Preferred Spatial Frequencies for Human Face Processing Are Associated with Optimal Class Discrimination in the Machine

Psychophysical studies suggest that humans preferentially use a narrow band of low spatial frequencies for face recognition. Here we asked whether artificial face recognition systems have an improved recognition performance at the same spatial frequencies as humans. To this end, we estimated recognition performance over a large database of face images by computing three discriminability measures: Fisher Linear Discriminant Analysis, Non-Parametric Discriminant Analysis, and Mutual Information. In order to address frequency dependence, discriminabilities were measured as a function of (filtered) image size. All three measures revealed a maximum at the same image sizes, where the spatial frequency content corresponds to the psychophysical found frequencies. Our results therefore support the notion that the critical band of spatial frequencies for face recognition in humans and machines follows from inherent properties of face images, and that the use of these frequencies is associated with optimal face recognition performance.

Unsupervised active regions for multiresolution image segmentation

An unsupervised approach to image segmentation which fuses region and boundary information is presented. The proposed approach takes advantage of the combined use of 3 different strategies: the guidance of seed placement, the control of decision criterion, and the boundary refinement. The new algorithm uses the boundary information to initialize a set of active regions which compete for the pixels in order to segment the whole image. The method is implemented on a multiresolution representation which ensures noise robustness as well as computation efficiency. The accuracy of the segmentation results has been proven through an objective comparative evaluation of the method

Image Segmentation Using Information Bottleneck Method

In image processing, segmentation algorithms constitute one of the main focuses of research. In this paper, new image segmentation algorithms based on a hard version of the information bottleneck method are presented. The objective of this method is to extract a compact representation of a variable, considered the input, with minimal loss of mutual information with respect to another variable, considered the output. First, we introduce a split-and-merge algorithm based on the definition of an information channel between a set of regions (input) of the image and the intensity histogram bins (output). From this channel, the maximization of the mutual information gain is used to optimize the image partitioning. Then, the merging process of the regions obtained in the previous phase is carried out by minimizing the loss of mutual information. From the inversion of the above channel, we also present a new histogram clustering algorithm based on the minimization of the mutual information loss, where now the input variable represents the histogram bins and the output is given by the set of regions obtained from the above split-and-merge algorithm. Finally, we introduce two new clustering algorithms which show how the information bottleneck method can be applied to the registration channel obtained when two multimodal images are correctly aligned. Different experiments on 2-D and 3-D images show the behavior of the proposed algorithms

Efficient image mosaicing for multi-robot visual underwater mapping

Robotic platforms have advanced greatly in terms of their remote sensing capabilities, including obtaining optical information using cameras. Alongside these advances, visual mapping has become a very active research area, which facilitates the mapping of areas inaccessible to humans. This requires the efficient processing of data to increase the final mosaic quality and computational efficiency. In this paper, we propose an efficient image mosaicing algorithm for large area visual mapping in underwater environments using multiple underwater robots. Our method identifies overlapping image pairs in the trajectories carried out by the different robots during the topology estimation process, being this a cornerstone for efficiently mapping large areas of the seafloor. We present comparative results based on challenging real underwater datasets, which simulated multi-robot mapping

Reconocimiento de objetos multi-clase basado en descriptores de forma

Este trabajo presenta un sistema para detectar y clasificar objetos binarios según la forma de éstos. En el primer paso del procedimiento, se aplica un filtrado para extraer el contorno del objeto. Con la información de los puntos de forma se obtiene un descriptor BSM con características altamente descriptivas, universales e invariantes. En la segunda fase del sistema se aprende y se clasifica la información del descriptor mediante Adaboost y Códigos Correctores de Errores. Se han usado bases de datos públicas, tanto en escala de grises como en color, para validar la implementación del sistema diseñado. Además, el sistema emplea una interfaz interactiva en la que diferentes métodos de procesamiento de imágenes pueden ser aplicados.

Motion analysis in terms of wireless video capsule endoscopy

El treball presentat suposa una visió general de l'"Endoscopia amb Càpsula de Vídeo Wireless" i la inspecció de sequències de contraccions intestinals amb les últimes tecnologies de visió per computador. Després de la observació preliminar dels fonaments mèdics requerits, la aplicació de visió per computador es presenta en aquestos termes. En essència, aquest treball proveïx una exhaustiva selecció, descripció i avaluació de cert conjunt de mètodes de processament d'imatges respecte a l'anàlisi de moviment, en el entorn de seqüències d'imatges preses amb una càpsula endoscòpica. Finalment, es presenta una aplicació de software per configurar i emprar de forma ràpida i fàcil un entorn experimental.

Evaluación de la regeneración ósea mediante procesado de imagen

La regeneració òssia és un procés estudiat per experts de tot el món. Aquests experts estudien materials capaços d’accelerar el procés de formació de teixit ossi en zones on s’han produït defectes ossis. Després d’un determinat període de temps de l’aplicació dels materials d’estudi en la zona on hi havia una manca de teixit ossi, s’obtenen imatges d’aquesta zona on l’expert mitjançant l’ inspecció visual d’aquestes imatges avalua si l’os s’ha regenerat bé o no. El problema d’aquest mètode d’avaluació es que requereix d’un expert on la valoració d’aquest és subjectiva i difícil de quantificar, el que pot provocar que hi hagi discordança entre experts. Amb la finalitat de aprofitar les imatges en que es basa l’expert per avaluar la capacitat de regeneració òssia dels materials d’estudi es proposa realitzar un anàlisi quantitatiu de la regeneració òssia basat en el processament d’imatge. L’algorisme dissenyat es capaç de classificar imatges de la mandíbula en: imatges de regeneració bona i dolenta mitjançant la parametrització de l’histograma de nivells de grisos de la imatge, solucionant la falta d’objectivitat del mètode d’avaluació de la regeneració òssia i la necessitat d’un expert per realitzar-la.

PHOTO STORE : Galeria virtual d'imatges

Ofereix a l'usuari la possibilitat de crear la seva pròpia galeria virtual d'imatges, i de classificar-les en àlbums dividits en categories per oferir una catalogació molt més específica. Els àlbums els subdividim públics per aque qualsevol visitant del web (registrat o no) pugui tenir la possibilitat d'accedir-hi,visualitzar i imprimir les fotos; o privats per a l'ús exclusiu de l'usuari que els publica.

Gestor de fotos geoetiquetades

En aquest treball de final de carrega s¿ha desenvolupat una aplicació que permet la gestió d¿imatges geoetiquetades publicades en els sistemes Flicker i PicasaWeb fent servir les tecnologies de Microsoft .NET i els serveis web que ofereixen les APIs públiques d¿aquestssistemes.

PICTour : aplicació modular per a la gestió d'imatges geoetiquetades mitjançant serveis en línea independents basada en tecnologia .NET

Aplicació realitzada emprant diverses tecnologies de la plataforma .NET i capaç d'adaptar-se a l'escenari canviant de la web 2.0 i aprofitar les eines que ofereix.

Sistema de catalogació edició i publicació en web d'imatges

Es pretén assolir tres grans objectius referits al tractament d'matges els quals són: la catalogació, l'edició i l'intercanvi d'aquestes mitjançant un espai web.

Gestió de fotos geoetiquetades amb Flickr i Picasa

Aquest projecte ens portarà a construir producte de software que ens permeti gestionar des de la aplicació les fotos que tenim publicades a Flickr i Picasa.

Scene Classification Using a Hybrid Generative/Discriminative Approach

We investigate whether dimensionality reduction using a latent generative model is beneficial for the task of weakly supervised scene classification. In detail, we are given a set of labeled images of scenes (for example, coast, forest, city, river, etc.), and our objective is to classify a new image into one of these categories. Our approach consists of first discovering latent ";topics"; using probabilistic Latent Semantic Analysis (pLSA), a generative model from the statistical text literature here applied to a bag of visual words representation for each image, and subsequently, training a multiway classifier on the topic distribution vector for each image. We compare this approach to that of representing each image by a bag of visual words vector directly and training a multiway classifier on these vectors. To this end, we introduce a novel vocabulary using dense color SIFT descriptors and then investigate the classification performance under changes in the size of the visual vocabulary, the number of latent topics learned, and the type of discriminative classifier used (k-nearest neighbor or SVM). We achieve superior classification performance to recent publications that have used a bag of visual word representation, in all cases, using the authors' own data sets and testing protocols. We also investigate the gain in adding spatial information. We show applications to image retrieval with relevance feedback and to scene classification in videos

Correction of shading effects in vision-based UUV localization

This paper describes the improvements achieved in our mosaicking system to assist unmanned underwater vehicle navigation. A major advance has been attained in the processing of images of the ocean floor when light absorption effects are evident. Due to the absorption of natural light, underwater vehicles often require artificial light sources attached to them to provide the adequate illumination for processing underwater images. Unfortunately, these flashlights tend to illuminate the scene in a nonuniform fashion. In this paper a technique to correct non-uniform lighting is proposed. The acquired frames are compensated through a point-by-point division of the image by an estimation of the illumination field. Then, the gray-levels of the obtained image remapped to enhance image contrast. Experiments with real images are presented

On the way to solve lighting problems in underwater imaging

A major obstacle to processing images of the ocean floor comes from the absorption and scattering effects of the light in the aquatic environment. Due to the absorption of the natural light, underwater vehicles often require artificial light sources attached to them to provide the adequate illumination. Unfortunately, these flashlights tend to illuminate the scene in a nonuniform fashion, and, as the vehicle moves, induce shadows in the scene. For this reason, the first step towards application of standard computer vision techniques to underwater imaging requires dealing first with these lighting problems. This paper analyses and compares existing methodologies to deal with low-contrast, nonuniform illumination in underwater image sequences. The reviewed techniques include: (i) study of the illumination-reflectance model, (ii) local histogram equalization, (iii) homomorphic filtering, and, (iv) subtraction of the illumination field. Several experiments on real data have been conducted to compare the different approaches