical documents: a survey
International Journal on Document Analysis and Recognition
Jigsaw Puzzles, Edge Matching, and Polyomino Packing: Connections and Complexity
Graphs and Combinatorics
Skew Detection for Chinese Handwriting by Horizontal Stroke Histogram
ICDAR '07 Proceedings of the Ninth International Conference on Document Analysis and Recognition - Volume 02
Solving jigsaw puzzles using image features
Pattern Recognition Letters
RoboCup 2007: Robot Soccer World Cup XI
Combining Forces to Reconstruct Strip Shredded Text Documents
HM '08 Proceedings of the 5th International Workshop on Hybrid Metaheuristics
Meta-heuristics for reconstructing cross cut shredded text documents
Proceedings of the 11th Annual conference on Genetic and evolutionary computation
Image segmentation using histogram fitting and spatial information
MDA'06/07 Proceedings of the 2007 international conference on Advances in mass data analysis of signals and images in medicine biotechnology and chemistry
Salient region detection and segmentation
ICVS'08 Proceedings of the 6th international conference on Computer vision systems
Contour-shape based reconstruction of fragmented, 1600 BC wallpaintings
IEEE Transactions on Signal Processing
Document analysis applied to fragments: feature set for the reconstruction of torn documents
DAS '10 Proceedings of the 9th IAPR International Workshop on Document Analysis Systems
Hi-index | 0.00 |
In Archaeography, Philology, Forensics, and related research areas fragments of documents are very common. These fragments are the basis for the subsequent reconstruction process, where the goal is to make the original information spread over several fragments visible again. The fragments can originate from paper shredders, hand torn pages or in the case of ancient manuscripts this is due to bad storage conditions, or other destroying facts. So we can distinguish between an "on-purpose" destruction because the information contained on the pages should not be readable anymore or a "time-induced" destruction for ancient documents which is unintentional. Nevertheless the reconstruction of document fragments is an interesting research question. This paper shows a preliminary step for the page reconstruction namely the automatic orientation of snippets in order to eliminate the rotation in the later reconstruction (puzzling) process. Furthermore features like paper color and the color of the inks used are analyzed as a pre-classification step to find matching snippets. In the case of "on-purpose" destruction there is no a-priori information on which fragment belongs to which page which makes a reconstruction based on thousands of fragments from unknown sources difficult since the combinatorial effort explodes (NP-hardness). Preliminary results on orientation and color segmentation are presented and show that these pre-processing steps can be performed reliably and can be used for reconstruction and snippet classification.