Computing illumination-invariant descriptors of spatially filtered color image regions

Optimal spatial filter selection for illumination-invariant color texture discrimination

Color textures contain a large amount of spectral and spatial structure that can be exploited for recognition. Recent work has demonstrated that spatial filters offer a convenient means of extracting illumination-invariant spatial information from a color image. In this paper, we address the problem of deriving optimal filters for illumination-invariant color texture discrimination. Color textures are represented by a set of illumination-invariant features that characterize the color distribution of a filtered image region. Similar features have been used in previous studies. Given a pair of color textures, we derive a spatial filter that maximizes the distance between these textures in feature space. We provide a method for using the pairwise result to obtain a filter that maximizes discriminability among multiple classes. A set of experiments on a database of deterministic and random color textures obtained under different illumination conditions demonstrates the improved discriminatory power achieved by using an optimized filter.

A methodology for extracting objective color from images

We present a methodology for correcting color images taken in practical indoor environments, such as laboratories, factories, and studios, that explicitly models illuminant location, surface reflectance and geometry, and camera responsivity. We explicitly model surfaces by taking our color images with corresponding registered three-dimensional (3-D) range images, which provide surface orientation and location information for every point in the scene. We automatically detect regions where color correction should not be applied, such as specularities, coarse texture regions, and jump edges. This correction results in objective color measures of the imaged surfaces. This kind of integrated, comprehensive system of color correction has not existed until now. i.e., it is the first of its kind in computer vision. We demonstrate results of applying this methodology to real images for applications in photorealistic rerendering, skin lesion detection, burn scar color measurement, and general color image enhancement. We also have tested the method under different lighting configurations and with three different range scanners.

Spatial template extraction for image retrieval by region matching

This paper presents a template and its relation extraction and estimation (TREE) algorithm for indexing images from picture libraries with more semantics-sensitive meanings. This algorithm can learn the commonality of visual concepts from multiple images to give a middle-level understanding about image contents. In this approach, each image is represented by a set of templates and their spatial relations as keys to capture the essence of this image. Each template is characterized by a set of dominant regions, which reflect different appearances of an object at different conditions and can be obtained by the template extraction and analysis (TEA) algorithm through region matching. The spatial template relation extraction and measurement (STREAM) algorithm is then proposed for obtaining the spatial relations between these templates. Due to the nature of a template, which can represent object's appearances at different conditions, the proposed approach owns better capabilities and flexibilities to capture image contents than traditional region-based methods. In addition, through maintaining the spatial layout of images, the semantic meanings of the query images can be extracted and lead to significant improvements in the accuracy of image retrieval. Since no time-consuming optimization process is involved, the proposed method learns the visual concepts extremely fast. Experimental results are provided to prove the superiority of the proposed method.

Using color histogram normalization for recovering chromatic illumination-changed images

We propose a novel image-recovery method using the covariance matrix of the red-green-blue (R-G-B) color histogram and tensor theories. The image-recovery method is called the color histogram normalization algorithm. It is known that the color histograms of an image taken under varied illuminations are related by a general affine transformation of the R-G-B coordinates when the illumination is changed. We propose a simplified affine model for application with illumination variation. This simplified affine model considers the effects of only three basic forms of distortion: translation, scaling, and rotation. According to this principle, we can estimate the affine transformation matrix necessary to recover images whose color distributions are varied as a result of illumination changes. We compare the normalized color histogram of the standard image with that of the tested image. By performing some operations of simple linear algebra, we can estimate the matrix of the affine transformation between two images under different illuminations. To demonstrate the performance of the proposed algorithm, we divide the experiments into two parts: computer-simulated images and real images corresponding to illumination changes. Simulation results show that the proposed algorithm is effective for both types of images. We also explain the noise-sensitive skew-rotation estimation that exists in the general affine model and demonstrate that the proposed simplified affine model without the use of skew rotation is better than the general affine model for such applications.

Model acquisition and invariant tracking of unknown materials in hyperspectral images

We consider the problem of acquiring models for unknown materials in airborne 0.4-2.5 microm hyperspectral imagery and using these models to identify the unknown materials in image data obtained under significantly different conditions. The material models are generated with use of an airborne sensor spectrum measured under unknown conditions and a physical model for spectral variability. For computational efficiency, the material models are represented by using low-dimensional spectral subspaces. We demonstrate the effectiveness of the material models by using a set of material tracking experiments in HYDICE images acquired in forest and desert environments over widely varying conditions. We show that techniques based on the new representation significantly outperform methods based on direct spectral matching.

Hierarchical color image region segmentation for content-based image retrieval system

In this work, we propose a model of a content-based image retrieval system by using the new idea of combining a color segmentation with relationship trees and a corresponding tree-matching method. We retain the hierarchical relationship of the regions in an image during segmentation. Using the information of the relationships and features of the regions, we can represent the desired objects in images more accurately. In retrieval, we compare not only region features but also region relationships.