Image category recognition is important to access visual information on the level of objects and scene types. So far, intensity-based descriptors have been widely used for feature extraction at salient points. To increase illumination invariance and discriminative power, color descriptors have been proposed. Because many different descriptors exist, a structured overview is required of color invariant descriptors in the context of image category recognition. Therefore, this paper studies the invariance properties and the distinctiveness of color descriptors (software to compute the color descriptors from this paper is available from http://www.colordescriptors.com) in a structured way. The analytical invariance properties of color descriptors are explored, using a taxonomy based on invariance properties with respect to photometric transformations, and tested experimentally using a data set with known illumination conditions. In addition, the distinctiveness of color descriptors is assessed experimentally using two benchmarks, one from the image domain and one from the video domain. From the theoretical and experimental results, it can be derived that invariance to light intensity changes and light color changes affects category recognition. The results further reveal that, for light intensity shifts, the usefulness of invariance is category-specific. Overall, when choosing a single descriptor and no prior knowledge about the data set and object and scene categories is available, the OpponentSIFT is recommended. Furthermore, a combined set of color descriptors outperforms intensity-based SIFT and improves category recognition by 8 percent on the PASCAL VOC 2007 and by 7 percent on the Mediamill Challenge.

Evaluating Color Descriptors for Object and Scene Recognition

A scheme is developed for classifying the types of motion perceived by a humanlike robot. It is assumed that the robot receives visual images of the scene using a perspective system model. Equations, theorems, concepts, clues, etc., relating the objects, their positions, and their motion to their images on the focal plane are presented. >

http://ieeexplore.ieee.org/iel2/815/3148/00100651.pdf

Robot vision

The Foundations of Statistics By Prof. Leonard J. Savage. (Wiley Publications in Statistics.) Pp. xv + 294. (New York; John Wiley and Sons, Inc.; London: Chapman and Hall, Ltd., 1954.) 48s. net.

Probability and Statistical Inference

https://www.cse.sc.edu/~songwang/document/prl12.pdf

CrackTree: Automatic crack detection from pavement images

Computational color constancy is a fundamental prerequisite for many computer vision applications. This paper presents a survey of many recent developments and state-of-the-art methods. Several criteria are proposed that are used to assess the approaches. A taxonomy of existing algorithms is proposed and methods are separated in three groups: static methods, gamut-based methods, and learning-based methods. Further, the experimental setup is discussed including an overview of publicly available datasets. Finally, various freely available methods, of which some are considered to be state of the art, are evaluated on two datasets.

Computational Color Constancy: Survey and Experiments

This paper is concerned with the derivation of a progression of shadow-free image representations. First, we show that adopting certain assumptions about lights and cameras leads to a 1D, gray-scale image representation which is illuminant invariant at each image pixel. We show that as a consequence, images represented in this form are shadow-free. We then extend this 1D representation to an equivalent 2D, chromaticity representation. We show that in this 2D representation, it is possible to relight all the image pixels in the same way, effectively deriving a 2D image representation which is additionally shadow-free. Finally, we show how to recover a 3D, full color shadow-free image representation by first (with the help of the 2D representation) identifying shadow edges. We then remove shadow edges from the edge-map of the original image by edge in-painting and we propose a method to reintegrate this thresholded edge map, thus deriving the sought-after 3D shadow-free image.

/pdf/on-the-removal-of-shadows-from-images-20rcnm8x1p.pdf

On the removal of shadows from images

We present a re-evaluation of previous experimental data for five different colour constancy algorithms, based on experiments on real and synthetic images. Our work is motivated by the observation that previous analysis of algorithm performance is flawed because it uses inappropriate statistical measures of performance. We discuss these flaws in detail and suggest more appropriate statistical tests. We show that using these tests conclusions as to the relative performance of algorithms are significantly changed as compared to the original analysis of the data. In particular we conclude that the performance of two algorithms: Gamut mapping and color by correlation is statistically equivalent and significantly better than the three other algorithms tested (Max-RGB and two versions of Grey-world).

/pdf/re-evaluating-colour-constancy-algorithms-4j502y45ew.pdf

Re-evaluating colour constancy algorithms

Gamut mapping colour constancy algorithms attempt to map image RGBs captured under an unknown light to corresponding RGBs under a reference light so as to render images colour constant. While the approach often works well, for a significant number of real images the algorithm delivers a null solution. We show that the null solution problem arises because of a failure of the diagonal model of illumination change on which the algorithm is based. We address the problem by proposing a new diagonal-offset model which has 6 rather than 3 parameters and which is able therefore to deal with a wider range of imaging conditions. Based on this model we formulate a convex programming solution to colour constancy and we show (by testing on real images) that the new algorithm is robust to the failures of the diagonal model and is capable of delivering very good colour constancy.

Convex programming colour constancy with a diagonal-offset model

In this paper we propose that two images are captured of every scene: a normal image and an image captured where a coloured filter is placed in front of the camera. This additional information is then used in solving for colour constancy. The novelty of our approach is not that we add a colour filter (this is an old idea) but in how we use the additional information. In contradistinction to previous work we propose that the dimensionality of the 6 measurements per image pixel remains at 3 (not 6): we do not add a filter to increase the number of degrees of freedom but rather as a way of estimating the illuminant. We say that a filter is chromagenic if the relationship between filtered and unfiltered RGBs varies with and depends strongly on illumination. The canonical chromagenic algorithm works by testing the applicability of pre-computed relations in situ in an image. We extend the chromagenic approach to incorporate knowledge of the gamut of colours we expect to see under a given light and so in effect we make a hybrid gamut mapping + chromagenic algorithm. Experiments validate our approach with chromagenic gamut mapping shown to deliver significantly better constancy than all other algorithms tested.

S.D. Hordley

Papers

On the removal of shadows from images

Re-evaluating colour constancy algorithms

Convex programming colour constancy with a diagonal-offset model

Colour constancy using the chromagenic constraint