What a histogram can really tell the classifier

doi:10.1016/0031-3203(78)90006-7

Pattern Recognition

Volume 10, Issues 5–6, 1978, Pages 351-357

https://doi.org/10.1016/0031-3203(78)90006-7 Get rights and content

Abstract

This paper presents a simple and efficient clustering technique based on the partitioning of the data histogram. The clustering technique was developed in the context of a study of possible unsupervized classification procedures for multispectral earth imagery. The ultimate goal was on-board data compression, the algorithmic production of thematic maps.

The incoming raw spectral data is first reduced to its two principal (Karhunen-Loêve) components, the histogram of which is then partitioned into natural classes on the sole weight of evidence of the global statistics of the imagery. During the course of the study, it became clear that some connection existed between the proposed philosophy and professor Thom's novel theory of “catastrophes”.⁽¹⁾ A simple metric is added to the histogram topology. The metric uses both Shannon's and Fisher's notions of self information. In the domain of definition of the histogram, zones corresponding to the natural classes become separated by a no man's land, an inter-class zone. Under the same formulation, the metric is “Euclidean” on the class zone, “non-Euclidean”, i.e. “Lorentz” on the inter-class zone. This methodology and the underlying philosophy were tested in practice, and encouraging results were obtained.

References (0)

Cited by (8)

A comparative study for brain tumor detection in MRI images using texture features
2019, Sensors for Health Monitoring
MRI images are a very rich source of texture. Analysis of texture is crucial for the automation of tumor detection from MRI images. By analyzing what information a specific texture analysis method exploits to construct a feature vector, this chapter presents various texture analysis methods, understanding the ingredients of these methods and recognizing their merits and limitations. For a comparison between the state-of-the-art texture analysis methods, this chapter presents a common experimental protocol. A comprehensive treatise of four texture analysis methods with three classifiers is implemented and evaluated. Thus, this study aims to provide panoramas of texture analysis methods for the detection of a brain tumor from MRI images and reviews related works of the past.
Image annotation: Then and now
2018, Image and Vision Computing
Citation Excerpt :
While describing the texture, the computer vision researchers are describing it as everything of an image after extracting the color components and local shapes [2]. The various methods for extraction of texture features include histogram based first order texture features [56], gray tone spatial dependence matrix [57] and its variants [58,59], local binary pattern (LBP) [60] and its variant [61], local directional pattern [62] and its variant [63], wavelet features [64], etc. According to [65], if we get the same histogram twice, then the same class of spatial stimulus has been encountered.
Automatic image annotation (AIA) plays a vital role in dealing with the exponentially growing digital images. Image annotation helps in effective retrieval, organization, classification, auto-illustration, etc. of the image. It started in early 1990. However, in the last three decades, there has been extensive research in AIA, and various new approaches have been advanced. In this article, we review more than 200 references related to image annotation proposed in the last three decades. This paper is an attempt to discuss predominant approaches, its constraints and ways to deal. Each segment of the article exhibits a discourse to expound the finding and future research directions and their hurdles. This paper also presents performance evaluation measures with relevant and influential image annotation database.
Noise, histogram and cluster validity for Gaussian-mixtured data
1987, Pattern Recognition
In this study, a critique of the clustering methodology is carried out for the definition of a cluster, determination of the number of clusters and evaluation of heuristic partitional clustering algorithms, when the data is a noisy Gaussian Mixture. The effects of noise in determining the number of clusters and the clustering parameters are investigated. Two cluster validity criteria, namely, the likelihood information criterion and the sum of squared error are described. It is concluded that these criteria can be used as a guide in deciding on the number of valid clusters. By using the proposed sum of squared error criterion, an improvement algorithm which reduces the effect of noise on the results of heuristic clustering algorithms is described.
What the fourier transform can really bring to clustering
1984, Pattern Recognition
The general philosophy and motivations of extracting classification information from histograms have been developed in a previously published paper.⁽¹⁾ The content of the present paper deals with an optimum signal theory implementation of the same concepts by appropriate Fourier filtering of the data histogram. This strategy was developed to cluster remotely sensed multispectral imagery.
First, the theoretical foundations of clustering are explained in terms of Watanabe's ‘Ugly Duckling’ theorem on classification. A brief outline of the clustering strategy detailed in Leboucher and Lowitz is then given for the sake of clarity. In the following sections the clustering methodology is explained in terms of signal detection and signal filtering. The mathematical model is then refined and optimized using the prolate spheroidal wave function expansions of Slepian et al.
Computer simulations of this new strategy were conducted on test multispectral imagery and some clustering results are presented.
Can a local histogram really map texture information?
1983, Pattern Recognition
This paper presents a methodology to extract information from a set of r labeled counts with constant sum N called an “Organ Pipe Diagram (OPD)”. A histogram is a particular OPD with an order relation on its count labels.
As an application of this methodology, if a global image of radiometries is scanned by a window, a “module” value and a “state” can be defined for the local histogram. The corresponding maps of modules and states yield a useful local spatial information closely related to texture. The methodology is interesting in itself, as it shows how a geometry can be built-up from a set of labeled counts whose space of definition is shown to be a simplex.
Stability and dimensionality of Karhunen-Loêve multispectral image expansions
1978, Pattern Recognition
The Karhunen-Loêve (K.L.) expansion is a useful tool for the representation, pre-processing and orthogonal coding of multispectral imagery: Each spatial pixel is analysed independently as the K.L. transform is taken in the spectral dimension, i.e. along the various N spectral channels. The eigenvectors are those of the covariance matrix. The (principal) eigenimages are thus “false color” images, which can be viewed without decoding as the spatial topology is unchanged, and the higher order principal images present a strong contrast enhancement.⁽¹⁾ These principal images are also uncorrelated, a very desirable feature for many applications including clustering.⁽²⁾
The source dependency of the eigenvectors, however, introduces “instability” in the form of pronounced statistical noise on some principal images. This paper gives the results of a numerical study carried out on a 7 channel Daedalus Multispectral Scene. The uncertainties of the eigenvalues and eigenvectors are evaluated from two “drawings” of the pixels of the raw data.
Both the numerical results of the study and the direct viewing of the principal images show that three out of the seven have so much noise that they do not yield any useful information. Only the first two principal images have excellent stability, and they contain most of the total contrast variance of the scene. Two other principal images of lower order are also stable, but, contribute very little to the total contrast variance. These images carry texture information rather than homogeneous zone clustering information.

View all citing articles on Scopus

View full text