Harro M. G. Stokman

Robust histogram construction from color invariants for object recognition

An effective object recognition scheme is to represent and match images on the basis of histograms derived from photometric color invariants. A drawback, however, is that certain color invariant values become very unstable in the presence of sensor noise. To suppress the effect of noise for unstable color invariant values, in this paper, histograms are computed by variable kernel density estimators. To apply variable kernel density estimation in a principled way, models are proposed for the propagation of sensor noise through color invariant variables. As a result, the associated uncertainty is obtained for each color invariant value. The associated uncertainty is used to derive the parameterization of the variable kernel for the purpose of robust histogram construction. It is empirically verified that the proposed density estimator compares favorably to traditional histogram schemes for the purpose of object recognition.

Selection and Fusion of Color Models for Image Feature Detection

The choice of a color model is of great importance for many computer vision algorithms (e.g., feature detection, object recognition, and tracking) as the chosen color model induces the equivalence classes to the actual algorithms. As there are many color models available, the inherent difficulty is how to automatically select a single color model or, alternatively, a weighted subset of color models producing the best result for a particular task. The subsequent hurdle is how to obtain a proper fusion scheme for the algorithms so that the results are combined in an optimal setting. To achieve proper color model selection and fusion of feature detection algorithms, in this paper, we propose a method that exploits nonperfect correlation between color models or feature detection algorithms derived from the principles of diversification. As a consequence, a proper balance is obtained between repeatability and distinctiveness. The result is a weighting scheme which yields maximal feature discrimination. The method is verified experimentally for three different image feature detectors. The experimental results show that the fusion method provides feature detection results having a higher discriminative power than the standard weighting scheme. Further, it is experimentally shown that the color model selection scheme provides a proper balance between color invariance (repeatability) and discriminative power (distinctiveness)

Classifying color edges in video into shadow-geometry, highlight, or material transitions

We aim at using color information to classify the physical nature of edges in video. To achieve physics-based edge classification, we first propose a novel approach to color edge detection by automatic noise-adaptive thresholding derived from sensor noise analysis. Then, we present a taxonomy on color edge types. As a result, a parameter-free edge classifier is obtained labeling color transitions into one of the following types: 1) shadow-geometry, 2) highlight edges, and 3) material edges. The proposed method is empirically verified on images showing complex real world scenes.

Classifying color transitions into shadow-geometry, illumination, highlight or material edges

We aim at using color information to classify the physical nature of a color edge: that is whether the transition is due to shadows, abrupt surface orientation changes, illumination, highlights or material changes. To achieve a physics-based edge classification, we propose a taxonomy of color invariant edges. The taxonomy is based upon the sensitivity of the various color edges with respect to different imaging dependencies i.e. shadows, object shape, shading (i.e. illumination intensity changes), highlights and material characteristics. From this taxonomy, the edge classifier is derived labeling color transitions into the following types: (1) shadow, geometry or shading edges, (2) highlight edges, (3) material edges. Experiments conducted with the edge classification technique on color and hyperspectral images show that the proposed method successfully discriminates the different edge types.

Detection and Classification of Hyper-Spectral Edges

Intensity-based edge detectors cannot distinguish whether an edge is caused by material changes, shadows, surface orientation changes or by highlights. Therefore, our aim is to classify the physical cause of an edge using hyperspectra obtained by a spectrograph. Methods are presented to detect edges in hyperspectral images. In theory, the effect of varying imaging conditions is analyzed for ”raw” hyper-spectra, for normalized hyper-spectra, and for hue computed from hyper-spectra. From this analysis, an edge classifier is derived which distinguishes hyper-spectral edges into the following types: (1) a shadow or geometry edge, (2) a highlight edge, (3) a material edge.

Selection and fusion of color models for feature detection

The choice of a color space is of great importance for many computer vision algorithms (e.g. edge detection and object recognition). It induces the equivalence classes to the actual algorithms. However, the problem is how to automatically select the color space that produces the best result for a particular task. The subsequent difficulty then is how to obtain a proper weighting scheme for the algorithms so that the results are combined in an optimal setting. To achieve proper color space selection and fusion of feature detectors, in this paper, we propose a method that exploits non-perfect correlation between the color models derived from the principles of diversification. As a consequence, the weighting scheme yields maximal color discrimination. The method is verified experimentally for two different feature detectors. The experimental results show that the model provides feature detection results having a discriminative power of 30 percent higher than the standard weighting scheme.

Photometric invariant region detection

In this paper, we concentrate on determining homogeneously colored regions invariant to surface orientation change, illumination, shadows and highlights. To this end, the influence of various well-known color models (e.g. , , , , , , , and ) are examined, in theory, for the dichromatic reflection model and, in practice, for two distinct region-based segmentation methods: the k-means clustering technique and the split&merge algorithm. Experiments are conducted on color images taken from colored objects in real-world scenes. On the basis of the theoretical and experimental results it is concluded that , , , , and all detect regions invariant to a change in surface orientation, viewpoint of the camera, and illumination intensity. Furthermore, and also detect regions independent of highlights. , , , , ,a nd provide segmentation results which are all sensitive to surface orientation and illumination intensity as well as color models incorporating brightness into their systems: in , in ,a nd in .

Robust Photometric Invariant Region Detection in Multispectral Images

Our aim is to detect photometric invariant regions in multispectral images robust against sensor noise. Therefore, different polar angle representations of a spectrum are examined for invariance using the dichromatic reflection model. These invariant representations take advantage of white balancing. Based on the camera sensitivity, a theoretical expression is obtained of the certainty associated with the polar angular representations under the influence of noise. The expression is employed by the segmentation technique to ensure robustness against sensor noise.

Colour Constancy from Hyper-Spectral Data.

This paper aims for color constant identification of object colors through the analysis of spectral color data. New computational color models are proposed which are not only invariant to illumination variations (color constancy) but also robust to a change in viewpoint and object geometry (color invariance). Color constancy and invariance is achieved by spectral imaging using a white reference, and based on color ratio’s (without a white reference). From the theoretical and experimental results it is concluded that the proposed computational methods for color constancy and invariance are highly robust to a change in SPD of the light source as well as a change in the pose of the object.

Recovering the Spectral Distribution of the Illumination from Spectral Data by Highlight Analysis

The problem of color constancy for discounting illumination color to obtain the apparent color of the object has been the topic of much research in computer vision. By assuming the neutral interface reflection and dichromatic reflection with highlights (i.e. highlights have the same color as the illuminant) various methods have been proposed aiming at recovering the illuminant color from color highlight analysis. In general, these methods are based on three color stimuli to approximate color. In this contribution, we estimate the spectral distribution from surface reflection using spectral information obtained by a spectrograph. The imaging spectrograph provides a spectral range at each pixel covering the visible wavelength range. Our method differ from existing methods by using a robust clustering technique to obtain the body and surface components in a multi-spectral space. These components determine the direction of the illumination spectral color. Then, we recover the illumination spectral power distribution by using principal component analysis for all wavelengths. To obtain the most reliable estimate of the spectral power distribution of the illuminant, all possible combinations of wavelengths are used to generate the optimal averaged estimation of the spectral power distribution of the scene illuminant. Our method is restricted to images containing a substantial amount of body reflection and highlights.