Search

In this paper, we applied texture analysis to evaluate cerebral degeneration in amyotrophic lateral sclerosis (ALS). Two well-known methods, the gray level co-occurrence matrix (GLCM) and the gray level aura matrix (GLAM) were employed to extract texture features from routine T1 and T2 MR images. Texture features were analyzed by statistical inference, support vector machine to determine classification rate, and receiver operator characteristic curve (ROC) analysis. Twenty control subjects (average age = 56.8±12.4) and 19 ALS patients (average age = 56.7±13.7) were recruited for the study. Texture features were statistically different in ALS compared to controls (p< 0.0001 for T1, and p< 0.00001 for T2) and provided a classification rate with more than 76%, and 82% accuracy on T1 and T2 weighted images, respectively. ROC analysis yielded area under the curves approaching 0.93, and a maximal sensitivity and specificity of 100% and 95%, respectively. Texture features moderately correlated with parenchymal brain volume suggesting that atrophy partially accounted for the texture results; however, texture features had a superior classification rate indicating that other cerebral pathology due to ALS besides atrophy was being captured by texture analysis. We conclude that texture analysis shows promise as a quantitative biomarker to study cerebral degeneration in ALS. To our best knowledge, this is the first study to apply the GLAM as a texture method to medical image analysis, showing that it provides features superior (or at least comparable) to the well known GLCM features. | TRID-ID TR14-01

This paper presents a novel, simple, yet powerful texture analysis method inspired by the well-known Local Binary Patterns (LBP) method called the Local Frequency Descriptors (LFD). Like LBP, the proposed method is invariant to rotation and linear changes of illumination; however,it does not suffer from the limitations of LBP such as exponential growth of features with an increment in the number of neighbors. The experimental results on the Outex and CUReT datasets show that the proposed LFD method outperforms state-of-the-art texture analysis methods. In addition, LFD is very robust to noise and can improve LBP results up to 50% in extremely noisy conditions. In this paper, we discuss different aspects of the LFD and explain how it addresses the main limitations of LBP and of its variants. | TRID-ID TR12-03

Technical report TR11-07. In this paper, we present a structured light method to recover depth maps. Contrary to most temporal coding methods which require projecting a series of patterns, our method needs one color pattern only. Unlike most spatial coding methods which establish correspondence only along the edges of the captured images, our method produces a dense set of correspondence. Our method is built upon an important observation that a Gaussian blurred De Bruijn pattern preserves the desirable windowed uniqueness property. A Gaussian blurred De Bruijn pattern is used so that the color of every illuminated pixel is used to its fullest advantage. The simulated experiments show that the proposed method establishes a correspondence set whose density and accuracy are close to that of using temporal coding methods. We also demonstrate the robustness of our approach by applying it to several real-world datasets. | TRID-ID TR11-07

Proceedings of Graphics Interface 2001, Ottawa, Ontario, Canada, Canada, 7 - 9 June 2001, 71-80, In this paper, a novel concept, rayset, is proposed. A new image based representation, object centered concentric mosaics (OCCM), is derived based on this concept. The rayset is a parametric function, which consists of two mapping relations. The first mapping relation maps from a parameter space to the ray space. The second one maps from the parameter space to the attribute space. We show that different image-based scene representations can all be cast as different kinds of raysets, and image-based rendering approaches can be regarded as attempts to sample and reconstruct the scene using different raysets. A collection of OCCM is a 3-D rayset, which can be used to represent an object. The storage size for OCCM is about the same as an animation sequence generated with a virtual camera rotated around the object. However, comparing with such an animation sequence, OCCM provide a much richer experience because the user can move back and forth freely in the scene and observe the changes in parallax.