Niraj P. Doshi

A comparative analysis of local binary pattern texture classification

Texture recognition is an important aspect of many computer vision applications. Local binary pattern (LBP) based texture algorithms have gained significant popularity in recent years and have been shown to be useful for a variety of tasks. While over the years a variety of LBP algorithms have been introduced in the literature, what is missing is a comprehensive evaluation of their performance. In this paper, we fill this gap and benchmark 37 texture descriptors based on 15 LBP variants for texture classification against common standard datasets of textures including those captured at different rotation angles and under different illumination conditions. Overall, LBP variance (LBPV) is found to give the best texture classification performance.

Enhancement of nailfold capillaroscopy images

Nailfold capillaroscopy (NC) is a non-invasive imaging technique employed to assess the condition of blood capillaries in the nailfold. It is particularly useful for early detection of scleroderma spectrum disorders and evaluation of Raynauds phenomenon. While diagnosis based on NC is typically performed by manual inspection, computerised nailfold capillaroscopy can help to reduce the inherent ambiguity present in human judgement while greatly reducing the time for diagnosis. A crucial step in automated image analysis not only of NC images but of any kind of medical images is an image enhancement process. In this paper, we evaluate the performance of six image enhancement/noise removal techniques for NC images, as a pre-cursor to edge detection aimed at identifying capillaries. Results on a variety of NC images show that bilateral filters and enhancers provide the best image quality for subsequent capillary detection.

An evaluation of image enhancement techniques for capillary imaging

Nailfold capillaroscopy (NC) is a non-invasive imaging technique employed to assess the condition of blood capillaries in the nailfold, and is known to be effective particularly for early detection of scleroderma spectrum disorders and evaluation of Raynauds phenomenon. Manual inspection of NC images can be aided by a computerised system avoiding the inherent ambiguity present in human judgment and improving the diagnosis speed. For such an automated analysis, image enhancement is typically the first step. The performance of an employed image enhancement algorithm is crucial due to its influence on subsequent algorithms. In this paper, we aim to provide a comparative evaluation of different image enhancement techniques for nailfold capillaroscopy (NC) images. In particular, we evaluate the performance of ten image enhancement/noise removal techniques for NC images as a pre-cursor to edge detection aimed at identifying capillaries. Results on a variety of NC images show that bilateral filters and enhancers, non local means and anisotropic diffusion provide the best image quality for this task.

Nailfold capillaroscopy pattern recognition using texture analysis

Nailfold capillaroscopy (NC) is a non-invasive imaging technique employed to assess the condition of blood capillaries in the nailfold. It is particularly useful for early detection of scleroderma spectrum disorders and evaluation of Raynauds phenomenon. While diagnosis based on NC is typically performed by manual inspection, computerised nailfold capillaroscopy can help to reduce the inherent ambiguity present in human judgement while greatly reducing the time for diagnosis. Diagnosis of NC images involves the recognition of early, active and late patterns, also known as NC patterns or scleroderma (SD) patterns, in the images. In this paper, we propose a holistic method to classify NC images in these well known patterns. In particular, we employ texture analysis to describe the underlying patterns, coupled with a classifier to first identify patterns in fingers, and then, through a voting strategy, reach a decision for a patient. Experimental results on a set of NC images with known ground truth demonstrate the efficacy of our approach.

Improved LBP texture classification using ensemble learning

Texture analysis and classification play an important role in many multimedia and computer vision applications. Local binary patterns (LBP) form a simple yet powerful texture descriptor characterising local neighbourhood properties, and consequently LBP variants are widely employed. In this paper, we demonstrate that through appropriate construction of a multiple classifier system, improved texture classification based on LBP features is possible. In particular, we employ a classifier ensemble where each classifier (a support vector machine) is trained in conjunction with a different feature selection method. The ensemble is then pruned based on a diversity measure, and the remaining models are combined using a neural fuser. Experimental results, obtained on Outex benchmark datasets and employing four LBP variants, confirm that our proposed approach leads to statistically significantly improved texture classification.

Texture Classification Using Multi-dimensional LBP Variance

Texture classification is an important task for a variety of computer vision applications. A successful group of texture algorithms based on local neighbourhood descriptors and known as LBP (local binary patterns) has been shown to provide good and robust discriminative power, and is typically applied in a rotation invariant form and calculated at multiple resolutions. Local contrast information can be integrated into the LBP histogram generation by using the variance as weights for LBP, leading to LBP variance (LBPV) texture features. Multi-scale LBPV histograms are obtained by concatenating the individual one-dimensional histograms derived from each scale. In this paper, we show that by calculating a multi-dimensional LBP variance (MD-LBPV) histogram improved texture classification can be achieved. We confirm this based on extensive experiments on several Outex benchmark datasets.

Automatic Classification of HEp-2 Cells Using Multi-dimensional Local Binary Patterns

Indirect immunofluorescence imaging is a fundamental technique used for detecting antinuclear antibodies in HEp-2 cells. This is particularly useful for the diagnosis of autoimmune diseases and other important pathological conditions involving the immune system. HEp-2 cells can be categorised into six groups: homogeneous, fine speckled, coarse speckled, nucleolar, cytoplasmic, and Centro mere cells, which give indications of different autoimmune diseases. This categorisation is typically performed through manual evaluation which is time consuming and subjective. In this paper, we propose a method for automatic classification of HEp-2 cells using local binary pattern (LBP) based texture descriptors. LBP is a simple yet powerful texture algorithm which encodes the relationship of pixels to their local neighbourhood. In our approach, we utilise multi-dimensional LBP (MD-LBP) histograms, which record multi-scale texture information while maintaining the relationships between the scales, and perform classification using support vector machines. We demonstrate our algorithm to work well on a dataset of 721 cell images, giving a correct classification rate exceeding 95%, which is particularly impressive as it is based solely on a single type of image feature.

An Improved Binarisation Algorithm for Nailfold Capillary Skeleton Extraction

Nailfold capillaroscopy (NC) is a non-invasive imaging technique employed to assess the condition of blood capillaries in the nail fold, and is routinely used for the detection of scleroderma spectral disorders, Raynauds phenomenon and other connective tissue diseases. While NC image evaluation is typically performed through manual inspection by an expert, computer-aided approaches of capillary inspection can reduce the time required for diagnosis. The aim of NC image analysis is usually to extract the skeletons of the capillaries present in the image which form the basis of further analysis for diagnosis. In this paper, we propose an improved binarisation technique for NC image analysis that addresses the challenge of non-uniform background by employing a Difference-of-Gaussian approach before thresholding, coupled with a post-processing stage to remove smaller image artefacts. Based on two previously published NC skeletonisation algorithms, we demonstrate that our technique leads to significantly better skeleton extraction on different types of NC images.

Texture classification using compact multi-dimensional local binary pattern descriptors

Texture analysis and classification plays an important role in many computer vision systems and applications. Local binary patterns (LBP) form a simple yet powerful texture descriptor characterising local neighbourhood properties, which, due to its effectiveness and robustness, is widely used. LBP descriptors can also be recorded at different radii leading to multiscale features. While in conventional LBP, this information is recorded, in form of a histogram, separately for each of the scales, it was shown that a multi-dimensional feature representation removes some ambiguity and leads to better texture classification. However, these multi-dimensional LBP (MD-LBP) histograms also make rather large feature descriptors which limits their practical use. In this paper, we show that we can effectively compactify the information contained in MD-LBP histograms, and show, through extensive experiments on seven Outex datasets, that with the same feature length as the original LBP method we are able to obtain clearly improved texture classification which closely matches that achieved by the full MD-LBP descriptor.

Scleroderma capillary pattern identification using texture descriptors and ensemble classification

Various connective tissue diseases lead to morphological alternations of blood capillaries. Consequently, observation of the capillaries at the finger nailfold - nailfold capillaroscopy (NC) - is a standard method for diagnosing diseases such as scleroderma or Raynauds phenomenon. This is typically performed through manual inspection by an expert to lead to a determination of one of the established NC scleroderma patterns (early, active, and late). In this paper, we present an automated method of analysing nailfold capillaroscopy images and categorising them into NC patterns. For this purpose, we extract a carefully chosen set of texture features from the images and employ an ensemble classification approach to arrive at decisions for each captured finger which are then aggregated to form a diagnosis for the patient. Experimental results on a set of 60 NC images from 16 subjects demonstrate the accuracy and usefulness of our presented approach.