Différences
Ci-dessous, les différences entre deux révisions de la page.
| Les deux révisions précédentes Révision précédente Prochaine révision | Révision précédente Prochaine révision Les deux révisions suivantes | ||
|
opengazer [Le 29/11/2017, 14:28] 78.194.2.45 [Opengazer] |
opengazer [Le 04/12/2017, 09:19] fabux Merci de faire un brouillon dans son espace et de venir en parler sur la liste. |
||
|---|---|---|---|
| Ligne 1: | Ligne 1: | ||
| - | {{tag>Trusty Xenial accessibilité handicap BROUILLON}} | + | {{tag>Trusty Xenial accessibilité BROUILLON}} |
| ---- | ---- | ||
| {{ :applications:icone_de_l'application.png?80}} | {{ :applications:icone_de_l'application.png?80}} | ||
| Ligne 30: | Ligne 30: | ||
| | **« Test de reconnaissance faciale. »** | \\ | | **« Test de reconnaissance faciale. »** | \\ | ||
| {{ https://eyecomtec.com/img/EyeComTec.Com_LAZgroup_Paralys_tech-img26.jpg?500 |Test de reconnaissance faciale}} | {{ https://eyecomtec.com/img/EyeComTec.Com_LAZgroup_Paralys_tech-img26.jpg?500 |Test de reconnaissance faciale}} | ||
| - | |||
| - | A subproject of Opengazer involves the automatic detection of facial gestures to drive a switch-based program. This program has a short learning phase (under 30 seconds) for each gesture, after which the gesture is automatically detected. Many patients (e.g., patients with cerebral palsy) have involuntary head motions that can introduce false positives during detection. We therefore also train a background model to deal with involuntary motions. All the software is written in C++ and Python and will be available for download soon. An example video of our gesture switch algorithm can be downloaded [here]. On Windows the video can be viewed with the VLC player. On Linux it is best displayed using Mplayer Movie Player. Note that this video has sound. Three gestures have been trained to generate three possible switch events: a left smile, right smile, and upwards eyebrow movement all correspond to switch events. The background model, in this case, detects blinks, sudden changes in lighting, and large head motions. The first official release will be at the end of June 2012. | ||
| - | The first version of Opengazer has the following workflow: | ||
| - | |||
| - | Feature point selection: | ||
| - | During startup the user is expected to select feature points on the face using the mouse. These points are tracked in subsequent steps in the algorithm. The first two points correspond to the corners of the eyes, which are also used in subsequent steps to extract the eye images. The user has to keep his/her head very still during the whole procedure. At this point the user should preferably save all the selected feature points. | ||
| - | |||
| - | Calibrating the system: | ||
| - | During this step a few red dots are displayed at various positions on the screen. Images of the eyes are extracted during the display of each dot. The eye images and their corresponding dot positions are used to train a Gaussian Process that represents the mapping between the image of an eye and the position on the screen. Note that changes in head pose often requires the system to be recalibrated. | ||
| - | Tracking: | ||
| - | |||
| - | After all the calibration dots are processed the Gaussian Process yields a predictive distribution, so that the expected point of eye focus on the display monitor can be estimated given a new image of the eye. If the user loads his/her selected feature points, the Viola Jones face detector is used once to determine the search region where the feature points are expected. Subsequently, optical flow is used to track each feature point. The eye images are extracted (using the first two selected corner points as reference), and the gaze is predicted using the extracted eye images and the trained Gaussian Process(()). | ||
| - | |||
| ===== Pré-requis ===== | ===== Pré-requis ===== | ||
| - | Requirements: | + | * vxl >= 1.5.1 http://vxl.sourceforge.net/ FIXME et l'accessibilité? |
| - | vxl >= 1.5.1 http://vxl.sourceforge.net/ | + | * [[http://sourceforge.net/projects/opencvlibrary|opencv]] >= 0.9.7 FIXME c'est pas mieux un lien comme ça :P |
| - | opencv >= 0.9.7 http://sourceforge.net/projects/opencvlibrary | + | * gtkmm-2.4 >= 2.8.0 http://www.gtkmm.org/ |
| - | gtkmm-2.4 >= 2.8.0 http://www.gtkmm.org/ | + | * cairomm-1.0 >= 0.6.0 http://cairographics.org/cairomm/ |
| - | cairomm-1.0 >= 0.6.0 http://cairographics.org/cairomm/ | + | * boost >= 1.32.0 http://www.boost.org/ |
| - | boost >= 1.32.0 http://www.boost.org/ | + | |
| - | Under Debian testing: | + | Sur la version "Debian testing" FIXME Et sur ubuntu???? |
| - | # apt-get install libcv-dev libhighgui-dev libcvaux-dev \ | + | <code>apt-get install libcv-dev libhighgui-dev libcvaux-dev libgtkmm-2.4-dev libcairomm-1.0-dev libboost-dev</code> |
| - | libgtkmm-2.4-dev libcairomm-1.0-dev libboost-dev | + | |
| - | (vxl must be installed from the source) | + | (vxl must be installed from the source) |
| - | Important: in vxl's ccmake, set BUILD_SHARED_LIBS to ON. | + | Important: in vxl's ccmake, set BUILD_SHARED_LIBS to ON. |
| + | |||
| + | FIXME Je ne parle pas anglais. Et on est sur ubuntu-**FR** | ||
| Ligne 71: | Ligne 58: | ||
| * Le gestionnaire d'archives s'ouvre sur le fichier ''opengazer-code-5'' | * Le gestionnaire d'archives s'ouvre sur le fichier ''opengazer-code-5'' | ||
| * [[archivage|Extraire l'archive]] dans votre dossier favori. Par exemple : ''~/Documents/Compilation''. Le dossier ''opengazer-code-5'' sera créé automatiquement. | * [[archivage|Extraire l'archive]] dans votre dossier favori. Par exemple : ''~/Documents/Compilation''. Le dossier ''opengazer-code-5'' sera créé automatiquement. | ||
| - | ===== Configuration ===== | ||
| - | |||
| - | Tout d'abord, [[:tutoriel:comment_modifier_un_fichier|ouvrez le fichier]] **/truc/machin/bidule** en modification puis … | ||
| - | |||
| - | ===== Utilisation ===== | ||
| - | |||
| - | Lancez l'application comme indiqué [[:tutoriel:comment_lancer_application|ici]] ou via le [[:terminal]] (toutes [[:versions]] ou [[:variantes]] d'Ubuntu) avec la [[:commande_shell|commande]] suivante : <code>machin-chose</code> | ||
| - | |||
| - | ===== Désinstallation ===== | ||
| - | |||
| - | Pour supprimer cette application, il suffit de [[:tutoriel:comment_supprimer_un_paquet|supprimer son paquet]]. Selon la méthode choisie, la configuration globale de l'application est conservée ou supprimée. Les journaux du système, et les fichiers de préférence des utilisateurs dans leurs dossiers personnels sont toujours conservés. | ||
| ===== Voir aussi ===== | ===== Voir aussi ===== | ||
| + | * //Traduction et adaptation d'après **(en)** [[https://eyecomtec.com/3105-Open-Gazer|« Analyse critique d'Open Gazer »]] | ||
| * **(en)** [[https://eyecomtec.com/3105-Open-Gazer|Site officiel de Opengazer]] | * **(en)** [[https://eyecomtec.com/3105-Open-Gazer|Site officiel de Opengazer]] | ||
| - | * **(fr)** [[Site de la communauté francophone du logiciel Bidule]] | ||
| * [[http://forum.ubuntu-fr.org/viewtopic.php?id=64840|Discussion « J'ai un soucis avec le logiciel Bidule »]] sur le forum Ubuntu-fr | * [[http://forum.ubuntu-fr.org/viewtopic.php?id=64840|Discussion « J'ai un soucis avec le logiciel Bidule »]] sur le forum Ubuntu-fr | ||
| ---- | ---- | ||
| - | //Auteur-traducteur : [[utilisateurs:eagle08|René Stoecklin]]. Date de création : 22 novembre 2017. \\ | + | //Contributeurs principaux : [[utilisateurs:eagle08|René Stoecklin]].// |
| - | Contributeurs principaux : [[utilisateurs:eagle08|René Stoecklin]].// | + | |
| - | + | ||
| - | //Traduction et adaptation d'après **(en)** [[https://eyecomtec.com/3105-Open-Gazer|« Analyse critique d'Open Gazer »]] — site : Eyecomtec ; auteur : inconnu ; date : inconnue.// | + | |