Classification Of Natural Textures Research Articles

Classification of Natural Textures using Rule Based Rank Matrix

This paper derives a new frame work for the classification of natural textures based on gradient rank vectors derived on a 2 X 2 grid. This paper identified the ambiguity in deriving ranks when two or more positions of the grid possess the same value. To attend this ambiguity and without increasing the total number of rank vectors on d positions this paper derived a rule based rank vector frame work. This paper replaced the 2 X 2 grid with the column position of the Rule based Rank Word Matrix (RRWM). The range of column positions will be d! for d positions. This paper then divides RRW texture image, into a 3 X 3 grid and derives cross and diagonal rule based rank words. From this, the present paper derived Rule based Rank Word-Cross and Diagonal Texture Matrix (RRW-CDTM) and derives GLCM features for effective texture classification. The experimental results on various texture databases revels the classification accuracy of the proposed method. The proposed method is compared with the state of art local based approaches.

A Neuro-Fuzzy based System for Classification of Natural Textures

A statistical approach based on the coordinated clusters representation of images is used for classification and recognition of textured images. In this paper, two issues are being addressed; one is the extraction of texture features from the fuzzy texture spectrum in the chromatic and achromatic domains from each colour component histogram of natural texture images and the second issue is the concept of a fusion of multiple classifiers. The implementation of an advanced neuro-fuzzy learning scheme has been also adopted in this paper. The results of classification tests show the high performance of the proposed method that may have industrial application for texture classification, when compared with other works.

Robust color texture descriptor for material recognition

This paper addresses the task of material and natural texture classification. We propose a new discriminant color texture descriptor based on local pattern encoding scheme using local maximum sum and difference histograms. This descriptor aims to improve the robustness of the sum and difference histograms (SDH) operator to noise and low quality images by using adaptive values of the pixels instead of their exact values. We also enhance the time and memory efficiency as well as the robustness to scale and rotation variations by rectifying the formula used to compute the SDH. Finally, we use three different encoding schemes in order to incorporate both color and texture information into the final descriptor. The proposed approach is evaluated on six popular and challenging datasets: Outex-TC13, New-BarkTex, FMD, KTH-TIPS2b, Outex-TC30 and Outex-TC32 databases. The experimental results show that the introduced operator significantly outperforms the state-of-the-art methods and enhance the performance of the basic SDH.

A multi-scale supervised orientational invariant neural architecture for natural texture classification

A multi-scale supervised neural architecture, called Multi-Scale SOON, is proposed for natural texture classification. This architecture recognizes the input textured image through a hierarchical categorization structure in multiple scales. This process consists of three sequential phases: a multi-scale feature extraction, a scale prototype pattern generation, and a multi-scale prototype fusion pattern classification. First phase extracts scale textural features using the Gabor filtering. Then, a hierarchical categorization shapes the classification. First categorization level generates the scale prototypes and an upper level categorizes the prototypes fusion. Three increasing complexity tests over the well-known Brodatz database are performed in order to quantify the Multi-Scale SOON behavior. The comparison to other standout methods proves Multi-Scale SOON behavior to be satisfactory. The tests, including the entire texture album, show the stability and robustness of the Multi-Scale SOON response.

Classification of natural textures in echolocation.

Through echolocation, a bat can perceive not only the position of an object in the dark; it can also recognize its 3D structure. A tree, however, is a very complex object; it has thousands of reflective surfaces that result in a chaotic acoustic image of the tree. Technically, the acoustic image of an object is its impulse response (IR), i.e., the sum of the reflections recorded when the object is ensonified with an acoustic impulse. The extraction of the acoustic IR from the ultrasonic echo and the detailed IR analysis underlies the bats' extraordinary object-recognition capabilities. Here, a phantom-object playback experiment is developed to demonstrate that the bat Phyllostomus discolor can evaluate a statistical property of chaotic IRs, the IR roughness. The IRs of the phantom objects consisted of up to 4,000 stochastically distributed reflections. It is shown that P. discolor spontaneously classifies echoes generated with these IRs according to IR roughness. This capability enables the bats to evaluate complex natural textures, such as foliage types, in a meaningful manner. The present behavioral results and their simulations in a computer model of the bats' ascending auditory system indicate the involvement of modulation-sensitive neurons in echo analysis.

A self-organizing neural system for learning to recognize textured scenes

A self-organizing ARTEX model is developed to categorize and classify textured image regions. ARTEX specializes the FACADE model of how the visual cortex sees, and the ART model of how temporal and prefrontal cortices interact with the hippocampal system to learn visual recognition categories and their names. FACADE processing generates a vector of boundary and surface properties, notably texture and brightness properties, by utilizing multi-scale filtering, competition, and diffusive filling-in. Its context-sensitive local measures of textured scenes can be used to recognize scenic properties that gradually change across space, as well as abrupt texture boundaries. ART incrementally learns recognition categories that classify FACADE output vectors, class names of these categories, and their probabilities. Top-down expectations within ART encode learned prototypes that pay attention to expected visual features. When novel visual information creates a poor match with the best existing category prototype, a memory search selects a new category with which classify the novel data. ARTEX is compared with psychophysical data, and is bench marked on classification of natural textures and synthetic aperture radar images. It outperforms state-of-the-art systems that use rule-based, backpropagation, and K-nearest neighbor classifiers.

Biosonar in a textured world

Capabilities of bats to analyze spectral profiles have been demonstrated by several researchers. However, suggestions as to the informational content of the biologically accessible features in terms of the echo-generating process are not yet entirely convincing. Invoking a general analogy to visual color perception does not provide an operational definition of the hypothetical perceptual mechanism. The proposed mechanisms are mostly restricted to a scenario, where the spacing of two reflectors may be determined via the resulting comb-filter transfer function. The generality of this concept is curtailed by most natural surfaces constituting aggregates of multiple reflecting facets with a pronounced random component to their arrangement. Classification of natural textures is conceived to be a pivotal capability which may underly performance in several tasks probably performed by the animals, e.g., landmark identification and control of scanning movement. In order to understand how the demands of texture classification relate to the key features of biological sonar systems, the following steps are taken: Starting from a database of textures typical of bat’s habitats (i.e., foliage), the implications of two paramount attributes of biological sonar systems are studied: sensor mobility and a joint time-frequency representation encoded in spike patterns.

Fractal-based classification of natural textures

Texture classification is an important first step in image segmentation and image recognition. The classification algorithm must be able to overcome distortions, such as scale, aspect and rotation changes in the input texture. In this paper, a new fractal model for texture classification is presented. The model is based on fractional Brownian motion (FBM). It is also shown that this model is invariant to changes in incident light; empirical results are also given. The isotropic nature of Brownian motion is particularly useful for outdoor applications, where the viewing direction may change. Classification results of this model are presented; comparisons with other texture measurement models indicate that the incremental FBM (IFBM) model has better performance for the samples tested.

Texture description using fractal and energy features

The fractal dimension of a texture has been used in the past as a segmentation feature, but since it cannot sufficiently describe enough textural characteristics, additional features are needed. In this paper we demonstrate that by combining the fractal dimension with a simple textural energy measure, a significant performance improvement is achieved compared to using each feature alone. The fractal dimension is computed using an efficient method that is also more accurate than most other popular methods, and the textural energy is easily computed using convolutional masks. Segmentation and classification of natural textures based on these two features is presented and the effect of additive noise is considered.

Comments on "Classification of natural textures by means of two-dimensional orthogonal masks" by P. Cohen, V. Lacasse and C.T. DeDinh

The commenter discusses a texture classification technique by Cohen et al. described in the above-titled correspondence (see ibid., vol.37, no.1, p.125, 1989) that uses features derived from a set of four orthogonal masks applied to a 2*2 local neighborhood. The technique is an extension of the sum and difference histograms method previously published by the commenter. He points out that he has published a technique that is more general and subsumes the results of Cohen et al. and of his own earlier work. He also points out a mathematical error in the work by Cohen et al., which from a practical point of view, it is likely to have only minor effects.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Classification of natural textures by means of two-dimensional orthogonal masks

An approach to texture classification in which each local neighborhood is transformed reversibly into a minimal set of uncorrelated features is described. These features are found to represent local average, as well as first- and second-order derivative information of the texture. Comparison to other techniques of similar complexity, using identical classification procedures, shows the superiority of the proposed approach. Moreover, this approach leads directly to a real-time parallel implementation. >