Search results for "computer vision"

Zero-shot Semantic Segmentation using Relation Network

2021

Zero-shot learning (ZSL) is widely studied in recent years to solve the problem of lacking annotations. Currently, most studies on ZSL are for image classification and object detection. But, zero-shot semantic segmentation, pixel level classification, is still at its early stage. Therefore, this work proposes to extend a zero-shot image classification model, Relation Network (RN), to semantic segmentation tasks. We modified the structure of RN based on other state-of-the-arts semantic segmentation models (i.e. U-Net and DeepLab) and utilizes word embeddings from Caltech-UCSD Birds 200-2011 attributes and natural language processing models (i.e. word2vec and fastText). Because meta-learning …

Time Unification on Local Binary Patterns Three Orthogonal Planes for Facial Expression Recognition

2019

International audience; Machine learning has known a tremendous growth within the last years, and lately, thanks to that, some computer vision algorithms started to access what is difficult or even impossible to perceive by the human eye. While deep learning based computer vision algorithms have made themselves more and more present in the recent years, more classical feature extraction methods, such as the ones based on Local Binary Patterns (LBP), still present a non negligible interest, especially when dealing with small datasets. Furthermore, this operator has proven to be quite useful for facial emotions and human gestures recognition in general. Micro-Expression (ME) classification is…

WATCHING PEOPLE: ALGORITHMS TO STUDY HUMAN MOTION AND ACTIVITIES

2020

Nowadays human motion analysis is one of the most active research topics in Computer Vision and it is receiving an increasing attention from both the industrial and scientific communities. The growing interest in human motion analysis is motivated by the increasing number of promising applications, ranging from surveillance, human–computer interaction, virtual reality to healthcare, sports, computer games and video conferencing, just to name a few. The aim of this thesis is to give an overview of the various tasks involved in visual motion analysis of the human body and to present the issues and possible solutions related to it. In this thesis, visual motion analysis is categorized into thr…

Restoration and Enhancement of Historical Stereo Photos

2021

Restoration of digital visual media acquired from repositories of historical photographic and cinematographic material is of key importance for the preservation, study and transmission of the legacy of past cultures to the coming generations. In this paper, a fully automatic approach to the digital restoration of historical stereo photographs is proposed, referred to as Stacked Median Restoration plus (SMR+). The approach exploits the content redundancy in stereo pairs for detecting and fixing scratches, dust, dirt spots and many other defects in the original images, as well as improving contrast and illumination. This is done by estimating the optical flow between the images, and using it …

Space-Frequency Quantization for Image Compression With Directionlets

2007

The standard separable 2-D wavelet transform (WT) has recently achieved a great success in image processing because it provides a sparse representation of smooth images. However, it fails to efficiently capture 1-D discontinuities, like edges or contours. These features, being elongated and characterized by geometrical regularity along different directions, intersect and generate many large magnitude wavelet coefficients. Since contours are very important elements in the visual perception of images, to provide a good visual quality of compressed images, it is fundamental to preserve good reconstruction of these directional features. In our previous work, we proposed a construction of critic…

A Cognitive Architecture for Robotic Hand Posture Learning

2005

This paper deals with the design and implementation of a visual control of a robotic system composed of a dexterous hand and video camera. The aim of the proposed system is to reproduce the movements of a human hand in order to learn complex manipulation tasks or to interact with the user. A novel algorithm for robust and fast fingertips localization and tracking is presented. A suitable kinematic hand model is adopted to achieve a fast and acceptable solution to an inverse kinematics problem. The system is part of a cognitive architecture for posture learning that integrates the perceptions by a high-level representation of the scene and of the observed actions. The anthropomorphic robotic…

Effects of menu structure and touch screen scrolling style on the variability of glance durations during in-vehicle visual search tasks.

2011

The effects of alternative navigation device display features on drivers' visual sampling efficiency while searching forpoints of interest were studied in two driving simulation experiments with 40 participants. Given that the number of display items was sufficient, display features that facilitate resumption of visual search following interruptions were expected to lead to more consistent in-vehicle glance durations. As predicted, compared with a grid-style menu, searching information in a list-style menu while driving led to smaller variance in durations of in-vehicle glances, in particular with nine item displays. Kinetic touch screen scrolling induced a greater number of very short in-v…

Semi-blind Source Extraction Methods: Application to the measurement of non-contact physiological signs

2018

Non-contact physiological measurements are highlydesirable in many biomedical fields such asdiagnosis of infants, geriartic patients, patients withextreme physical trauma, and fitness and well-being.Remote photoplethysmography is increasingly beingused for non-contact measurement of heart rate fromvideos which is one of the most common biomedicalproperty required for most medical diagnosis. Oneof the common techniques for performing remotephotoplethysmography involves using Blind SourceSeparation (BSS) methods to extract the cardiacsignal from video data.In this context, the objective of this thesis is todevelop different methods in the field of extractionand separation of sources by improv…

Editorial:Governance AI ethics

2022

Large-scale nonlinear dimensionality reduction for network intrusion detection

2017

International audience; Network intrusion detection (NID) is a complex classification problem. In this paper, we combine classification with recent and scalable nonlinear dimensionality reduction (NLDR) methods. Classification and DR are not necessarily adversarial, provided adequate cluster magnification occurring in NLDR methods like $t$-SNE: DR mitigates the curse of dimensionality, while cluster magnification can maintain class separability. We demonstrate experimentally the effectiveness of the approach by analyzing and comparing results on the big KDD99 dataset, using both NLDR quality assessment and classification rate for SVMs and random forests. Since data involves features of mixe…