On February 25:th I visited the research group led by Andrea Marchetti at IIT, CNR in Pisa and presented ongoing research in Handwritten Text Recognition, Age Estimation and Face Recognition.
Paper Presentation
I presented the paper "Exploring Handwritten Document Collections: An EPSC-Based Approach for Feature Extraction and Similarity Analysis" at 21st Conference on Information and Research Science Connecting to Digital and Library Science - IRCDL 2025, February 20--21, 2025, Udine, Italy
Presentation at EB-CRIME
On the 29:th of October I presented my work on age estimation together with my colleagues in the EB-CRIME project. I use subspaces to improve performance and this is an ongoing research project.
Embedded Prototype Subspace Classification
This is an important part of my contribution to the field of AI. An earlier blog post, has been updated with new information about this project. Several improvements have been done, which show how to make ensembles and creating efficient feature vectors using the Fourier Transform. New Papers Age-Invariant Face Recognition using Face Feature Vectors … Continue reading Embedded Prototype Subspace Classification
Embedded Prototype Subspace Classification: A subspace learning framework
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
Anders Hast 