In order to go beyond the black-box deep neural network, this paper introduces a novel learning framework: Embedded Prototype Subspace Classification (EPSC), which is based on subspaces (or manifolds) for image classification (especially handwritten text). The proposed EPSC framework is intended to be both easy to comprehend and visualise, with mathematically well-defined components. This is … Continue reading Embedded Prototype Subspace Classification: A subspace learning framework
Blog
Consensus Ranking for Increasing Mean Average Precision in Keyword Spotting
Word spotting use a query word image to find any instances of that word among document images. The obtained list of words is ranked according to similarity to the query word. Ideally, any false positives should only occur in the end of that list. However, in reality they often occur higher up, which decreases the … Continue reading Consensus Ranking for Increasing Mean Average Precision in Keyword Spotting
The Astrid Lindgren Code
Read more about the project in Swedish.
The first study of the original manuscript by Astrid Lindgren
Starting next year I will work part time in team studying the original manuscript of the world renown author Astrid Lindgren. please see the press release of the project ”Astrid Lindgren-koden”. And also have a look at the project web page in Swedish at the Swedish Institute for Children's Books (SBI Svenska barnboksinstitutet).
Invited Talk
For the record: I had a talk at Internationella GIS-dagen 14 November, 2018. Anders Hast, Institutionen för informationsteknologi: "Stereovisualisering av historiska flygfoton i GeoMemories projektet"
Anders Hast 