DISSECTING AND REASSEMBLING COLOR CORRECTION ALGORITHMS FOR IMAGE STITCHING

Abstract

This paper introduces a new compositional framework for classifying color correction methods according to their two main computational units. The framework was used to dissect fifteen among the best color correction algorithms and the computational units so derived, with the addition of four new units specifically designed for this work, were then reassembled in a combinatorial way to originate about one hundred distinct color correction methods, most of which never considered before. The above color correction methods were tested on three different existing datasets, including both real and artificial color transformations, plus a novel dataset of real image pairs categorized according to the kind of color alterations induced by specific acquisition setups. Differently from previous evaluations, special emphasis was given to effectiveness in real world applications, such as image mosaicing and stitching, where robustness with respect to strong image misalignments and light scattering effects is required. Experimental evidence is provided for the first time in terms of the most recent perceptual image quality metrics, which are known to be the closest to human judgment. Comparative results show that combinations of the new computational units are the most effective for real stitching scenarios, regardless of the specific source of color alteration. On the other hand, in the case of accurate image alignment and artificial color alterations, the best performing methods either use one of the new computational units, or are made up of fresh combinations of existing units.

Existing System

GPS (Gradient Preserving Spline), Linear Color Propagation (LCP)

Proposed System

The main contributions of this work arise from the above framework, which allowed us both to investigate existing methods from a new perspective, and to develop more effective solutions to the color correction problem. In this paper, we introduce a compositional framework for classifying color correction methods in a new way. The idea stems from the observation that any color correction method can be decomposed into two main Computational Units (CUs). These are (1) the low-level color map Model Estimator (ME), that actually computes the color maps, and (2) the high level color map Prober and Aggregator (PA), that organizes, combines and applies the color maps. The PA unit (a) receives as input an image pair, computes sets of pixel correspondences and (b) outputs them to the ME unit, then (c) inputs from ME one or more color maps, and finally (d) provides as output the corrected image. The two CUs are distinct yet mutually interdependent, providing input data to each other in steps (b)-(c), that can be iterated according to the PA used.

Architecture

ARCHITECTURE