Refine
Document Type
- Article (1)
- Master's Thesis (1)
- ZIB-Report (1)
- Research data (1)
Language
- English (4) (remove)
Is part of the Bibliography
- no (4)
Institute
- Visual Data Analysis (4) (remove)
The historical importance of ancient manuscripts is unique since they provide information about the heritage of ancient cultures. Often texts are hidden in rolled or folded documents. Due to recent impro- vements in sensitivity and resolution, spectacular disclosures of rolled hidden texts were possible by X-ray tomography. However, revealing text on folded manuscripts is even more challenging. Manual unfolding is often too risky in view of the fragile condition of fragments, as it can lead to the total loss of the document. X-ray tomography allows for virtual unfolding and enables non-destructive access to hid- den texts. We have recently demonstrated the procedure and tested unfolding algorithms on a mockup sample. Here, we present results on unfolding ancient papyrus packages from the papyrus collection of the Musée du Louvre, among them objects folded along approximately orthogonal folding lines. In one of the packages, the first identification of a word was achieved, the Coptic word for “Lord”.
The historical importance of ancient manuscripts is unique since they provide information about the heritage of ancient cultures. Often texts are hidden in rolled or folded documents. Due to recent impro- vements in sensitivity and resolution, spectacular disclosures of rolled hidden texts were possible by X-ray tomography. However, revealing text on folded manuscripts is even more challenging. Manual unfolding is often too risky in view of the fragile condition of fragments, as it can lead to the total loss of the document. X-ray tomography allows for virtual unfolding and enables non-destructive access to hid- den texts. We have recently demonstrated the procedure and tested unfolding algorithms on a mockup sample. Here, we present results on unfolding ancient papyrus packages from the papyrus collection of the Musée du Louvre, among them objects folded along approximately orthogonal folding lines. In one of the packages, the first identification of a word was achieved, the Coptic word for “Lord”.
Aim of this thesis was to evaluate the performance of three popular machine learning methods – decision trees, support vector machines, and neural networks – on a supervised image classification task from the domain of cell biology. Specifically, the task was to classify microtubule ends in electron tomography images as open or closed. Microtubules are filamentous macromolecules of the cytoskeleton. Distribution of their end types is of interest to cell biologists as it allows to analyze microtubule nucleation sites. Currently classification is done manually by domain experts, which is a difficult task due to the low signal-to-noise ratio and the abundance of microtubules in a single cell. Automating this tedious and error prone task would be beneficial to both efficiency and consistency.
Images of microtubule ends were obtained from electron tomography reconstructions of mitotic spindles. As ground truth data for training and testing four independent expert classifications for the same samples from different tomograms were used. Image information around microtubule ends was extracted in various formats for further processing.
For all classifiers we considered how the performance varies when different preprocessing techniques (per-feature and per-image standardization) are applied. or decision trees and support vector machines we also evaluated the effect of training on a) imbalanced versus under- and over-sampled data and b) image-based vs feature-based input for specifically designed features.
The results show that for decision trees and support vector machines classification on features outperforms classification on images. Both methods give most equalized per-class accuracies when the training data was undersampled and when preprocessed with per-image standardization prior to features extraction. Neural networks gave the best results when no preprocessing was applied.
The final decision tree, support vector machine, and neural network obtained accuracies on the test set for (open,closed ) samples of (62%, 72%), (66%, 70%), and (61%, 78%) respectively, when considering all samples where at least one expert assigned a label. Restricting the test set to samples with at least three agreeing expert labels raised these to (78%, 84%), (74%, 92%), and (82%, 88%). It can be observed that many samples misclassified by the algorithms were also difficult to classify for the experts.