Evolving ambiguous images

This article describes the use of evolutionary methods to generate ambiguous images---images that the brain or a computer may interpret in multiple ways. Object detectors often falsely identify the presence of objects in these images, even when they are not visible to human observers.

Evolving ambiguous images

This work explores the creation of ambiguous images, i.e., images that may induce multistable perception, by evolutionary means. Ambiguous images are created using a general purpose approach, composed of an expression-based evolutionary engine and a set of object detectors, which are trained in advance using Machine Learning techniques. Images are evolved using Genetic Programming and object detectors are used to classify them. The information gathered during classification is used to assign fitness. In a first stage, the system is used to evolve images that resemble a single object. In a second stage, the discovery of ambiguous images is promoted by combining pairs of object detectors. The analysis of the results highlights the ability of the system to evolve ambiguous images and the differences between computational and human ambiguous images.

Une silhouette naturelle est-elle fréquemment classée dans plusieurs catégories de base?

Les silhouettes ambiguës, comme celle du lapin/canard (Jastrow, 1899), ont été étudiées selon plusieurs approches. Toutefois, les figures prises en exemples dans la large majorité des études sont généralement les mêmes. Cette redondance des images ambiguës utilisées pousse à croire qu'elles sont peut-être assez rares. Certaines observations anecdotiques suggèrent cependant qu’elles seraient au contraire relativement fréquentes. C'est ce que cherche à déterminer cette expérience. Nous avons utilisé des modèles tridimensionnels d'animaux projetés de façon aléatoire afin d'en extraire les silhouettes dont la complexité périmétrique a ensuite été modifiée par lissage. Treize sujets ont dû indiquer ce qu'ils percevaient dans l'image. Nous démontrons qu’une silhouette est classée en moyenne dans 1.9079 catégories de base. Nous avons également démontré qu’une diminution de la complexité périmétrique rend d’abord une silhouette plus ambiguë pour éventuellement atteindre un sommet (équivalent à environ six fois la complexité périmétrique d’un disque) à la suite duquel l’ambiguïté chute.

Silenciosas narrativas em imagem-tempo: João Gilberto Noll, esvaziamento discursivo e cinema moderno

Este trabalho consiste num exercício de leitura da narrativa literária do escritor brasileiro João Gilberto Noll, promovendo uma aproximação de sua obra ao conceito de imagem-tempo, do filósofo Gilles Deleuze, no tocante a aspectos narrativos e à tendência ao esvaziamento discursivo, ao silêncio, enquanto elemento significativo na produção artística e tendência na arte moderna. O conceito imagem-tempo foi engendrado pelo filósofo francês para pensar o cinema moderno, que se perfaz num regime de imagens que rompe com a narratividade clássica, com a percepção baseada no esquema sensório-motor. Neste trabalho, no entanto, o conceito é pensado em relação à obra literária de João Gilberto Noll, que guarda forte relação com o cinema moderno e se nos apresenta em fragmentada tessitura imagética, tendendo ao esvaziamento discursivo. Assim, tendo como ponto de reflexão a obra de Noll, buscamos discutir como a imagem-tempo e o silêncio compõem a obra do escritor. Após apresentação e discussão do conceito de imagem-tempo e de silêncio, procedemos a uma leitura de pontos significativos da obra ficcional de Noll, ensaiando uma relação entre cinema, literatura e outras artes no que concerne basicamente à produção de imagens numa determinada forma narrativa, bem como às implicações dessas formas para o pensamento. Por uma questão de economia estratégica, para a formação de um recorte de expressão significativa da produção do escritor, suas obras diretamente consideradas neste trabalho são Hotel Atlântico (1989) e O quieto animal da esquina (1991). Pretende-se com essa relação (1) propor alguns caminhos interpretativos para a obra de Noll e (2) investigar como a produção narrativa moderna, sobretudo a que se aproxima do conceito de imagem-tempo, constituída de forte apelo visual, que se perfaz na produção de imagens ambíguas, de narrativas descontínuas, de protagonistas errantes, tende a esse esvaziamento discursivo, ao silêncio.

O DEUS ROSIANO: ANÁLISE TEOLÓGICO-LITERÁRIA DAS IMAGENS AMBÍ-GUAS DE DEUS EM GRANDE SERTÃO: VEREDAS

Tudo é e não é . Analisar algumas imagens ambíguas de Deus em Grande Sertão: Veredas foi o objetivo desta dissertação. Para tanto, essa análise é uma tentativa interdisciplinar de leitura e interpretação, em que Teologia e Literatura são interlocutoras. A partir do romance rosiano, sob à luz hermenêutica da crítica literária e da reflexão teológica, tentamos indicar que a escritura de João Guimarães Rosa apresenta Deus de modo ambíguo. Essa assertiva é possível, pois se percebeu na provisoriedade humana, poetizada pelo escritor e personificada por Riobaldo, o traço sine qua non do modo de ver mundos misturados . Ao rememorar e renarrar as estórias sua vida, Riobaldo abre espaço ao Mistério. Nonada . Em cada travessia, o protagonista-narrador reflete acerca de Deus , por meio da fala poética cujas imagens diversas sugerem um Deus muito contrariado . Sem enquadramentos teológicos e/ou filosóficos definitivos, Rosa provoca-nos ao mostrar-nos que o Deus que roda tudo revela-se e evade-se no sertão-universo. Lugar físico-mítico. É no sertão que intentamos seguir os rastros de Deus segundo a íris riobaldiana. Olhar de constante movimento entre o obscuro e o revelado, entre o é e não é.(AU)

Tibetan Written Images : A Study of Imagery in the Writings of Dhondup Gyal

Dhondup Gyal (Don grub rgyal, 1953 - 1985) was a Tibetan writer from Amdo (Qinghai, People's Republic of China). He wrote several prose works, poems, scholarly writings and other works which have been later on collected together into The Collected Works of Dhondup Gyal, in six volumes. He had a remarkable influence on the development of modern Tibetan literature in the 1980s. Examining his works, which are characterized by rich imagery, it is possible to notice a transition from traditional to modern ways of literary expression. Imagery is found in both the poems and prose works of Dhondup Gyal. Nature imagery is especially prominent and his writings contain images of flowers and plants, animals, water, wind and clouds, the heavenly bodies and other environmental elements. Also there are images of parts of the body and material and cultural images. To analyse the images, most of which are metaphors and similes, the use of the cognitive theory of metaphor provides a good framework for making comparisons with images in traditional Tibetan literature and also some images in Chinese, Indian and Western literary works. The analysis shows that the images have both traditional and innovative features. The source domains of images often appear similar to those found in traditional Tibetan literature and are slow to change. However, innovative shifts occur in the way they are mapped on their target domains, which may express new meanings and are usually secular in nature if compared to the religiosity which often characterizes traditional Tibetan literature. Dhondup Gyal's poems are written in a variety of styles, ranging from traditional types of verse compositions and poems in the ornate kāvya-style to modern free verse poetry. The powerful central images of his free verse poems and some other works can be viewed as structurally innovative and have been analysed with the help of the theory of conceptual blending. They are often ambiguous in their meaning, but can be interpreted to express ideas related to creativity, freedom and the need for change and development.

Recovering Intrinsic Images from a Single Image

We present an algorithm that uses multiple cues to recover shading and reflectance intrinsic images from a single image. Using both color information and a classifier trained to recognize gray-scale patterns, each image derivative is classified as being caused by shading or a change in the surface's reflectance. Generalized Belief Propagation is then used to propagate information from areas where the correct classification is clear to areas where it is ambiguous. We also show results on real images.

A Laminar Cortical Model for 3D Perception of Slanted and Curved Surfaces and of 2D Images: Developement, attention, and Bistability

A model of laminar visual cortical dynamics proposes how 3D boundary and surface representations of slated and curved 3D objects and 2D images arise. The 3D boundary representations emerge from interactions between non-classical horizontal receptive field interactions with intracorticcal and intercortical feedback circuits. Such non-classical interactions contextually disambiguate classical receptive field responses to ambiguous visual cues using cells that are sensitive to angles and disparity gradients with cortical areas V1 and V2. These cells are all variants of bipole grouping cells. Model simulations show how horizontal connections can develop selectively to angles, how slanted surfaces can activate 3D boundary representations that are sensitive to angles and disparity gradients, how 3D filling-in occurs across slanted surfaces, how a 2D Necker cube image can be represented in 3D, and how bistable Necker cuber percepts occur. The model also explains data about slant aftereffects and 3D neon color spreading. It shows how habituative transmitters that help to control developement also help to trigger bistable 3D percepts and slant aftereffects, and how attention can influence which of these percepts is perceived by propogating along some object boundaries.

Analyse de mouvements faciaux à partir d'images vidéo

Lors d'une intervention conversationnelle, le langage est supporté par une communication non-verbale qui joue un rôle central dans le comportement social humain en permettant de la rétroaction et en gérant la synchronisation, appuyant ainsi le contenu et la signification du discours. En effet, 55% du message est véhiculé par les expressions faciales, alors que seulement 7% est dû au message linguistique et 38% au paralangage. L'information concernant l'état émotionnel d'une personne est généralement inférée par les attributs faciaux. Cependant, on ne dispose pas vraiment d'instruments de mesure spécifiquement dédiés à ce type de comportements. En vision par ordinateur, on s'intéresse davantage au développement de systèmes d'analyse automatique des expressions faciales prototypiques pour les applications d'interaction homme-machine, d'analyse de vidéos de réunions, de sécurité, et même pour des applications cliniques. Dans la présente recherche, pour appréhender de tels indicateurs observables, nous essayons d'implanter un système capable de construire une source consistante et relativement exhaustive d'informations visuelles, lequel sera capable de distinguer sur un visage les traits et leurs déformations, permettant ainsi de reconnaître la présence ou absence d'une action faciale particulière. Une réflexion sur les techniques recensées nous a amené à explorer deux différentes approches. La première concerne l'aspect apparence dans lequel on se sert de l'orientation des gradients pour dégager une représentation dense des attributs faciaux. Hormis la représentation faciale, la principale difficulté d'un système, qui se veut être général, est la mise en œuvre d'un modèle générique indépendamment de l'identité de la personne, de la géométrie et de la taille des visages. La démarche qu'on propose repose sur l'élaboration d'un référentiel prototypique à partir d'un recalage par SIFT-flow dont on démontre, dans cette thèse, la supériorité par rapport à un alignement conventionnel utilisant la position des yeux. Dans une deuxième approche, on fait appel à un modèle géométrique à travers lequel les primitives faciales sont représentées par un filtrage de Gabor. Motivé par le fait que les expressions faciales sont non seulement ambigües et incohérentes d'une personne à une autre mais aussi dépendantes du contexte lui-même, à travers cette approche, on présente un système personnalisé de reconnaissance d'expressions faciales, dont la performance globale dépend directement de la performance du suivi d'un ensemble de points caractéristiques du visage. Ce suivi est effectué par une forme modifiée d'une technique d'estimation de disparité faisant intervenir la phase de Gabor. Dans cette thèse, on propose une redéfinition de la mesure de confiance et introduisons une procédure itérative et conditionnelle d'estimation du déplacement qui offrent un suivi plus robuste que les méthodes originales.