Interpreting image databases by region classification
Pattern RecognitionPublished 1 April 1997
Neill Campbell, W.P.J. Mackeown, Barry Thomas, Tom Trościanko
Citations92
SJR quartileQ1
SJR score2.06
SNIP2.67
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This paper addresses automatic interpretation of images of outdoor scenes by using a large database of ground-truth labelled images, a neural network is trained as a pattern classifier, thereby enabling image databases to be queried on scene content.
Abstract
This paper addresses automatic interpretation of images of outdoor scenes. The method allows instances of objects from a number of generic classes to be identified: vegetation, buildings; vehicles; roads, etc., thereby enabling image databases to be queried on scene content. The feature set is based, in part, on psychophysical principles and includes measures of colour, texture and shape. Using a large database of ground-truth labelled images, a neural network is trained as a pattern classifier. The method is demonstrated on a large test set to provide highly accurate image interpretations, with over 90% of the image area labelled correctly.
Keywords
Computer ScienceEngineering
Journal of the Optical Society of America AUncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters
3,165 Citations1985John Daugman
Evidence is presented that the 2D receptive-field profiles of simple cells in mammalian visual cortex are well described by members of this optimal 2D filter family, and thus such visual neurons could be said to optimize the general uncertainty relations for joint 2D-spatial-2D-spectral information resolution.
ComputerQuery by image and video content: the QBIC system
3,058 Citations1995Myron Flickner, Harpreet Sawhney +10 more
The QBIC system is described and its query capabilities are demonstrated, which allows queries on large image and video databases based on example images, user-constructed sketches and drawings, selected color and texture patterns, camera and object motion, and other graphical information.
IEEE Transactions on Pattern Analysis and Machine IntelligenceMultichannel texture analysis using localized spatial filters
1,375 Citations1990Alan C. Bovik, Marianna Clark +1 more
An interpretation of image texture as a region code, or carrier of region information, is emphasized and examples are given of both types of texture processing using a variety of real and synthetic textures.
Journal of the Optical Society of America APreattentive texture discrimination with early vision mechanisms
960 Citations1990Jitendra Malik, Pietro Perona
This model can predict the salience of texture boundaries in any arbitrary gray-scale image and Quantitative predictions of the degree of discriminability of different texture pairs match well with experimental measurements of discriminability in human observers.
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE<title>Photobook: tools for content-based manipulation of image databases</title>
883 Citations1994Alexander P. Pentland, Rosalind W. Picard +1 more
The Photobook system is described, which is a set of interactive tools for browsing and searching images and image sequences that differ from those used in standard image databases in that they make direct use of the image content rather than relying on annotations.
Elsevier eBooksPrinciples of Digital Image Synthesis
593 Citations1995
Focusing on theory, Andrew Glassner provides a comprehensive explanation of the three core fields of study that come together to form digital image synthesis: the human visual system, digital signal processing, and the interaction of matter and light.
Training Models of Shape from Sets of Examples
455 Citations1992T.F. Cootes, Chris Taylor +2 more
IEEE Transactions on Pattern Analysis and Machine IntelligenceModel-Based Three-Dimensional Interpretations of Two-Dimensional Images
359 Citations1983Rodney A. Brooks
IEEE Transactions on Information TheoryStochastic models for closed boundary analysis: Representation and reconstruction
231 Citations1981R.L. Kashyap, Rama Chellappa
The stochastic model representing the closed boundary is invariant to transformations like sealing, translation, choice of starting point, and rotation over angles that are multiples of 2\pi/N, where N is the number of observations.
Image and Vision ComputingCombining point distribution models with shape models based on finite element analysis
167 Citations1995T.F. Cootes, Chris Taylor
Pattern RecognitionContour sequence moments for the classification of closed planar shapes
149 Citations1987Lalit Gupta, M Srinath
It is shown that moment functions derived from contour sequences are invariant to shape translation, rotation and scale transformations.
ComputerSoftware Systems for Computer Graphics
15 Citations1976A.P. Lucido
This paper examines the structure both of subroutine libraries for use with some base language and of complete programming languages, and outlines the advantages and disadvantages of each, along with facilities that should be present in any software package.
IEE Proceedings - Vision Image and Signal ProcessingContextual image labelling with a neural network
11 Citations1994W.P.J. Mackeown
A neural network with a multilayer perceptron architecture is shown to be capable of labelling the visible objects in colour images of urban and rural outdoor scenes and a label clustering transformation is proposed and shown to cause a significant increase in the expected classification accuracy of the network.
Engineering Applications of Artificial IntelligenceRoad recognition with a neural network
11 Citations1994W.P.J. Mackeown, Phil Greenway +2 more
A neural-network model that is capable of recognising roads in colour images of urban and rural road scenes, and the two problems of segmentation and recognition are separated through the use of “ideal” segmentations, allowing the performance of the recognition method to be assessed independently of the effects of using an imperfect real segmentation process.
Automatic Interpretation of Outdoor Scenes.
9 Citations1995NW Campbell, Wpj Mackeown +2 more
A powerful set of features designed for outdoor scene analysis is extracted from regions in the segmented images and used to train a neural network to recognise eleven different classes of objects, including sky, road, building and vegetation.
Texture classification of segmented regions of FLIR images using neural networks
8 Citations2002J.F. Haddon, J.F. Boyce
The major regions in a sequence of FLIR images, segmented using co-occurrence techniques, are subjected to texture classification, which helps to train a range of multilayer perceptron neural networks using autonomously segmented regions in every fifth image.