Perceptual organization and visual recognition

By David G. Lowe. 2012

1,381 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Industrial and Manufacturing Engineering

View Paper: https://www.semanticscholar.org/paper/9d32a6b82be4c5323b0ff31655ede6422f5add8c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Industrial and Manufacturing Engineering

Citations in the corpus

Using Generative Models for Handwritten Digit Recognition (1996, methodology): “Motivated by the success of model-based shape recognition in overcoming some of these shortcomings [17], we have investigated the use of deformable elastic models for handwritten digit recognition [18].”
Alignment by Maximization of Mutual Information (1995, background): “A smooth, optimizable version of such a metric can be defined by introducing a penalty both for unmatched edges and for the distance between those that are matched (Lowe, 1985; Wells III, 1992).”
Learning visual groups from co-occurrences in space and time (2015, background): “The idea that perceptual groups reﬂect statistical structure in the environment has deep roots in the perception and cognition literature (Barlow (1985); Wilkin & Tenenbaum (1985); Tenenbaum & Witkin (1983); Lowe (2012); Rock (1983)).”
Deep Neural Networks as a Computational Model for Human Shape Sensitivity (2016, background): “In particular, Biederman focused on those properties of object shape that remain unchanged when the three-dimensional shape of an object is projected to the two-dimensional surface on the eye’s retina, such as curved versus straight object axis, parallel versus converging edges, and so on [23].”
Invariant Visual Object and Face Recognition: Neural and Computational Bases, and a Model, VisNet (2012, background): “This alignment approach is the main theme of the book by Ullman (1996), and there are a number of computer implementations (Lowe, 1985; Grimson, 1990; Huttenlocher and Ullman, 1990; Shashua, 1995).”
Markov Random Field Modeling in Image Analysis (2001, background): “1992), image segmentation (Silverman and Cooper 1988; Li 1990a), perceptual grouping (Lowe 1985; Mohan and Nevatia 1989; Herault and Horaud 1993), interpretation of line drawings (Leclerc and Fischler 1992), object matching and recognition (Fischler and Elschlager 1973; Davis 1979; Shapiro and Haral”
Toward a Biased Competition Account of Object-Based Segregation and Attention (2000, background): “Non-accidental properties (Lowe, 1985, 1987), properties which are unlikely to arise due to an observer's accidental viewpoint, also provide bottom-up cues that assist segregation.”
Three-Dimensional Object Recognition from Single Two-Dimensional Images (1987, background): “An extensive discussion of these issues has been presented by the author in previous work [19], but here we will examine the more practical question of applying these methods to the development of a particular vision system.”
Learning by watching: extracting reusable task knowledge from visual observation of human performance (1994, methodology): “Line images are extracted from each segmented region to match against known geometric models using Lowe's method [22].”
Object recognition and pose estimation using color cooccurrence histograms and geometric modeling (2005, methodology): “Although there are systems for which this step is performed automatically, [14, 23 ,31] the proposed approaches are time consuming and not appealing for real-time applications.”