French vital records data gathering and analysis through image processing and machine learning algorithms [PDF]
Journal of Data Mining and Digital Humanities, 2021 Vital records are rich of meaningful historical data concerning city as well as countryside inhabitants that can be used, among others, to study former populations and then reveal the social, economic and demographic characteristics of those populations.
Cyprien Plateau-Holleville +3 more
doaj +1 more source
Cursive Arabic Handwriting Recognition System Without Explicit Segmentation Based on Hidden Markov Models [PDF]
Journal of Data Mining and Digital Humanities, 2018 In this paper we present a system for offline recognition cursive Arabic handwritten text which is analytical without explicit segmentation based on Hidden Markov Models (HMMs).
Mouhcine Rabi +2 more
doaj +1 more source
Language Models for Image Captioning: The Quirks and What Works [PDF]
, 2015 Two recent approaches have achieved state-of-the-art results in image captioning. The first uses a pipelined process where a set of candidate words is generated by a convolutional neural network (CNN) trained on images, and then a maximum entropy (ME ...
Cheng, Hao +7 more
core +1 more source
Towards dense object tracking in a 2D honeybee hive
, 2017 From human crowds to cells in tissue, the detection and efficient tracking of multiple objects in dense configurations is an important and unsolved problem.
Bozek, Katarzyna +3 more
core +2 more sources
Multimodal news article analysis [PDF]
, 2017 The intersection of Computer Vision and Natural Language Processing has been a hot topic of research in recent years, with results that were unthinkable only a few years ago.
Ramisa Ayats, Arnau
core +2 more sources
Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network [PDF]
, 2016 Recently, several models based on deep neural networks have achieved great success in terms of both reconstruction accuracy and computational performance for single image super-resolution. In these methods, the low resolution (LR) input image is upscaled
Aitken, AP +7 more
core +1 more source
U-Net: Convolutional Networks for Biomedical Image Segmentation
, 2015 There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the available ...
Brox, Thomas +2 more
core +1 more source
DPC-Net: Deep Pose Correction for Visual Localization
, 2018 We present a novel method to fuse the power of deep networks with the computational efficiency of geometric and probabilistic localization algorithms. In contrast to other methods that completely replace a classical visual estimator with a deep network ...
Kelly, Jonathan, Peretroukhin, Valentin
core +1 more source
Overview: Computer vision and machine learning for microstructural characterization and analysis
, 2020 The characterization and analysis of microstructure is the foundation of microstructural science, connecting the materials structure to its composition, process history, and properties.
Cohn, Ryan +6 more
core +1 more source
Learning to count with deep object features
, 2015 Learning to count is a learning strategy that has been recently proposed in the literature for dealing with problems where estimating the number of object instances in a scene is the final objective.
Pujol, Oriol +2 more
core +1 more source