Search results for "Pattern recognition"
showing 10 items of 2301 documents
hidden markov random fields and cuckoo search method for medical image segmentation
2020
Segmentation of medical images is an essential part in the process of diagnostics. Physicians require an automatic, robust and valid results. Hidden Markov Random Fields (HMRF) provide powerful model. This latter models the segmentation problem as the minimization of an energy function. Cuckoo search (CS) algorithm is one of the recent nature-inspired meta-heuristic algorithms. It has shown its efficiency in many engineering optimization problems. In this paper, we use three cuckoo search algorithm to achieve medical image segmentation.
Unsupervised learning of category-specific symmetric 3D keypoints from point sets
2020
Lecture Notes in Computer Science, 12370
3D landmark detection for augmented reality based otologic procedures
2019
International audience; Ear consists of the smallest bones in the human body and does not contain significant amount of distinct landmark points that may be used to register a preoperative CT-scan with the surgical video in an augmented reality framework. Learning based algorithms may be used to help the surgeons to identify landmark points. This paper presents a convolutional neural network approach to landmark detection in preoperative ear CT images and then discusses an augmented reality system that can be used to visualize the cochlear axis on an otologic surgical video.
Event-Based Trajectory Prediction Using Spiking Neural Networks
2021
International audience; In recent years, event-based sensors have been combined with spiking neural networks (SNNs) to create a new generation of bio-inspired artificial vision systems. These systems can process spatio-temporal data in real time, and are highly energy efficient. In this study, we used a new hybrid event-based camera in conjunction with a multi-layer spiking neural network trained with a spike-timing-dependent plasticity learning rule. We showed that neurons learn from repeated and correlated spatio-temporal patterns in an unsupervised way and become selective to motion features, such as direction and speed. This motion selectivity can then be used to predict ball trajectory…
Enhancement and assessment of WKS variance parameter for intelligent 3D shape recognition and matching based on MPSO
2016
This paper presents an improved wave kernel signature (WKS) using the modified particle swarm optimization (MPSO)-based intelligent recognition and matching on 3D shapes. We select the first feature vector from WKS, which represents the 3D shape over the first energy scale. The choice of this vector is to reinforce robustness against non-rigid 3D shapes. Furthermore, an optimized WKS-based method for extracting key-points from objects is introduced. Due to its discriminative power, the associated optimized WKS values with each point remain extremely stable, which allows for efficient salient features extraction. To assert our method regarding its robustness against topological deformations,…
Repérage précis de caméras multispectrales et de scanners 3D pour le recalage de données multicapteurs appliqué à l'étude du patrimoine
2012
Session "Atelier V3DPAT"; National audience; Nos travaux portent sur le recalage de données multi-capteurs et spécifiquement sur la projection de textures 2D sur des modèles 3D d'objet du patrimoine en pierre. Nous nous intéressons particulièrement aux textures acquises par imagerie multispectrale mais notre technique est également adaptée à d'autres systèmes optiques d'acquisition tels que l'imagerie thermique. Les modèles 3D, eux, sont acquis par un système de projection de franges. La difficulté du recalage multicapteur vient principalement de la variation de la représentation de l'objet. Ainsi, les points saillants d'un jeu de données ne correspondent pas forcément à ceux d'une autre re…
Reconnaissance de la Forme 3D et Estimation de la Profondeur Implémentation sur FPGA Spartan 3A d'un SoC pour la Vision 3D (Shape From Focus) Problém…
2007
Le terme de « vision 3D » ou « de numérisation 3D », est apparu à la fin des années 1990, pour désigner des techniques d'acquisition de mesures tridimensionnelle sur des surfaces, techniques ayant la caractéristique de donner des nuages de points denses et importants dont l'ordre de grandeur est de quelques dizaines à plusieurs millions de points. Le nuage de points représente en fait l'information de l'image de profondeur et selon des différents traitements à l'image on peut aboutir à un ordre de précision de la reconstitution de l'objet ou scène en 3D. La vision 3D demeure une méthodologie de base pour réassurer le mécanisme de reconstitution des images tridimensionnelles. Outre les besoi…
Une approche performante de suivi visuel pour les caméras catadioptriques
2012
Session "Posters"; National audience; Dans cet article, nous proposons une méthode performante permettant d'appliquer des algorithmes de suivi visuel à des images catadioptriques. Cette méthode est basée sur une représentation sphérique de l'image qui permet de prendre en compte les distorsions et la résolution non-uniforme des images catadioptriques. Les résultats expérimentaux proposés démontrent que les méthodes probabilistes et déterministes peuvent être adaptées de manière à suivre un objet avec précision dans une séquence d'images catadioptriques
Optimisation et implémentation de méthodes bio-inspirées d'extraction de caractéristiques pour la reconnaissance d'objets visuels
2016
Industry has growing needs for so-called “intelligent systems”, capable of not only ac-quire data, but also to analyse it and to make decisions accordingly. Such systems areparticularly useful for video-surveillance, in which case alarms must be raised in case ofan intrusion. For cost saving and power consumption reasons, it is better to perform thatprocess as close to the sensor as possible. To address that issue, a promising approach isto use bio-inspired frameworks, which consist in applying computational biology modelsto industrial applications. The work carried out during that thesis consisted in select-ing bio-inspired feature extraction frameworks, and to optimize them with the aim t…
Deep learning for dehazing: Benchmark and analysis
2018
International audience; We compare a recent dehazing method based on deep learning , Dehazenet, with traditional state-of-the-art approach, on benchmark data with reference. Dehazenet estimates the depth map from a single color image, which is used to inverse the Koschmieder model of imaging in the presence of haze. In this sense, the solution is still attached to the Koschmieder model. We demonstrate that this method exhibits the same limitation than other inversions of this imaging model.