A Detailed Look at Scale and Translation Invariance in a Hierarchical Neural Model of Visual Object Recognition

The HMAX model has recently been proposed by Riesenhuber & Poggio as a hierarchical model of position- and size-invariant object recognition in visual cortex. It has also turned out to model successfully a number of other properties of the ventral visual stream (the visual pathway thought to be crucial for object recognition in cortex), and particularly of (view-tuned) neurons in macaque inferotemporal cortex, the brain area at the top of the ventral stream. The original modeling study only used ``paperclip'' stimuli, as in the corresponding physiology experiment, and did not explore systematically how model units' invariance properties depended on model parameters. In this study, we aimed at a deeper understanding of the inner workings of HMAX and its performance for various parameter settings and ``natural'' stimulus classes. We examined HMAX responses for different stimulus sizes and positions systematically and found a dependence of model units' responses on stimulus position for which a quantitative description is offered. Interestingly, we find that scale invariance properties of hierarchical neural models are not independent of stimulus class, as opposed to translation invariance, even though both are affine transformations within the image plane.

Vector-Based Integration of Local and Long-Range Information in Visual Cortex

Integration of inputs by cortical neurons provides the basis for the complex information processing performed in the cerebral cortex. Here, we propose a new analytic framework for understanding integration within cortical neuronal receptive fields. Based on the synaptic organization of cortex, we argue that neuronal integration is a systems--level process better studied in terms of local cortical circuitry than at the level of single neurons, and we present a method for constructing self-contained modules which capture (nonlinear) local circuit interactions. In this framework, receptive field elements naturally have dual (rather than the traditional unitary influence since they drive both excitatory and inhibitory cortical neurons. This vector-based analysis, in contrast to scalarsapproaches, greatly simplifies integration by permitting linear summation of inputs from both "classical" and "extraclassical" receptive field regions. We illustrate this by explaining two complex visual cortical phenomena, which are incompatible with scalar notions of neuronal integration.

Translation Invariance in Object Recognition, and Its Relation to Other Visual Transformations

Human object recognition is generally considered to tolerate changes of the stimulus position in the visual field. A number of recent studies, however, have cast doubt on the completeness of translation invariance. In a new series of experiments we tried to investigate whether positional specificity of short-term memory is a general property of visual perception. We tested same/different discrimination of computer graphics models that were displayed at the same or at different locations of the visual field, and found complete translation invariance, regardless of the similarity of the animals and irrespective of direction and size of the displacement (Exp. 1 and 2). Decisions were strongly biased towards same decisions if stimuli appeared at a constant location, while after translation subjects displayed a tendency towards different decisions. Even if the spatial order of animal limbs was randomized ("scrambled animals"), no deteriorating effect of shifts in the field of view could be detected (Exp. 3). However, if the influence of single features was reduced (Exp. 4 and 5) small but significant effects of translation could be obtained. Under conditions that do not reveal an influence of translation, rotation in depth strongly interferes with recognition (Exp. 6). Changes of stimulus size did not reduce performance (Exp. 7). Tolerance to these object transformations seems to rely on different brain mechanisms, with translation and scale invariance being achieved in principle, while rotation invariance is not.

Visual Segmentation without Classification in a Model of the Primary Visual Cortex

Stimuli outside classical receptive fields significantly influence the neurons' activities in primary visual cortex. We propose that such contextual influences are used to segment regions by detecting the breakdown of homogeneity or translation invariance in the input, thus computing global region boundaries using local interactions. This is implemented in a biologically based model of V1, and demonstrated in examples of texture segmentation and figure-ground segregation. By contrast with traditional approaches, segmentation occurs without classification or comparison of features within or between regions and is performed by exactly the same neural circuit responsible for the dual problem of the grouping and enhancement of contours.

Visual Recognition and Categorization on the Basis of Similarities to Multiple Class Prototypes

To recognize a previously seen object, the visual system must overcome the variability in the object's appearance caused by factors such as illumination and pose. Developments in computer vision suggest that it may be possible to counter the influence of these factors, by learning to interpolate between stored views of the target object, taken under representative combinations of viewing conditions. Daily life situations, however, typically require categorization, rather than recognition, of objects. Due to the open-ended character both of natural kinds and of artificial categories, categorization cannot rely on interpolation between stored examples. Nonetheless, knowledge of several representative members, or prototypes, of each of the categories of interest can still provide the necessary computational substrate for the categorization of new instances. The resulting representational scheme based on similarities to prototypes appears to be computationally viable, and is readily mapped onto the mechanisms of biological vision revealed by recent psychophysical and physiological studies.

Visual Speech Synthesis by Morphing Visemes

We present MikeTalk, a text-to-audiovisual speech synthesizer which converts input text into an audiovisual speech stream. MikeTalk is built using visemes, which are a small set of images spanning a large range of mouth shapes. The visemes are acquired from a recorded visual corpus of a human subject which is specifically designed to elicit one instantiation of each viseme. Using optical flow methods, correspondence from every viseme to every other viseme is computed automatically. By morphing along this correspondence, a smooth transition between viseme images may be generated. A complete visual utterance is constructed by concatenating viseme transitions. Finally, phoneme and timing information extracted from a text-to-speech synthesizer is exploited to determine which viseme transitions to use, and the rate at which the morphing process should occur. In this manner, we are able to synchronize the visual speech stream with the audio speech stream, and hence give the impression of a photorealistic talking face.

On the difficulty of feature-based attentional modulations in visual object recognition: A modeling study.

Numerous psychophysical experiments have shown an important role for attentional modulations in vision. Behaviorally, allocation of attention can improve performance in object detection and recognition tasks. At the neural level, attention increases firing rates of neurons in visual cortex whose preferred stimulus is currently attended to. However, it is not yet known how these two phenomena are linked, i.e., how the visual system could be "tuned" in a task-dependent fashion to improve task performance. To answer this question, we performed simulations with the HMAX model of object recognition in cortex [45]. We modulated firing rates of model neurons in accordance with experimental results about effects of feature-based attention on single neurons and measured changes in the model's performance in a variety of object recognition tasks. It turned out that recognition performance could only be improved under very limited circumstances and that attentional influences on the process of object recognition per se tend to display a lack of specificity or raise false alarm rates. These observations lead us to postulate a new role for the observed attention-related neural response modulations.

Geometric Aspects of Visual Object Recognition

This thesis presents there important results in visual object recognition based on shape. (1) A new algorithm (RAST; Recognition by Adaptive Sudivisions of Tranformation space) is presented that has lower average-case complexity than any known recognition algorithm. (2) It is shown, both theoretically and empirically, that representing 3D objects as collections of 2D views (the "View-Based Approximation") is feasible and affects the reliability of 3D recognition systems no more than other commonly made approximations. (3) The problem of recognition in cluttered scenes is considered from a Bayesian perspective; the commonly-used "bounded-error errorsmeasure" is demonstrated to correspond to an independence assumption. It is shown that by modeling the statistical properties of real-scenes better, objects can be recognized more reliably.

Espai creatiu. Poesia visual. Autoretrat

Poesia visual guanyadora del concurs literari organitzat a la Facultat per celebrar la Diada de St. Jordi 2005 amb el lema "Sentir paraules"

Departament de Psicologia [Ressenya del llibre Adolescents and audio-visual media in five countries, de Ferran Casas, Irene Rizzini, Rose September, Per Egil Mjaavatn i Usha Nayar (coord.)]

Aquest llibre és el producte d'anys de cooperació entre equips de recerca de cinc països diferents, tot ells Key Institutions de la xarxa Childwatch International, en el marc d'un projecte plurinacional sobre adolescents i mitjans

CoDaPack. An Excel and Visual Basic based software of compositional data analysis. Current version and discussion form upcoming versions

In the eighties, John Aitchison (1986) developed a new methodological approach for the statistical analysis of compositional data. This new methodology was implemented in Basic routines grouped under the name CODA and later NEWCODA inMatlab (Aitchison, 1997). After that, several other authors have published extensions to this methodology: Marín-Fernández and others (2000), Barceló-Vidal and others (2001), Pawlowsky-Glahn and Egozcue (2001, 2002) and Egozcue and others (2003). (...)

Ver ordenadamente : el cuadrante visual y su aplicación en los procesos de la percepción visual.

Las fotografías son de Paco Vega y la propia autora

Cultura y tradiciones asturianas en la Educación Plástica y Visual : unidad didáctica La sidra.

Esta unidad didáctica utiliza la sidra como hilo conductor, una bebida típica de la región obtenida de la manzana, elegida por su cercanía al ambiente familiar y social de los alumnos, por dar a conocer un patrimonio cultural y artístico, cercano pero bastante desconocido y por ser tratado al mismo tiempo desde varias áreas: Ciencias Sociales, Música, Ciencias Naturales, Lengua Española, Lengua y Cultura Asturiana, etc...Se seleccionaron los elementos naturales y objetos relacionados con la fabricación de la sidra, así como en algunas de las obras artísticas inspiradas en ella. Sin olvidar su aspecto conceptual, se plantea con un carácter eminentemente práctico, evitando el planteamiento de ejercicios de solución única, procurando que cada actividad propuesta se pueda realizar con mayor o menor grado de dificultad, dependiendo de las características del alumnado. Alternan actividades individuales con otras colectivas. La evaluación se realiza a partir de unos criterios que tratan de medir la propia evaluación de los alumnos. Al final se presenta abundante material de apoyo: que va desde la explicación de los útiles de dibujo, a ejemplos de construcciones geométricas, pasando por la descripción de conceptos visuales, así como de las técnicas y materiales más comunes. Concluye el material con una selección de fotos e ilustraciones que servirán para el desarrollo de la unidad, así como una relación de pintores asturianos relacionados con el tópico.

Gu??a de recursos para la elaboraci??n de la respuesta educativa al alumnado discapacitado visual en el Bachillerato

Resumen basado en la publicaci??n

Dificultades de aprendizaje perceptivo-visual, análisis de una experiencia escolar : estudio de casos.

Comprobar si los cambios curriculares que se introducen en la investigación producen cambios en el desarrollo de los alumnos. Ofrecer la posibilidad de aplicación de estos resultados a pedagogos y profesionales de Educación Especial cuyos alumnos tengan características semenjantes. Fase de inmersión, exploración, diagnóstico y formulación de hipótesis; análisis de los recursos, elaboración del plan de intervención; intervención educativa, y evaluación del proceso. Memorandum análitico y anotaciones de investigación, entrevistas y cuestionarios, anotaciones de otros observadores, test y pruebas psicopedagógicas, documentación fotográfica y perfiles. Análisis de documentos. La aportación de actividades perceptivo-visuales y motrices previas y simultáneas a la enseñanza lectoescritora proporciona unas habilidades que ayudan al aprendizaje por varias razones: los programas suponen la adquisición de estrategias que se corresponden con las exigidas para cualquier tarea escolar; el plan de intervención comprende tres aspectos el desarrollo de la comunicación verbal, asimilación de términos referidos a conceptos básicos de espacio, tiempo y cantidad y potenciar el lenguaje como regulador de la acción y aprendizaje. Fecha finalización tomada del código del documento.