文献类型： 会议论文
第一作者： Mabrouka Hagui
作者： Mabrouka Hagui 1 ; Mohamed Ali Mahjoub 1 ;
作者机构： 1.SAGE Research Unit, ENISo School of Engineers of Sousse, Sousse University
关键词： Dynamic Conditional Random Fields;Gait Recognition;SURF Descriptor;Feature Extraction;Factorial CRF;Hierarchical CRF
会议名称： International Conference on Agents and Artificial Intelligence
主办单位：
页码： 432-437
摘要： Gait is a recent biometric technology which aims at identifying people at distance by the way they walk. It has the advantage of recognizing person without their cooperation and doesn't need high resolution of image. In this paper, we present a new discriminative method for gait recognition using dynamic conditional random fields (CRF). We use a dynamic CRF model to combine two classifiers a spatial classifier which assigns a label to a local features (SURF descriptors) and temporal classifier which uses a motion History Image (MHI). The proposed framework, firstly extracts the human silhouette. Secondly, it takes out spatial and temporal cues from each frame; the proposed system combines spatial and temporal features to improve the performance of human identification. In this paper, we compare two different dynamic CRFs models for analyzing human walk, the two models are Factorial CRFs and Hidden dynamic CRFs.
分类号： TP18-53
- 相关文献
[1]Approaches for Identifying Suicide Ideation in Social Media Texts: Comprehensive Review. Jayshri Suresh Sonawane,Dinesh Jain. 2024
[2]Research and Application of Pig Iris Recognition Technology. Shipu Xu,Guoqing Liu,Yong Liu,Yunsheng Wang. 2024
[3]Student’s Feedback by emotion and speech recognition through Deep Learning. Ati Jain,Hare Ram Sah. 2021
[4]Coupled Hidden Markov Model for video fall detection. Mabrouka Hagui,Mohamed Ali Mahjoub,Faycel Elayeb. 2015
[5]Study for Emotion Recognition of Different Age Groups Students during Online Class. Ati Jain,Hare Ram Sah,Abhay Kothari. 2021
作者其他论文 更多>>
-
A combined Approach Based on Fuzzy Classification and Contextual Region Growing To Image Segmentation
作者：Mahaman Sani Chaibou;Karim Kalti;Basel Solaiman;Mohamed Ali Mahjoub
关键词：Image Segmentation;Fuzzy Classification;Region-growing;Context Information;Contextual Region-growing
-
Comparative study and enhancement of Camera Tampering Detection algorithms
作者：Mabrouka Hagui;Ahmed Boukhris;Mohamed Ali Mahjoub
关键词：Camera Tampering;Detection;Occulusion;Defocus;Motion
-
Possibilistic Reasoning Effects on Hidden Markov Models Effectiveness
作者：Anis Elbahi;Mohamed Nazih Omri;Mohamed Ali Mahjoub
关键词：Hidden Markov Models;Possibilistic Theory;Fuzzy Logic;Human Activity Recognition
-
Coupled Hidden Markov Model for video fall detection
作者：Mabrouka Hagui;Mohamed Ali Mahjoub;Faycel Elayeb
关键词：Fall detection;Feature extraction;Shape deformation;Motion History of image;Coupled Hidden Markov Models
-
Performance Evaluation and Benchmarking of Six Texture-based Feature Sets for Segmenting Historical Documents
作者：Maroua Mehri;Mohamed Mhiri;Pierre Heroux;Petra Gomez-Kramer;Mohamed Ali Mahjoub;Remy Mullot
关键词：Historical digitized document images;Segmentation;Texture;Multiscale approach
