Using Zernike moments for the illumination and geometry invariant classification of multispectral texture
IEEE Transactions on Image ProcessingPublished 1 January 1998
Lizhi Wang, Glenn Healey
Citations138
SJR quartileQ1
SJR score2.50
SNIP3.41
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
A method for recognizing color texture independent of rotation, scale, and illumination is developed, with the new result that illumination, rotation, and scale changes in the scene correspond to a specific transformation of correlation function Zernike moment matrices.
Abstract
We develop a method for recognizing color texture independent of rotation, scale, and illumination. Color texture is modeled using spatial correlation functions defined within and between sensor bands. Using a linear model for surface spectral reflectance with the same number of parameters as the number of sensor classes, we show that illumination and geometry changes in the scene correspond to a linear transformation of the correlation functions and a linear transformation of their coordinates. A several step algorithm that includes scale estimation and correlation moment computation is used to achieve the invariance. The key to the method is the new result that illumination, rotation, and scale changes in the scene correspond to a specific transformation of correlation function Zernike moment matrices. These matrices can be estimated from a color image. This relationship is used to derive an efficient algorithm for recognition. The algorithm is substantiated using classification results on over 200 images of color textures obtained under various illumination conditions and geometric configurations.
Keywords
Computer SciencePhysics and Astronomy
IEEE Transactions on Systems Man and CyberneticsTextural Features for Image Classification
22,499 Citations1973Robert M. Haralick, K. Shanmugam +1 more
These results indicate that the easily computable textural features based on gray-tone spatial dependancies probably have a general applicability for a wide variety of image-classification applications.
IRE Transactions on Information TheoryVisual pattern recognition by moment invariants
7,528 Citations1962Ming-Kuei Hu
It is shown that recognition of geometrical patterns and alphabetical characters independently of position, size and orientation can be accomplished and it is indicated that generalization is possible to include invariance with parallel projection.
Journal of the Optical Society of AmericaImage analysis via the general theory of moments*
2,248 Citations1980M. R. Teague
IEEE Transactions on Pattern Analysis and Machine IntelligenceInvariant image recognition by Zernike moments
1,889 Citations1990A. Khotanzad, Yaw Hua Hong
A systematic reconstruction-based method for deciding the highest-order ZERNike moments required in a classification problem is developed and the superiority of Zernike moment features over regular moments and moment invariants was experimentally verified.
Journal of the Franklin InstituteA spatial processor model for object colour perception
1,640 Citations1980Gershon Buchsbaum
A comprehensive mathematical model to account for colour constancy is formulated and provides a general unified mathematical framework for related psychophysical phenomenology.
IEEE Transactions on Pattern Analysis and Machine IntelligenceOn image analysis by the methods of moments
1,553 Citations1988C.-H. Teh, R.T. Chin
MIT Press eBooksGeometric invariance in computer vision
1,022 Citations1992Joseph L. Mundy, Andrew Zisserman
Part 1 foundations: algebraic invariants - invariant theory and enumerative combinatorics of young tableaux, and applications: transformation invariant indexing and invariant linear methods in photogrammetry and model-matching.
Journal of the Optical Society of America AEvaluation of linear models of surface spectral reflectance with small numbers of parameters
741 Citations1986Laurence T. Maloney
The results suggest that constraints on possible surface-reflectance functions and the "filtering" properties of the shapes of the spectral-sensitivity curves of photoreceptors can both contribute to color constancy.
IEEE Transactions on Pattern Analysis and Machine IntelligenceColor constant color indexing
556 Citations1995Brian Funt, Graham D. Finlayson
Results of tests with the new color-constant-color-indexing algorithm show that it works very well even when the illumination varies spatially in its intensity and color, which circumvents the need for color constancy preprocessing.
Journal of the Optical Society of America ACharacteristic spectra of Munsell colors
533 Citations1989Jussi Parkkinen, Jarmo Hallikainen +1 more
Psychonomic ScienceDependency of the spectral reflectance curves of the Munsell color chips
400 Citations1964Jozef Cohen
IEEE Transactions on Pattern Analysis and Machine IntelligenceA Model-Based Method for Rotation Invariant Texture Classification
344 Citations1986Rangasami L. Kashyap, A. Khotanzad
A new model-based approach for texture classification which is rotation invariant, i.e., the recognition accuracy is not affected if the orientation of the test texture is different from the Orientation of the training samples.
IEEE Transactions on Acoustics Speech and Signal ProcessingClassification of invariant image representations using a neural network
303 Citations1990A. Khotanzad, Jiayue Lu
Through extensive experimentation with noiseless as well as noisy binary images of all English characters, the following conclusions are reached: the MLP outperforms the other three classifiers, especially when noise is present; the nearest-neighbor classifier performs about the same as the NN for thenoiseless case.
IEEE Transactions on Pattern Analysis and Machine IntelligenceClassification of rotated and scaled textured images using Gaussian Markov random field models
300 Citations1991Fernand S. Cohen, Z. Fan +1 more
A modified Bayes decision rule is used to classify a given test image into one of C possible texture classes and the classification power of the method is demonstrated through experimental results on natural textures from the Brodatz album.
IEEE Transactions on Pattern Analysis and Machine IntelligenceTexture Analysis Using Generalized Co-Occurrence Matrices
296 Citations1979Larry S. Davis, Steven A. Johns +1 more
IEEE Transactions on Neural NetworksTranslation, rotation, and scale invariant pattern recognition by high-order neural networks and moment classifiers
229 Citations1992Stavros Perantonis, P.J.G. Lisboa
The performance of these networks at recognizing types and handwritten numerals independently of their position, size, and orientation is compared with and found superior to the performance of a layered feedforward network to which image features extracted by the method of moments are presented as input.
Journal of the Optical Society of America AGlobal color constancy: recognition of objects by use of illumination-invariant properties of color distributions
172 Citations1994Glenn Healey, David Slater
An algorithm is developed that assigns color descriptors to an object that depend on the surface properties of the object and not on the illumination, and performs significantly better than previous recognition algorithms based on color distribution.
IEEE Transactions on Pattern Analysis and Machine IntelligenceThe illumination-invariant recognition of 3D objects using local color invariants
108 Citations1996David Slater, Glenn Healey
An object recognition system is implemented that indexes into a database of models using the invariants and that uses associated geometric information for hypothesis verification and pose estimation, and is therefore relatively insensitive to occlusion.
MIT Press eBooksObject recognition based on moment (or algebraic) invariants
101 Citations1992Gabriel Taubin, David B. Cooper
A new family of computationally efficient algorithms, based on matrix computations, are presented for the evaluation of both Euclidean and affine algebraic moment invariants of data sets, reducing the computation required for the matching, and hence initial object recognition.
Pattern RecognitionPolarograms: A new tool for image texture analysis
98 Citations1981Larry S. Davis
A polarogram is a polar plot of an orientation sensitive texture statistic which gives rise to a class of texture descriptors which are sensitive to both texture coarseness and directionality, but yet which are invariant to rotations of the image textures.
Journal of the Optical Society of America AIllumination-invariant recognition of texture in color images
62 Citations1995Glenn Healey, Lizhi Wang
This work shows that illumination changes correspond to linear transformations of a surface correlation matrix, and derives a distance function for comparing sets of spatial correlation functions that can be used for illumination-invariant recognition.
IEEE Transactions on Pattern Analysis and Machine IntelligenceRetrieving multispectral satellite images using physics-based invariant representations
58 Citations1996Glenn Healey, Anil K. Jain
A set of algorithms and a search strategy for the robust content-based retrieval of multispectral satellite images using representations and methods that are invariant to illumination and atmospheric conditions are presented.
Journal of the Optical Society of America AUse of invariants for recognition of three-dimensional color textures
56 Citations1994Raghava Kondepudy, Glenn Healey
An image model for color texture based on spatial correlation functions defined both within and between color bands is introduced and it is shown that three-dimensional geometric transformations of a surface in the scene produce corresponding transformations in these correlation functions.
Advanced materials researchApplication of ART-2 Neural Network and Invariant Moment in Image Pattern Recognition
24 Citations2012Lei Hao, Yue Hua Gao +1 more
This paper mainly uses image pre-processing and feature extraction to calculate the invariant moment of image, and ultimately realizes the image pattern recognition based on ART-2 neural network, which solves the contradiction between network's plasticity and stability.
IEEE Transactions on Pattern Analysis and Machine IntelligenceLocal surface shape estimation of 3-D textured surfaces using Gaussian Markov random fields and stereo windows
9 Citations1993Maqbool Patel, Fernand S. Cohen
A stereo-windows concept is introduced to obtain a unique and consistent parent texture from the image data that, under appropriate transformations, yields the observed texture in the image.