Graham D. Finlayson
Bio: Graham D. Finlayson is an academic researcher from University of East Anglia. The author has contributed to research in topics: Standard illuminant & Color constancy. The author has an hindex of 46, co-authored 306 publications receiving 10403 citations. Previous affiliations of Graham D. Finlayson include University of York & Universities UK.
Papers published on a yearly basis
TL;DR: Results of tests with the new color-constant-color-indexing algorithm show that it works very well even when the illumination varies spatially in its intensity and color, which circumvents the need for color constancy preprocessing.
Abstract: Objects can be recognized on the basis of their color alone by color indexing, a technique developed by Swain-Ballard (1991) which involves matching color-space histograms. Color indexing fails, however, when the incident illumination varies either spatially or spectrally. Although this limitation might be overcome by preprocessing with a color constancy algorithm, we instead propose histogramming color ratios. Since the ratios of color RGB triples from neighboring locations are relatively insensitive to changes in the incident illumination, this circumvents the need for color constancy preprocessing. Results of tests with the new color-constant-color-indexing algorithm on synthetic and real images show that it works very well even when the illumination varies spatially in its intensity and color. >
TL;DR: This paper shows how to recover a 3D, full color shadow-free image representation by first (with the help of the 2D representation) identifying shadow edges and proposing a method to reintegrate this thresholded edge map, thus deriving the sought-after 3D shadow- free image.
Abstract: 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.
TL;DR: A new probabilistic instantiation of this correlation framework is proposed and shown to deliver very good color constancy on both synthetic and real images, and is rich enough to allow many existing algorithms to be expressed within it.
Abstract: The paper considers the problem of illuminant estimation: how, given an image of a scene, recorded under an unknown light, we can recover an estimate of that light. Obtaining such an estimate is a central part of solving the color constancy problem. Thus, the work presented will have applications in fields such as color-based object recognition and digital photography. Rather than attempting to recover a single estimate of the illuminant, we instead set out to recover a measure of the likelihood that each of a set of possible illuminants was the scene illuminant. We begin by determining which image colors can occur (and how these colors are distributed) under each of a set of possible lights. We discuss how, for a given camera, we can obtain this knowledge. We then correlate this information with the colors in a particular image to obtain a measure of the likelihood that each of the possible lights was the scene illuminant. Finally, we use this likelihood information to choose a single light as an estimate of the scene illuminant. Computation is expressed and performed in a generic correlation framework which we develop. We propose a new probabilistic instantiation of this correlation framework and show that it delivers very good color constancy on both synthetic and real images. We further show that the proposed framework is rich enough to allow many existing algorithms to be expressed within it: the gray-world and gamut-mapping algorithms are presented in this framework and we also explore the relationship of these algorithms to other probabilistic and neural network approaches to color constancy.
01 Nov 2004
TL;DR: It is shown that Max-RGB and Grey-World are two instantia-tions of Minkowski norm, and that for a large cali-brated dataset L6 norm colour constancy works best over-all (the authors have improved the performance achieved by a sim-ple normalization based approach).
Abstract: Colour constancy is a central problem for any visual system performing a task which requires stable perception of the colour world. To solve the colour constancy problem we estimate the colour of the prevailing light and then, at the second stage, remove it. Two of the most commonly used simple techniques for estimating the colour of the light are the Grey-World and Max-RGB algorithms. In this paper we begin by observing that this two colour constancy computations will respectively return the right answer if the average scene colour is grey or the maximum is white (and conversely, the degree of failure is proportional to the extent that these assumptions hold). We go on to ask the following question: “ Would we perform better colour constancy by assuming the scene average is some shade of grey?”. We give a mathematical answer to this question. Firstly, we show that Max-RGB and Grey-World are two instantia-tions of Minkowski norm. Secondly, that for a large cali-brated dataset L6 norm colour constancy works best over-all (we have improved the performance achieved by a sim-ple normalization based approach). Surprisingly we found performance to be similar to more elaborated algorithm.
••28 May 2002
TL;DR: It is shown that a good calibration can be achieved simply by recording a sequence of images of a fixed outdoor scene over the course of a day, and that the resulting calibration is close to that achievable using measurements of the camera's sensitivity functions.
Abstract: Illumination conditions cause problems for many computer vision algorithms. In particular, shadows in an image can cause segmentation, tracking, or recognition algorithms to fail. In this paper we propose a method to process a 3-band colour image to locate, and subsequently remove shadows. The result is a 3-band colour image which contains all the original salient information in the image, except that the shadows are gone.We use the method set out in  to derive a 1-d illumination invariant shadow-free image. We then use this invariant image together with the original image to locate shadow edges. By setting these shadow edges to zero in an edge representation of the original image, and by subsequently re-integrating this edge representation by a method paralleling lightness recovery, we are able to arrive at our sought after full colour, shadow free image. Preliminary results reported in the paper show that the method is effective.A caveat for the application of the method is that we must have a calibrated camera. We show in this paper that a good calibration can be achieved simply by recording a sequence of images of a fixed outdoor scene over the course of a day. After calibration, only a single image is required for shadow removal. It is shown that the resulting calibration is close to that achievable using measurements of the camera's sensitivity functions.
TL;DR: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Abstract: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene. The features are invariant to image scale and rotation, and are shown to provide robust matching across a substantial range of affine distortion, change in 3D viewpoint, addition of noise, and change in illumination. The features are highly distinctive, in the sense that a single feature can be correctly matched with high probability against a large database of features from many images. This paper also describes an approach to using these features for object recognition. The recognition proceeds by matching individual features to a database of features from known objects using a fast nearest-neighbor algorithm, followed by a Hough transform to identify clusters belonging to a single object, and finally performing verification through least-squares solution for consistent pose parameters. This approach to recognition can robustly identify objects among clutter and occlusion while achieving near real-time performance.
••07 Jun 2015
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
Abstract: We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.
TL;DR: The working conditions of content-based retrieval: patterns of use, types of pictures, the role of semantics, and the sensory gap are discussed, as well as aspects of system engineering: databases, system architecture, and evaluation.
Abstract: Presents a review of 200 references in content-based image retrieval. The paper starts with discussing the working conditions of content-based retrieval: patterns of use, types of pictures, the role of semantics, and the sensory gap. Subsequent sections discuss computational steps for image retrieval systems. Step one of the review is image processing for retrieval sorted by color, texture, and local geometry. Features for retrieval are discussed next, sorted by: accumulative and global features, salient points, object and shape features, signs, and structural combinations thereof. Similarity of pictures and objects in pictures is reviewed for each of the feature types, in close connection to the types and means of feedback the user of the systems is capable of giving by interaction. We briefly discuss aspects of system engineering: databases, system architecture, and evaluation. In the concluding section, we present our view on: the driving force of the field, the heritage from computer vision, the influence on computer vision, the role of similarity and of interaction, the need for databases, the problem of evaluation, and the role of the semantic gap.
TL;DR: Almost 300 key theoretical and empirical contributions in the current decade related to image retrieval and automatic image annotation are surveyed, and the spawning of related subfields are discussed, to discuss the adaptation of existing image retrieval techniques to build systems that can be useful in the real world.
Abstract: We have witnessed great interest and a wealth of promise in content-based image retrieval as an emerging technology. While the last decade laid foundation to such promise, it also paved the way for a large number of new techniques and systems, got many new people involved, and triggered stronger association of weakly related fields. In this article, we survey almost 300 key theoretical and empirical contributions in the current decade related to image retrieval and automatic image annotation, and in the process discuss the spawning of related subfields. We also discuss significant challenges involved in the adaptation of existing image retrieval techniques to build systems that can be useful in the real world. In retrospect of what has been achieved so far, we also conjecture what the future may hold for image retrieval research.
01 Jan 2006