Visual features of intermediate complexity and their use in classification

@article{Ullman2002VisualFO,
  title={Visual features of intermediate complexity and their use in classification},
  author={Shimon Ullman and Michel Vidal-Naquet and Erez Sali},
  journal={Nature Neuroscience},
  year={2002},
  volume={5},
  pages={682-687}
}
The human visual system analyzes shapes and objects in a series of stages in which stimulus features of increasing complexity are extracted and analyzed. The first stages use simple local features, and the image is subsequently represented in terms of larger and more complex features. These include features of intermediate complexity and partial object views. The nature and use of these higher-order representations remains an open question in the study of visual processing by the primate cortex… 
A feedforward architecture accounts for rapid categorization
TLDR
It is shown that a specific implementation of a class of feedforward theories of object recognition (that extend the Hubel and Wiesel simple-to-complex cell hierarchy and account for many anatomical and physiological constraints) can predict the level and the pattern of performance achieved by humans on a rapid masked animal vs. non-animal categorization task.
Exploration of complex visual feature spaces for object perception
TLDR
This work implemented a novel functional magnetic resonance imaging method in which visual stimuli are selected in real-time based on BOLD responses to recently shown stimuli, and examined both the behavior and the complex visual properties the method identified as reliably activating selected brain regions.
The Optimal Human Ventral Stream from Estimates of the Complexity of Visual Objects
TLDR
A generic information-processing hierarchical model is put forth, and it is shown how the total number of neurons required depends on the number of hierarchical levels and on the complexity of visual objects that must be recognized.
Fragmented ambiguous objects: Stimuli with stable low-level features for object recognition tasks
TLDR
A set of line segment-based images that are matched for luminance, contrast, and orientation distribution but result in a range of object and non-object percepts, and identify a set of 100 images that all have the same low-level properties but cover a rangeof recognizability and semantic stability.
An Approach to Visual Scenes Matching with Curvilinear Regions
TLDR
This paper presents a biologically-inspired artificial vision system that is similar to other existing methods that also use intermediate complexity features for achieving visual matching, but the novelty of the system is the curvilinear features that it uses.
Learning a dictionary of shape-components in visual cortex: comparison with neurons, humans and machines
TLDR
This may be the first time that a neurobiological model, faithful to the physiology and the anatomy of visual cortex, not only competes with some of the best computer vision systems thus providing a realistic alternative to engineered artificial vision systems, but also achieves performance close to that of humans in a categorization task involving complex natural images.
Inferential Models of the Visual Cortical Hierarchy*
TLDR
This chapter describes how a Bayesian, inferential perspective may help to understand the organization of visual knowledge, and its utilization through the feedforward and feedback flow of information.
The use of higher-order statistics in rapid object categorization in natural scenes.
TLDR
This work investigated the eccentricity-dependent role of shape and statistical information for ultrarapid object categorization, using the higher-order statistics proposed by Portilla and Simoncelli (2000).
Computational object recognition: a biologically motivated approach
TLDR
A conceptual framework for artificial object recognition systems is proposed based on findings from neurophysiological and neuropsychological research on the visual system in primate cortex and the use of incremental and view-based approaches together with the ability of online feature selection and the interconnection of object-views to form an overall object representation is suggested.
Robust Object Recognition with Cortex-Like Mechanisms
TLDR
A hierarchical system that closely follows the organization of visual cortex and builds an increasingly complex and invariant feature representation by alternating between a template matching and a maximum pooling operation is described.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 31 REFERENCES
Columns for visual features of objects in monkey inferotemporal cortex
TLDR
The anterior inferotemporal area of the monkey cortex, the final station of the visual cortical stream crucial for object recognition, consists of columns, each containing cells responsive to similar visual features of objects.
Hierarchical models of object recognition in cortex
TLDR
A new hierarchical model consistent with physiological data from inferotemporal cortex that accounts for this complex visual task and makes testable predictions is described.
SEEMORE: Combining Color, Shape, and Texture Histogramming in a Neurally Inspired Approach to Visual Object Recognition
TLDR
It is concluded that in the light of the vast hardware resources available in the ventral stream of the primate visual system relative to those exercised here, the appealingly simple feature-space conjecture remains worthy of serious consideration as a neurobiological model.
The “independent components” of natural scenes are edge filters
What Is the Goal of Sensory Coding?
  • D. Field
  • Computer Science
    Neural Computation
  • 1994
TLDR
It is proposed that compact coding schemes are insufficient to account for the receptive field properties of cells in the mammalian visual pathway and suggested that natural scenes, to a first approximation, can be considered as a sum of self-similar local functions (the inverse of a wavelet).
A sequence of object‐processing stages revealed by fMRI in the human occipital lobe
TLDR
Functional magnetic resonance imaging was used in combined functional selectivity and retinotopic mapping tests to reveal object‐related visual areas in the human occpital lobe and suggest the existence of object‐fragment representation in LO.
Neuronal mechanisms of object recognition.
TLDR
Recent experimental findings about the representation of object images in the inferotemporal cortex, a brain structure that is thought to be essential for object vision, are summarized and discussed in relation to the computational frames proposed for object recognition.
Emergence of simple-cell receptive field properties by learning a sparse code for natural images
TLDR
It is shown that a learning algorithm that attempts to find sparse linear codes for natural scenes will develop a complete family of localized, oriented, bandpass receptive fields, similar to those found in the primary visual cortex.
...
1
2
3
4
...