Various lighting changes are one of the factors that degrade the recognition performance of
face images, in particular, when a shadow is formed on a face image due to lighting or …

We now explain the loss functions that we apply to supervise the three steps of our method.
Recall that we use a self-supervised approach to train our model involving synthetic shadow …

The generally unsupervised nature of autoencoder models implies that the main training
metric is formulated as the error between input images and their corresponding …

We propose a method for detecting a facial symmetry axis from a frontal face image. The
proposed method adopts a voting procedure like Hough transform that transforms a set of …

Portrait photos are among the most important photographic depictions of humans and their
loved ones. Even though the quality of cameras and thus the photographs have improved …

초록 다양한 조명 변화는 얼굴 이미지의 인식 성능을 떨어뜨리는 요인 중 하나이며, 특히 조명
또는 주변 환경에 의해 얼굴 이미지 위에 그림자가 생기면 인식 성능이 크게 저하되는 것이 …

Having a compact, casual pocket camera always within reach is a delight. It opens the
opportunity to capture spontaneous moments and casual events. While users appreciate the …

Recovering 3D geometries of scenes from 2D images is one of the most fundamental and
challenging problems in computer vision. On one hand, traditional geometry-based …

L'objectif de cette thèse est de mettre au point un moyen de détecter les adventices dans un
champ à l'aide d'images multispectrales, afin de pouvoir déterminer quelles sont les …