V
Vinaychandran Pondenkandath
Researcher at University of Fribourg
Publications - 31
Citations - 420
Vinaychandran Pondenkandath is an academic researcher from University of Fribourg. The author has contributed to research in topics: Deep learning & Artificial neural network. The author has an hindex of 11, co-authored 31 publications receiving 288 citations. Previous affiliations of Vinaychandran Pondenkandath include Kaiserslautern University of Technology.
Papers
More filters
Proceedings ArticleDOI
Transforming sensor data to the image domain for deep learning — An application to footstep detection
TL;DR: In this paper, the authors leverage the discriminative power of pre-trained deep convolutional neural networks on 2D sensor data by transforming the sensor modality to the visual domain.
Journal ArticleDOI
Combining graph edit distance and triplet networks for offline signature verification
Paul Maergner,Vinaychandran Pondenkandath,Michele Alberti,Marcus Liwicki,Kaspar Riesen,Rolf Ingold,Andreas Fischer +6 more
TL;DR: Offline signature verification is a challenging pattern recognition task where a writer model is inferred using only a small number of genuine signatures using a combination of complementary writer mode and reader mode.
Proceedings ArticleDOI
A Comprehensive Study of ImageNet Pre-Training for Historical Document Image Analysis
Linda Studer,Michele Alberti,Vinaychandran Pondenkandath,Pinar Goktepe,Thomas Kolonko,Andreas Fischer,Marcus Liwicki,Rolf Ingold +7 more
TL;DR: In this article, the authors present a comprehensive empirical survey on the effect of ImageNet pre-training for diverse historical document analysis tasks, including character recognition, style classification, manuscript dating, semantic segmentation, and content-based retrieval.
Posted Content
A Comprehensive Study of ImageNet Pre-Training for Historical Document Image Analysis
Linda Studer,Michele Alberti,Vinaychandran Pondenkandath,Pinar Goktepe,Thomas Kolonko,Andreas Fischer,Marcus Liwicki,Rolf Ingold +7 more
TL;DR: A comprehensive empirical survey on the effect of ImageNet pre-training for diverse historical document analysis tasks, including character recognition, style classification, manuscript dating, semantic segmentation, and content-based retrieval finds a clear trend across different network architectures that ImageNetPre-training has a positive effect on classification as well as content- based retrieval.
Proceedings ArticleDOI
DeepDIVA: A Highly-Functional Python Framework for Reproducible Experiments
TL;DR: DeepDIVA is introduced: an infrastructure designed to enable quick and intuitive setup of reproducible experiments with a large range of useful analysis functionality and case studies in the area of handwritten document analysis where researchers benefit from the integrated functionality.