SB
Articles

Technical writing.

Lessons from architecture, integration or UI pattern decisions. Drawn from professional and personal projects.

Publications

Computer vision · 2018-2020

Four papers from my research master's at the University of La Rochelle (MIA Laboratory). Detailed summaries here — PDFs are not hosted (IEEE copyright).

IEEE IPAS 2020

Colorizing genuine archival photos: palette + scribbles

CNN colorization networks are trained on colour photos converted to grayscale — ill-suited to genuine archival B&W (silver halide). I improve the output with two hints: an automated global palette + manual scribbles where it matters (flags, monuments).

Colorization Deep learning Archival CNN Interactive
Read
IEEE MCNA 2020

Colorizing a B&W movie with a salient-colour palette

A palette of 'salient' scene colours (distinct from the 'memorable' ones the network already infers well) is injected into the CNN as an additional input. One palette covers hundreds of frames — well-suited to movie colorization without per-frame scribbling.

Colorization Deep learning Colour palette CNN Movie
Read
EUVIP 2019

Detecting handwriting anomalies via a convolutional autoencoder

A convolutional autoencoder that detects — without annotation — that a portion of text was written by another hand. Tile splitting + partial Radon transform. Discrimination emerges during training via batch-to-batch shuffling.

Deep learning Handwriting Outlier detection Autoencoder Radon
Read
IEEE EUVIP 2018

Visible + NIR information for CNN face recognition

An original VNIR dataset (52 identities, 3 poses) captured by removing the ICF of a consumer camera. Two CNNs compared. Finding: 3-channel full-spectrum beats 4-channel RGB+I, and the blue channel benefits the most from NIR.

CNN Face recognition NIR Multispectral Dataset
Read