Non-iterative Comprehensive Normalisation
نویسندگان
چکیده
The light reflected from an object depends not only on object colours but also on lighting geometry and illuminant colour. As a consequence the raw colour recorded by a camera is not a reliable cue for object based tasks such as recognition and tracking. One solution to this problem is to find functions of image colours that cancel out dependencies due to illumination. While many invariant functions cancel out either dependency due to geometry or dependency due to illuminant colour, only the comprehensive normalisation has been shown (theoretically and experimentally) to cancel both. However, this invariance is bought at the price of an iterative procedure. In this paper we develop a non iterative log comprehensive normalisation procedure. We begin by reviewing the idea that lighting effects due to geometry and light colour can, under certain reasonable simplifying assumptions, both be modelled using simple scalar multipliers. We now take logarithms and turn geometry and light colour dependency into additive processes. We show how in this log color space two simple projection operators lead to invariance to geometry and light colour. Moreover, because projection operators are idempotent, illuminant invariance is achieved in a single step. Experiments demonstrated that log comprehensive normalisation used as a preprocessing step supports accurate colour based object recognition independent of lighting conditions.
منابع مشابه
Illuminant and gamma comprehensive normalisation in logRGB space
The light re ected from an object depends not only on object colours but also on lighting geometry and illuminant colour. As a consequence the raw colour recorded by a camera is not a reliable cue for object based tasks such as recognition and tracking. One solution to this problem is to nd functions of image colours that cancel out dependencies due to illumination. While many invariant functio...
متن کاملGamma Comprehensive Normalisation
The light reflected from an object depends not only on surface reflectance of the object but also on lighting geometry and illuminant color. As a consequence, the raw color recorded by a camera is not a reliable cue for color based tasks such as object recognition and tracking. One solution to this problem is to find color invariants which are independent of illumination. While many invariant f...
متن کاملCross-Platform Microarray Data Normalisation for Regulatory Network Inference
BACKGROUND Inferring Gene Regulatory Networks (GRNs) from time course microarray data suffers from the dimensionality problem created by the short length of available time series compared to the large number of genes in the network. To overcome this, data integration from diverse sources is mandatory. Microarray data from different sources and platforms are publicly available, but integration i...
متن کاملIntroduction to OLIN package
Microarray measurements are affected by a variety of systematic experimental errors limiting the accuracy of data produced. Two well-known systematic errors for two-colour arrays are the so-called intensity-dependent and spatial (location-dependent) dye bias. Normalisation aims to correct for systematic errors in microarray data. The common linear (or global) normalisation method often fails to...
متن کاملNon-rigid 3D Shape Registration using an Adaptive Template
We present a new fully-automatic non-rigid 3D shape registration (morphing) framework comprising (1) a new 3D landmarking and pose normalisation method; (2) an adaptive shape template method to accelerate the convergence of registration algorithms and achieve a better final shape correspondence and (3) a new iterative registration method that combines Iterative Closest Points with Coherent Poin...
متن کامل