SciTePress - Affiliation Profile

Jean Monnet University, France

Context (please use complete words only)

Field

Sort by

11 Papers

Targeted Test Time Adaptation of Memory Networks for Video Object Segmentation

Topics: Segmentation and Grouping; Object Detection and Localization

Authors: Isidore Dubuisson ¹ , Damien Muselet ¹ , Christophe Ducottet ¹ and Jochen Lang ²

Affiliations: ¹ Université Jean Monnet Saint-Etienne, CNRS, Institut d Optique Graduate School, Laboratoire Hubert Curien UMR 5516, F-42023, Saint-Etienne, France , ² School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, Canada

Digital Object Identifier: 10.5220/0013108500003912

Proceedings of VISAPP 2025, ISBN: 978-989-758-728-3

Quick Abstract

Semi Automatic Video Object Segmentation (SVOS) aims to segment few objects in a video based on the annotation of these particular objects in the first frame only. State-of-the-art methods rely on offline training on a large dataset that may lack specific samples and details directly applicable to the current test video. Common solutions are to use test-time adaptation to finetune the offline model with the single annotated frame or by relying on complex semi-supervised strategies. In this paper, we introduce targeted test-time adaptation of memory-based SVOS providing the benefits of finetuning with much smaller learning effort. Our method targets specific parts of the model to ensure improved results while maintaining robustness of the offline training. We find that targeting the bottleneck features and the masks that are saved in memory provide substantial benefits. The evaluation of our method shows a significant improvement for video segmentation on DAVIS16 and DAVIS17 datasets.

Printed Packaging Authentication: Similarity Metric Learning for Rotogravure Manufacture Process Identification

Topics: Features Extraction; Multimedia Forensics

Authors: Tetiana Yemelianenko ¹ , Alain Trémeau ² and Iuliia Tkachenko ¹

Affiliations: ¹ Univ. Lyon, Univ Lyon 2, CNRS, INSA Lyon, UCBL, LIRIS, UMR 5205, F-69676 Bron, France , ² Univ. Lyon, UJM-Saint-Etienne, Laboratoire Hubert Curien UMR CNRS 5516, F-42023 St-Etienne, France

Digital Object Identifier: 10.5220/0011728700003417

Proceedings of VISAPP 2023/VISIGRAPP, ISBN: 978-989-758-634-7

Quick Abstract

The number of medicine counterfeits increases each year due to the accessibility of printing devices and the weak protection of medicine blister foils. The medicine blisters are often produced using the rotogravure printing process. In this paper, we address the problem of rotogravure press identification and printed support identification using similarity metric learning. Both identification problems are difficult as the impact of printing press or of printing support are minimal, moreover the classical techniques (for example, the use of Pearson correlation) cannot identify the rotogravure press or the printing support used for the packaging production. We show that the similarity metric learning can easily identify the press used and the printing support used. Additionally, we explore the possibility to use the proposed approach for packaging authentication.

Mask-guided Image Classification with Siamese Networks

Topics: Features Extraction; Categorization and Scene Understanding; Video Surveillance and Event Detection; Deep Learning for Visual Understanding

Authors: Hiba Alqasir , Damien Muselet and Christophe Ducottet

Affiliation: Université Lyon, UJM-Saint-Etienne, CNRS, Institut Optique Graduate School, Laboratoire Hubert Curien UMR 5516, F-42023, Saint-Etienne, France

Digital Object Identifier: 10.5220/0009180005360543

Proceedings of VISAPP 2020/VISIGRAPP, ISBN: 978-989-758-402-2

Quick Abstract

This paper deals with a CNN-based image classification task where the class of each image depends on a small detail in the image. Our original idea consists in providing a binary mask to the network so that it knows where is located the important information. This mask as well as the color image are provided as inputs to a siamese network. A contrastive loss function controls the projection of the network outputs in an embedding space enforcing the extraction of image features at the location proposed by the mask. This solution is tested on a real application whose aim is to secure the boarding on ski chairlifts by checking if the safety bar of the carrier is open or closed. Each chairlift has its own safety bar masks (open and close) and we propose to exploit this additional data to help the image classification between close or open safety bar. We show that the use of a siamese network allows to learn a single model that performs very well on 20 different skilifts.

Authentication of Medicine Blister Foils: Characterization of the Rotogravure Printing Process

Topics: Media Watermarking and Security; Multimedia Forensics

Authors: Iuliia Tkachenko , Alain Trémeau and Thierry Fournel

Affiliation: Laboratoire Hubert Curien, UMR CNRS 5516, Université de Lyon, UJM-Saint-Etienne, 18 rue Professeur B. Lauras, 42000 Saint-Etienne and France

Digital Object Identifier: 10.5220/0007565805770583

Proceedings of VISAPP 2019/VISIGRAPP, ISBN: 978-989-758-354-4

Quick Abstract

Nowadays the number of medicine packaging counterfeits increases very quickly. The rotogravure printing technique is worldwide used for medicine blister foils production. However, the existing anti-counterfeiting solutions do not take into account this printing process. Additionally, it is not easy to apply conventional solutions while using blister foils instead of uncoated/coated paper. In this paper, we study some features of the rotogravure printing and identify the future paths to fight the increasing number of counterfeited medicine products. We present the result of a preliminary study of such a process, extended to foils, and discuss some promising solutions for blister foils authentication.

Related Ontology Subjects/Areas/Topics (4)

Applications and Services		Media Watermarking and Security		Multimedia Forensics
Computer Vision, Visualization and Computer Graphics

A Hybrid Pedestrian Detection System based on Visible Images and LIDAR Data

Topics: Machine Learning Technologies for Vision; Features Extraction; Object Detection and Localization

Authors: Mohamed El Ansari ¹ , Redouan Lahmyed ¹ and Alain Tremeau ²

Affiliations: ¹ Faculty of Science and University of Ibn Zohr, Morocco , ² University Jean Monnet, France

Digital Object Identifier: 10.5220/0006620803250334

Proceedings of VISAPP 2018/VISIGRAPP, ISBN: 978-989-758-290-5

Quick Abstract

This paper presents a hybrid pedestrian detection system on the basis of 3D LIDAR data and visible images of the same scene. The proposed method consists of two main stages. In the first stage, the 3D LIDAR data are classified to obtain a set of clusters, which will be mapped into the visible image to get regions of interests (ROIs). The second stage classifies the ROIs (pedestrian/non pedestrian) using SVM as classifier and color based histogram of oriented gradients (HOG) together with the local self-similarity (LSS) as features. The proposed method has been tested on LIPD dataset and the results demonstrate its effectiveness.

Related Ontology Subjects/Areas/Topics (3)

Computer Vision, Visualization and Computer Graphics

Features Extraction

Image and Video Analysis

3D Reconstruction of Indoor Scenes using a Single RGB-D Image

Topic: Image-Based Modeling and 3D Reconstruction

Authors: Panagiotis-Alexandros Bokaris ¹ , Damien Muselet ² and Alain Trémeau ²

Affiliations: ¹ University of Paris-Saclay and Univ. Paris-Sud, France , ² Université Jean Monnet, France

Digital Object Identifier: 10.5220/0006107803940401

Proceedings of VISAPP 2017/VISIGRAPP, ISBN: 978-989-758-227-1

Quick Abstract

The three-dimensional reconstruction of a scene is essential for the interpretation of an environment. In this paper, a novel and robust method for the 3D reconstruction of an indoor scene using a single RGB-D image is proposed. First, the layout of the scene is identified and then, a new approach for isolating the objects in the scene is presented. Its fundamental idea is the segmentation of the whole image in planar surfaces and the merging of the ones that belong to the same object. Finally, a cuboid is fitted to each segmented object by a new RANSAC-based technique. The method is applied to various scenes and is able to provide a meaningful interpretation of these scenes even in cases with strong clutter and occlusion. In addition, a new ground truth dataset, on which the proposed method is further tested, was created. The results imply that the present work outperforms recent state-of-the-art approaches not only in accuracy but also in robustness and time complexity.

Related Ontology Subjects/Areas/Topics (6)

Applications		Geometry and Modeling		Pattern Recognition
Computer Vision, Visualization and Computer Graphics		Image-Based Modeling		Software Engineering

Color-based and Rotation Invariant Self-similarities

Topics: Color and Texture Analyses; Features Extraction

Authors: Xiaohu Song , Damien Muselet and Alain Tremeau

Affiliation: UJM-Saint-Etienne, CNRS and LaHC UMR 5516, France

Digital Object Identifier: 10.5220/0006107503440351

Proceedings of VISAPP 2017/VISIGRAPP, ISBN: 978-989-758-225-7

Quick Abstract

One big challenge in computer vision is to extract robust and discriminative local descriptors. For many applications such as object tracking, image classification or image matching, there exist appearance-based descriptors such as SIFT or learned CNN-features that provide very good results. But for some other applications such as multimodal image comparison (infra-red versus color, color versus depth, ...) these descriptors failed and people resort to using the spatial distribution of self-similarities. The idea is to inform about the similarities between local regions in an image rather than the appearances of these regions at the pixel level. Nevertheless, the classical self-similarities are not invariant to rotation in the image space, so that two rotated versions of a local patch are not considered as similar and we think that many discriminative information is lost because of this weakness. In this paper, we present a method to extract rotation-invariant self similarities. In this aim, we propose to compare color descriptors of the local regions rather than the local regions themselves. Furthermore, since this comparison informs us about the relative orientations of the two local regions, we incorporate this information in the final image descriptor in order to increase the discriminative power of the system. We show that the self similarities extracted by this way are very discriminative.

Related Ontology Subjects/Areas/Topics (4)

Color and Texture Analyses		Features Extraction		Image and Video Analysis
Computer Vision, Visualization and Computer Graphics

Towards an Electronic Orientation Table: Using Features Extracted From the Image to Register Digital Elevation Model

Topics: Entertainment Imaging Applications; Mobile Imaging

Authors: Leo Nicolle ¹ , Julien Bonneton ¹ , Hubert Konik ² , Damien Muselet ² and Laure Tougne ¹

Affiliations: ¹ LIRIS, France , ² Univ. Lyon and UJM-Saint-Etienne, France

Digital Object Identifier: 10.5220/0006115700280038

Proceedings of VISAPP 2017/VISIGRAPP, ISBN: 978-989-758-227-1

Quick Abstract

The generation of a virtual representation of the bones and fragments is an artificial step required in order to obtain helpful models to work with in a simulation. Nowadays, the Marching Cubes algorithm is a de facto standard for the generation of geometric models from medical images. However, bone fragments models generated by Marching Cubes are huge and contain many unconnected geometric elements inside the bone due to the trabecular tissue. The development of new methods to generate geometrically simple 3D models from CT image stacks that preserve the original information extracted from them would be of great interest. In order to achieve that, a preliminary study for the development of a new method to generate triangle meshes from segmented medical images is presented. The method does not modify the points extracted from CT images, and avoid generating triangles inside the bone. The aim of this initial study is to analyse if a spatial decomposition may help in the process of generating a triangle mesh by using a divide-and-conquer approach. The method is under development and therefore this paper only presents some initial results and exposes the detected issues to be improved.

Related Ontology Subjects/Areas/Topics (4)

Applications and Services		Entertainment Imaging Applications		Mobile Imaging
Computer Vision, Visualization and Computer Graphics

RGB-D-λ: 3D Multispectral Acquisition with Stereo RGB Cameras

Authors: Alain Trémeau ¹ , Simone Bianco ² and Raimondo Schettini ²

Affiliations: ¹ University Jean Monnet, France , ² University of Milano-Bicocca, Italy

Digital Object Identifier: 10.5220/0005845406890696

Proceedings of RGB-SpectralImaging 2016/VISIGRAPP, ISBN: 978-989-758-175-5

Quick Abstract

In this paper we report some key questions related to the acquisition of accurate color images adressed by the Colour and Space in Cultural Heritage (COSCH) project. We summarize the main criteria defined by COSCH Working Group 1 and used by the authors to help Digital Cultural Heritage (DCH) users to have a deepen knowledge and understanding of the constraints, preconditions and practical aspects related to the use of a multi-spectral acquisition system. We also report how color data can be estimated from spectral data and discuss several issues related to the measurement of reflective surfaces by 2D imaging systems.

BRINGING ORDER IN THE BAG OF WORDS

Topics: Object and Face Recognition; Categorization and Scene Understanding

Authors: Shihong Zhang , Rahat Khan , Damien Muselet and Alain Trémeau

Affiliation: Université de Lyon, CNRS and Université de Saint-Étienne, France

Digital Object Identifier: 10.5220/0003859307230726

Proceedings of VISAPP 2012/VISIGRAPP, ISBN: 978-989-8565-03-7

Quick Abstract

This paper presents a method to infuse spatial information in the bag of words (BOW) framework for object categorization. The main idea is to account the local spatial distribution of the visual words. Rather than finding rigid local patterns, we consider the visual words in close spatial proximity as a pouch of words and we represent the image as a bag of word-pouches. For this purpose, sub-windows are extracted from the images and characterized by local bags of words. Then a clustering step is applied in the local bag of words space to construct the word-pouches. We show that this representation is complementary to the classical BOW. Thus a concatenation of these two representations is used as the final descriptor. Experiments are conducted on two very well known image datasets.

Context (please use complete words only)

Field

Sort by

Topic(s):

Title:
ISBN:
Year:
Acronym:
Subject:

Title:
Author:
Affiliation:
Subject:

Name:
Affiliation:
Country:
Conference:
Subject:

Name:
Country:
Subject:

Affiliation

Filter listed results, by