L
Laurent Heutte
Researcher at University of Rouen
Publications - 136
Citations - 5016
Laurent Heutte is an academic researcher from University of Rouen. The author has contributed to research in topics: Handwriting recognition & Feature extraction. The author has an hindex of 28, co-authored 133 publications receiving 3944 citations. Previous affiliations of Laurent Heutte include Matra & Intelligence and National Security Alliance.
Papers
More filters
Journal ArticleDOI
A Dataset for Breast Cancer Histopathological Image Classification
TL;DR: A dataset of 7909 breast cancer histopathology images acquired on 82 patients, which is now publicly available from http://web.ufpr.br/vri/breast-cancer-database, aimed at automated classification of these images in two classes, which would be a valuable computer-aided diagnosis tool for the clinician.
Proceedings ArticleDOI
Breast cancer histopathological image classification using Convolutional Neural Networks
TL;DR: This method aims to allow using the high-resolution histopathological images from BreaKHis as input to existing CNN, avoiding adaptations of the model that can lead to a more complex and computationally costly architecture.
Journal ArticleDOI
Multiple instance learning for histopathological breast cancer image classification
P. J. Sudharshan,Caroline Petitjean,Fabio Alexandre Spanhol,Luiz S. Oliveira,Laurent Heutte,Paul Honeine +5 more
TL;DR: The comparison between MIL and single instance classification reveals the relevance of the MIL paradigm for the task at hand, and allows to obtain comparable or better results than conventional (single instance) classification without the need to label all the images.
Proceedings ArticleDOI
Deep features for breast cancer histopathological image classification
TL;DR: The experimental evaluation of DeCaf features for BC recognition shows that these features can be a viable alternative to fast development of high-accuracy BC recognition systems, generally achieving better results than traditional hand-crafted textural descriptors and outperforming task-specific CNNs in some cases.
Journal ArticleDOI
A writer identification and verification system
TL;DR: It is shown that both the writer identification and the writer verification tasks can be carried out using local features such as graphemes extracted from the segmentation of cursive handwriting, making the approach general and very promising for large scale applications in the domain of handwritten document querying and writer verification.