This paper addresses the problem of segmenting an image by texture. Specifically, we are concerned with estimating the trajectory of the boundary between two regions characterized by different two-dimensional autocorrelation functions. An algorithm is developed which is an approximation to a maximum-likelihood estimator based on the assumption of Gaussian random fields with known mean and covariance. Preliminary experimental results are given.

A maximum-likelihood approach to image segmentation by texture

In this study we have applied Itakura-Saito (IS) type spectral distortion measures for classifying segments of digitized images using the multidimensional multichannel linear prediction (MLPC) theory. ItakuraSaito type spectral distortion measures have been successfully applied in the fields of speech coding, speech recognition and speaker identification and verification. But there has been only one such study to apply the gain-normalized Itakura-Saito distortion measure for classification of arbitrarily shaped image textures. Maragos et al. [l] have demonstrated that textures can be classifed by two-dimensional linear predictive models under a spectral distortion measure. We have extended this case to the more difficult, yet much more meaningful, multichannel linear predictive modeling [3] of arbitrarily shaped image textures. All three forms of the Itakura-Saito distortion measure [4,5], gain sensitive (GS), gain optimized (GO), and gain normalized (GN), have been extended to the multichannel linear prediction case. We have successfully used them in the template design and the classification modes.

https://ieeexplore.ieee.org/iel2/3982/11471/00523357.pdf

Applications of itakura-saito type spectral distortion measures to image analysis and classification

This paper presents a study on texture segmentation based on a two-dimensional linear prediction method. It begins with brief summary of the principle that the division of an image which gives the minimum of the total sum of final prediction errors over the whole image corresponds to the true segmentation. Then, the practical computation procedure is given. Finally, experiments of the application of the principle are demonstrated. The results indicate that arbitrarily-shaped texture regions can be well identified.

Partitioning of texture image using two-dimensional linear prediction model

A Principle of Texture Segmentation Based on Linear Prediction Model

This paper reports on a preliminary study of applying single-channel (scalar) and multichannel (vector) 2-D linear prediction to color image modeling and coding. Also, the novel idea of a multi-input single-output 2-D ADPCM coder is introduced. The results of this study indicate that texture information in multispectral images can be represented by linear prediction coefficients or matrices, where as the prediction error conveys edge-information. Moreover, by using a single-channel edge-information we obtained, from original color images of 24 bits/pixel, reconstructed images of good quality at information rates of 1 bit/pixel or less.

Multichannel linear predictive coding of color images

This paper is concerned with the use of 2-D linear prediction for image segmentation. It begins with a brief summary of the mathematics involved in 2-D linear predictive analysis of arbitrarily-shaped regions. Then, it introduces a 2-D LPC distance measure based on the error residual of 2-D linear prediction. Finally, it describes how the above results can be applied to image segmentation using a simple cluster seeking algorithm. The results indicate that arbitrarily-shaped image regions can be well identified and clustered using as features their 2-D LPC parameters.

R. Schafer

Papers

Two-dimensional linear predictive analysis of arbitrarily-shaped regions