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.

/pdf/object-perception-as-bayesian-inference-2ors0mo4ec.pdf

Object Perception as Bayesian Inference

https://www.cell.com/neuron/pdf/S0896-6273(07)00376-5.pdf

Brain states: top-down influences in sensory processing.

We argue that the study of human vision should be aimed at determining how humans perform natural tasks on natural images. Attempts to understand the phenomenology of vision from artificial stimuli, though worthwhile as a starting point, risk leading to faulty generalizations about visual systems. In view of the enormous complexity of natural images, they are similar to trying to evaluate the performance of a soldier in battle from his ability at playing with a water pistol. 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 which use analysis by synthesis strategies with intriguing similarities to the brain.

Vision as Bayesian Inference: Analysis by Synthesis?

It is now emerging that vision is usually limited by object spacing rather than size. The visual system recognizes an object by detecting and then combining its features. ‘Crowding’ occurs when objects are too close together and features from several objects are combined into a jumbled percept. Here, we review the explosion of studies on crowding—in grating discrimination, letter and face recognition, visual search, selective attention, and reading—and find a universal principle, the Bouma law. The critical spacing required to prevent crowding is equal for all objects, although the effect is weaker between dissimilar objects. Furthermore, critical spacing at the cortex is independent of object position, and critical spacing at the visual field is proportional to object distance from fixation. The region where object spacing exceeds critical spacing is the ‘uncrowded window’. Observers cannot recognize objects outside of this window and its size limits the speed of reading and search. Object recognition means calling a chair a chair, despite variations in style, viewpoint, rendering and surrounding clutter. Crowding is a breakdown of object recognition. Let us begin by sketching a popular two-step model of object recognition: feature detection and combination. Features are components of images that are detected independently 1–4 . They are typically simple and nonoverlapping. The first step in object recognition is feature detection 4 . Each neuron in the primary visual cortex responds when a feature matches its receptive field. Only the features that drive neurons hard enough are detected 5 . In the second step, the brain combines some of the detected features to recognize the object. This combining step (including ‘integration’, ‘binding’, ‘segmentation’, ‘pooling’, ‘grouping’, ‘contour integration’ and ‘selective attention’) is still mysterious 3,4,6–11 .

/pdf/the-uncrowded-window-of-object-recognition-1k0n3a0hy6.pdf

Edmund T. Rolls

Papers

High-level vision: Object recognition and visual cognition, Shimon Ullman. MIT Press, Bradford (1996), ISBN 0 262 21013 4