An extensive analysis of various texture feature extractors to detect Diabetes Mellitus using facial specific regions

INTRODUCTION

Researchers have recently discovered that Diabetes Mellitus can be detected through non-invasive computerized method. However, the focus has been on facial block color features. In this paper, we extensively study the effects of texture features extracted from facial specific regions at detecting Diabetes Mellitus using eight texture extractors.

MATERIALS AND METHODS

The eight methods are from four texture feature families: (1) statistical texture feature family: Image Gray-scale Histogram, Gray-level Co-occurance Matrix, and Local Binary Pattern, (2) structural texture feature family: Voronoi Tessellation, (3) signal processing based texture feature family: Gaussian, Steerable, and Gabor filters, and (4) model based texture feature family: Markov Random Field. In order to determine the most appropriate extractor with optimal parameter(s), various parameter(s) of each extractor are experimented. For each extractor, the same dataset (284 Diabetes Mellitus and 231 Healthy samples), classifiers (k-Nearest Neighbors and Support Vector Machines), and validation method (10-fold cross validation) are used.

RESULTS

According to the experiments, the first and third families achieved a better outcome at detecting Diabetes Mellitus than the other two.

CONCLUSIONS

The best texture feature extractor for Diabetes Mellitus detection is the Image Gray-scale Histogram with bin number=256, obtaining an accuracy of 99.02%, a sensitivity of 99.64%, and a specificity of 98.26% by using SVM.

Edge-Projected Integration of Image and Model Cues for Robust Model-Based Object Tracking

A real-world limitation of visual servoing approaches is the sensitivity of visual tracking to varying ambient conditions and background clutter. The authors present a model-based vision framework to improve the robustness of edge-based feature tracking. Lines and ellipses are tracked using edge-projected integration of cues (EPIC). EPIC uses cues in regions delineated by edges that are defined by observed edgels and a priori knowledge from a wire-frame model of the object. The edgels are then used for a robust fit of the feature geometry, but at times this results in multiple feature candidates. A final validation step uses the model topology to select the most likely feature candidates. EPIC is suited for real-time operation. Experiments demonstrate operation at frame rate. Navigating a walking robot through an industrial environment shows the robustness to varying lighting conditions. Tracking objects over varying backgrounds indicates robustness to clutter.

A hierarchical approach to feature extraction and grouping

In this paper, the problem of extracting and grouping image features from complex scenes is solved by a hierarchical approach based on two main processes: voting and clustering. Voting is performed for assigning a score to both global and local features. The score represents the evidential support provided by input data for the presence of a feature. Clustering aims at individuating a minimal set of significant local features by grouping together simpler correlated observations. It is based on a spatial relation between simple observations on a fixed level, i.e., the definition of a distance in an appropriate space. As the multilevel structure of the system implies that input data for an intermediate level are outputs of the lower level, voting can be seen as a functional representation of the "part-of" relation between features at different abstraction levels. The proposed approach has been tested on both synthetic and real images and compared with other existing feature grouping methods.

Learning to Segment Images Using Dynamic Feature Binding

Despite the fact that complex visual scenes contain multiple, overlapping objects, people perform object recognition with ease and accuracy. One operation that facilitates recognition is an early segmentation process in which features of objects are grouped and labeled according to which object they belong. Current computational systems that perform this operation are based on predefined grouping heuristics. We describe a system called MAGIC that learns how to group features based on a set of presegmented examples. In many cases, MAGIC discovers grouping heuristics similar to those previously proposed, but it also has the capability of finding nonintuitive structural regularities in images. Grouping is performed by a relaxation network that attempts to dynamically bind related features. Features transmit a complex-valued signal (amplitude and phase) to one another; binding can thus be represented by phase locking related features. MAGIC's training procedure is a generalization of recurrent backpropagation to complex-valued units.