Avancerad sökning

Visar resultat 1 - 5 av 41 avhandlingar som matchar ovanstående sökkriterier.

1. 1. Machine-Printed and Handwritten Ethiopic Script Recognition

   Författare :Yaregal Assabie; Chalmers tekniska högskola; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; NATURVETENSKAP; NATURAL SCIENCES; HMM; Handwriting Recognition; OCR; Direction Field Tensor; Ethiopic Character Recognition; Amharic Word Recognition; Structure Tensor;

   Sammanfattning : A written language is represented by using machine-printed or handwritten symbols called characters. For automatic recognition of written languages, handwritten script can be captured offline (by a scanner) and online (by electronic digital devices), whereas machine-printed text is captured offline. LÄS MER

3. 2. Reading Development and Reading Disability : Analyses of eye-movements and word recognition

   Författare :Christer Jacobson; Institutionen för psykologi; []
   Nyckelord :SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; Applied and experimental psychology; eye-movements; gender differences; growth-curves; reading disability; Word recognition; reading development; Tillämpad och experimentell psykologi;

   Sammanfattning : The primary ambition of this doctoral thesis is to provide an empirical basis for a better understanding of reading disability among school children. The current consensus in the research community is that most disabled readers fail in the acquisition of fast, accurate and automatic word recognition. LÄS MER

4. 3. Word Learning in the Developing Brain : ERP Dynamics of Learning Word-Object Associations

   Författare :Kristina Borgström; Institutionen för psykologi; []
   Nyckelord :SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; Word Learning; Language development; EEG; ERP; N400;

   Sammanfattning : This dissertation investigated electrophysiological measures of individual differences in toddlers’ ability to learn novel object labels and process familiar object words and their referents. The studies measured both visual and auditory event-related potentials (ERPs) in response to pictures of objects and words in a longitudinal sample of 20- to 24-month-olds, an age of dynamic vocabulary development. LÄS MER

5. 4. Word Vector Representations using Shallow Neural Networks

   Författare :Oluwatosin Adewumi; Marcus Liwicki; Marco Kuhlmann; Luleå tekniska universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Word vectors; NLP; Neural networks; Embeddings; Maskininlärning; Machine Learning;

   Sammanfattning : This work highlights some important factors for consideration when developing word vector representations and data-driven conversational systems. The neural network methods for creating word embeddings have gained more prominence than their older, count-based counterparts. LÄS MER

7. 5. Document Image Processing for Handwritten Text Recognition : Deep Learning-based Transliteration of Astrid Lindgren’s Stenographic Manuscripts

   Författare :Raphaela Heil; Anders Hast; Ekta Vats; Fredrik Wahlberg; Andreas Fischer; Uppsala universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; document image processing; handwritten text recognition; stenography; strikethrough; Computerized Image Processing; Datoriserad bildbehandling;

   Sammanfattning : Document image processing and handwritten text recognition have been applied to a variety of materials, scripts, and languages, both modern and historic. They are crucial building blocks in the on-going digitisation efforts of archives, where they aid in preserving archival materials and foster knowledge sharing. LÄS MER