PubMed Health⌕ Search

Biomedical subjects

Alan Yuille

Publications and source records attributed to Alan Yuille.

7 recordsLinked to original sources
PubMed2006

Probabilistic models of cognition: conceptual foundations.

Remarkable progress in the mathematics and computer science of probability has led to a revolution in the scope of probabilistic models. In particular, 'sophisticated' probabilistic methods apply to structured relational systems such as graphs and grammars, of immediate relevance to the cognitive sciences. This Special Issue outlines progress in this rapidly developing field, which provides a potentially unifying perspective across a wide range of domains and levels of explanation. Here, we introduce the historical and conceptual foundations of the approach, explore how the approach relates to studies of explicit probabilistic reasoning, and give a brief overview of the field as it stands today.

Algorithms↗
PubMed2006

Vision as Bayesian inference: analysis by synthesis?

We argue that the study of human vision should be aimed at determining how humans perform natural tasks with natural images. Attempts to understand the phenomenology of vision from artificial stimuli, although worthwhile as a starting point, can lead to faulty generalizations about visual systems, because of the enormous complexity of natural images. Dealing with this complexity is daunting, but Bayesian inference on structured probability distributions offers the ability to design theories of vision that can deal with the complexity of natural images, and that use 'analysis by synthesis' strategies with intriguing similarities to the brain. We examine these strategies using recent examples from computer vision, and outline some important implications for cognitive science.

Algorithms↗
PubMed2006

The perceived motion of a stereokinetic stimulus.

An ellipse rotating in the image plane can produce several different percepts. The two-dimensional (2D) percepts are either a rotating rigid ellipse or a constantly deforming non-rigid ellipse. The 3D percept is a rotating rigid circular disk that is tilted relative to the image plane. Stimuli that generate 3D percepts based on purely 2D rotational motion are known as stereokinetic stimuli. We examined the 3D percepts generated by the rotating ellipse stimulus. In theory, the motion of the 3D percept cannot be reliably inferred based on the 2D stimulus. When we quantitatively estimated observers' perceived motion, however, we found that the perceived motion was nearly identical across observers. These results suggest that all observers had similar 3D percepts. We assumed that given the 2D rotating ellipse stimulus the visual system generates a rigid 3D percept that is as slow and smooth as possible. The percepts predicted by these assumptions closely matched the experimental data. These findings suggest that perceptual ambiguity in stereokinetic stimuli is resolved using slow and smooth motion assumptions.

Depth Perception↗
PubMed2004

Object perception as Bayesian inference.

We perceive the shapes and material properties of objects quickly and reliably despite the complexity and objective ambiguities of natural images. Typical images are highly complex because they consist of many objects embedded in background clutter. Moreover, the image features of an object are extremely variable and ambiguous owing to the effects of projection, occlusion, background clutter, and illumination. The very success of everyday vision implies neural mechanisms, yet to be understood, that discount irrelevant information and organize ambiguous or noisy local image features into objects and surfaces. Recent work in Bayesian theories of visual perception has shown how complexity may be managed and ambiguity resolved through the task-dependent, probabilistic integration of prior object knowledge with image features.

Bayes Theorem↗
PubMed2003

Bayesian models of object perception.

The human visual system is the most complex pattern recognition device known. In ways that are yet to be fully understood, the visual cortex arrives at a simple and unambiguous interpretation of data from the retinal image that is useful for the decisions and actions of everyday life. Recent advances in Bayesian models of computer vision and in the measurement and modeling of natural image statistics are providing the tools to test and constrain theories of human object perception. In turn, these theories are having an impact on the interpretation of cortical function.

Animals↗
PubMed2003

The KGBR viewpoint-lighting ambiguity.

We address the visual ambiguities that arise in estimating object and scene structure from a set of images when the viewpoint and lighting are unknown. We obtain a novel viewpoint-lighting ambiguity called the KGBR that corresponds to a group of three-dimensional affine transformations on the object or scene geometry combined with transformations on the object or scene albedo. Our analysis assumes orthographic projection with an affine camera model. We include photometric cues, such as shadowing and shading, that we model using Lambertian reflectance functions with shadows (cast and attached) and multiple light sources (but no interreflections). We relate the KGBR to affine ambiguities in estimating shape and to the generalized bas-relief (GBR) ambiguity.

Humans↗