{"id":14986,"date":"2018-03-09T09:01:56","date_gmt":"2018-03-09T09:01:56","guid":{"rendered":"https:\/\/www.deberes.net\/tesis\/sin-categoria\/contributions-to-shape-and-texture-face-similarity-measurement\/"},"modified":"2018-03-09T09:01:56","modified_gmt":"2018-03-09T09:01:56","slug":"contributions-to-shape-and-texture-face-similarity-measurement","status":"publish","type":"post","link":"https:\/\/www.deberes.net\/tesis\/matematicas\/contributions-to-shape-and-texture-face-similarity-measurement\/","title":{"rendered":"Contributions to shape and texture face similarity measurement"},"content":{"rendered":"<h2>Tesis doctoral de <strong> Albert Pujol Torras <\/strong><\/h2>\n<p>Esta tesis propone mejoras en m\u00e9todos de proyecci\u00f3n lineal, con la finalidad de medir de forma precisa la similitud entre dos caras. Al mismo tiempo muestra como algunas de las ideas exitosamente aplicadas en el campo de reconocimiento basado en visitas, pueden extenderse de forma sencilla cuando \u00fanicamente consideramos informaci\u00f3n geom\u00e9trica de caras.  se proponen dos mejoras basados en visitas: estas se basan en considerar como afectan las oclusiones de las im\u00e1genes al proceso de codificaci\u00f3n de las mismas, y como la informaci\u00f3n topolog\u00eda de las im\u00e1genes puede introducirse en los modelos de proyecci\u00f3n reduciendo de este modo el tama\u00f1o de los conjuntos de aprendizaje requeridos para sintonizar estos modelos, atenuando de esta forma el problema de la generalizaci\u00f3n.  por otro lado se aborda la utilizaci\u00f3n de informaci\u00f3n de forma para caracterizar medidas de similitud facial. En este trabajo se muestra como los descriptores basados en crestas y valles de la imagen son apropiados para caracterizar informaci\u00f3n de forma, proponiendo un modelo formal basado en las distancias de hausdorff, el cual nos permitir\u00e1 desarrollar medidas adecuadas para el reconocimiento de caras. Utilizando este marco, este trabajo introduce las medidas supervisadas de hausdorff, donde distorsiones geom\u00e9tricas medidas en un conjunto de aprendizaje, son utilizadas para determinar o aprender como deber\u00edan medirse estas distorsiones en un futuro, mejorando de esta forma el comportamiento de los sistemas autom\u00e1ticos de reconocimiento de caras. Como consecuencia del marco formal introducido, esta tesis desarrolla tambi\u00e9n el proceso de construcci\u00f3n de prototipos geom\u00e9tricos y mapas auto-organizativos, coherentes con las medidas de hausdorff. Por \u00faltimo este trabajo analiza como el proceso de caricaturizaci\u00f3n de las caras afecta a los sistemas computacionales de reconocimiento de caras.<\/p>\n<p>&nbsp;<\/p>\n<h3>Datos acad\u00e9micos de la tesis doctoral \u00ab<strong>Contributions to shape and texture face similarity measurement<\/strong>\u00ab<\/h3>\n<ul>\n<li><strong>T\u00edtulo de la tesis:<\/strong>\u00a0 Contributions to shape and texture face similarity measurement <\/li>\n<li><strong>Autor:<\/strong>\u00a0 Albert Pujol Torras <\/li>\n<li><strong>Universidad:<\/strong>\u00a0 Aut\u00f3noma de barcelona<\/li>\n<li><strong>Fecha de lectura de la tesis:<\/strong>\u00a0 21\/12\/2001<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<h3>Direcci\u00f3n y tribunal<\/h3>\n<ul>\n<li><strong>Director de la tesis<\/strong>\n<ul>\n<li>Juan  Jose Villanueva Pipa\u00f3n<\/li>\n<\/ul>\n<\/li>\n<li><strong>Tribunal<\/strong>\n<ul>\n<li>Presidente del tribunal: alberto Sanfeliu cort\u00e9s <\/li>\n<li>Jos\u00e9 Luis Alba castro (vocal)<\/li>\n<li>jordi Vitri? marca (vocal)<\/li>\n<li>josef Kittler (vocal)<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Tesis doctoral de Albert Pujol Torras Esta tesis propone mejoras en m\u00e9todos de proyecci\u00f3n lineal, con la finalidad de medir [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""}},"footnotes":""},"categories":[1890,199,2528,126,1525,21130],"tags":[48001,11662,30472,44151,48002,15895],"class_list":["post-14986","post","type-post","status-publish","format-standard","hentry","category-ciencia-de-los-ordenadores","category-fisica","category-inteligencia-artificial","category-matematicas","category-optica","category-tratamiento-digital-de-imagenes","tag-albert-pujol-torras","tag-alberto-sanfeliu-cortes","tag-jordi-vitri-marca","tag-jose-luis-alba-castro","tag-josef-kittler","tag-juan-jose-villanueva-pipaon"],"_links":{"self":[{"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/posts\/14986","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/comments?post=14986"}],"version-history":[{"count":0,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/posts\/14986\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/media?parent=14986"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/categories?post=14986"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/tags?post=14986"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}