Comparison of Texture Analysis Schemes Under Nonideal Conditions

Abstract

Several recent advancements in the field of texture analysis prompt some fundamental questions. For instance, what is the true impact of these novel advancements under real-world environments? When do these novel advancements fail to perform? Which methods perform better and under what conditions? In this work, we investigate these and other issues under nonideal image acquisition environments, specifically, environments with changing conditions due to illumination variations and those caused by both affine and nonaffine transformations. We study the performance of nine popular texture analysis algorithms using three different datasets, with varying levels of difficulty. Experiments are performed on nonideal texture datasets under five different setups. We find that most state-of-the-art techniques do not perform well under these conditions. To a large extent, their performance under nonideal conditions depends critically on the nature of the textural surface. Moreover, most techniques fail to perform reliably when the number of classes in the dataset is increased significantly, over the regular-size datasets used in previous work. Multiscale features performed reasonably well against variations caused by illumination and rotation but are prone to fail under changes in scale. Surprisingly, the performance for most of the algorithms is generally stable on structured or periodic textures, even with variations in illumination or affine transformations.

Texture Description Through Histograms of Equivalent Patterns

“…As it has been set into evidence in a recent work [6], this classification strategy is particularly suitable for feature comparison purposes due to the absence of tuning parameters, easiness of implementation and other desirable asymptotic properties. A review of recent related literature indeed shows that 1-NN is most commonly adopted in evaluating the relative performance of texture analysis algorithms [16,31,54,70,115].…”

Rotation–Covariant Texture Learning Using Steerable Riesz Wavelets

“…Future work will also include the use of the steerable pyramid by Simoncelli et al [50] as an alternative to the isotropic multiscale framework used in this work. The proposed method outperforms most filterand wavelet-based approaches using the Outex_TC_00010 test suite [1], [26], [27], [29], [39], [42], [43], [51], where only few methods based on LBPs achieve a performance above 98% [14], [19], [21], [24], [25], [30], [33], sometimes with manual parameter optimization. MR8, LM and S filterbanks were reported to obtain performances of 72.57%, 51.8% and 68.61% when combined with SVMs in [16] in 2012 using the same database.…”

“…It has recently been used by several studies on texture recognition [14], [16], [19], [21], [24]- [27], [29], [30], [33], [39], [42], [51]. It consists of 24 texture classes with pronounced directional structures.…”

Feature Extraction for Image Classification and Analysis with Ant Colony Optimization Using Fuzzy Logic Approach

“…The first group comprises approaches for extracting the structural information from the images under the ideal conditions. Other group comprises of approaches that take the image under non ideal conditions [5]. In the present approach image under ideal conditions is considered for analysis.…”