Global ETD Search

11	Fully Convolutional Neural Networks for Pixel Classification in Historical Document Images Stewart, Seth Andrew 01 October 2018 (has links) We use a Fully Convolutional Neural Network (FCNN) to classify pixels in historical document images, enabling the extraction of high-quality, pixel-precise and semantically consistent layers of masked content. We also analyze a dataset of hand-labeled historical form images of unprecedented detail and complexity. The semantic categories we consider in this new dataset include handwriting, machine-printed text, dotted and solid lines, and stamps. Segmentation of document images into distinct layers allows handwriting, machine print, and other content to be processed and recognized discriminatively, and therefore more intelligently than might be possible with content-unaware methods. We show that an efficient FCNN with relatively few parameters can accurately segment documents having similar textural content when trained on a single representative pixel-labeled document image, even when layouts differ significantly. In contrast to the overwhelming majority of existing semantic segmentation approaches, we allow multiple labels to be predicted per pixel location, which allows for direct prediction and reconstruction of overlapped content. We perform an analysis of prevalent pixel-wise performance measures, and show that several popular performance measures can be manipulated adversarially, yielding arbitrarily high measures based on the type of bias used to generate the ground-truth. We propose a solution to the gaming problem by comparing absolute performance to an estimated human level of performance. We also present results on a recent international competition requiring the automatic annotation of billions of pixels, in which our method took first place. Convolutional Neural Networks Document Image Analysis Fully Convolutional Neural Networks Layout Analysis Page Segmentation Pixel-Labeling Region Classification Semantic Segmentation Data Augmentation Historical Document Processing Optical Character Recognition Handwriting Recognition Physical Sciences and Mathematics
12	Visualization of live search / Visualisering av realtidssök Nilsson, Olof January 2013 (has links) The classical search engine result page is used for many interactions with search results. While these are effective at communicating relevance, they do not present the context well. By giving the user an overview in the form of a spatialized display, in a domain that has a physical analog that the user is familiar with, context should become pre-attentive and obvious to the user. A prototype has been built that takes public medical information articles and assigns these to parts of the human body. The articles are indexed and made searchable. A visualization presents the coverage of a query on the human body and allows the user to interact with it to explore the results. Through usage cases the function and utility of the approach is shown. search technology search engine information retrieval live search query completion facet recall precision machine learning document classification linear classifier document categorization document clustering multi-label classification labelling hamming loss f-score visualization information visualization distance-similarity metaphor spatialized display visual information-seeking mantra user interface spatialization document processing Interaction Technologies Interaktionsteknik Computer Sciences Datavetenskap (datalogi) Information Systems Human Computer Interaction

Search results

Fully Convolutional Neural Networks for Pixel Classification in Historical Document Images

Visualization of live search / Visualisering av realtidssök