Francesca Gasparini

Coded aperture imaging

We have simulated the performance of various apertures used in coded aperture imaging—optically. The annulus, twin annulus, Fresnel zone plate and the uniformly redundant array have been decoded using a non-coherent correlation process. Ways of reducing the ‘d.c.’ background of the various apertures are discussed. Results of imaging extended and continuous-tone planar objects are presented.

Color balancing of digital photos using simple image statistics

The great diffusion of digital cameras and the widespread use of the internet have produced a mass of digital images depicting a huge variety of subjects, generally acquired by unknown imaging systems under unknown lighting conditions. This makes color balancing, recovery of the color characteristics of the original scene, increasingly difficult. In this paper, we describe a method for detecting and removing a color cast (i.e. a superimposed color due to lighting conditions, or to the characteristics of the capturing device), from a digital photo without any a priori knowledge of its semantic content. First a cast detector, using simple image statistics, classifies the input images as presenting no cast, evident cast, ambiguous cast, a predominant color that must be preserved (such as in underwater images or single color close-ups) or as unclassifiable. A cast remover, a modified version of the white balance algorithm, is then applied in cases of evident or ambiguous cast. The method we propose has been tested with positive results on a data set of some 750 photos.

Self-Adaptive Image Cropping for Small Displays

We propose a new self-adaptive image cropping algorithm where the processing steps are driven by the classification of the images into semantic classes. The algorithm exploits both visual and semantic information. Visual information is obtained from a visual attention model, while semantic information relates to the automatically assigned image genre and to the detection of face and skin regions.

Region-based Illuminant Estimation for Effective Color Correction

Several algorithms were proposed in the literature to recover the illuminant chromaticity of the original scene. These algorithms work well only when prior assumptions are satisfied, and the best and the worst algorithms may be different for different scenes. In particular for certain images a do nothing strategy can be preferred. Starting from these considerations, we have developed a region-based color constancy algorithm able to automatically select (and/or blend) among different color corrections, including a conservative do nothing strategy. The strategy to be applied is selected without any a priori knowledge of the image content and only performing image low level analysis.This book constitutes the refereed proceedings of the 15th International Conference on Image Analysis and Processing, ICIAP 2009, held in Vietri sul Mare, Italy, in September 2009. The 107 revised full papers presented together with 3 invited papers were carefully reviewed and selected from 168 submissions. The papers are organized in topical sections on computer graphics and image processing, low and middle level processing, 2D and 3D segmentation, feature extraction and image analysis, object detection and recognition, video analysis and processing, pattern analysis and classification, learning, graphs and trees, applications, shape analysis, face analysis, medical imaging, and image analysis and pattern recognition

Consensus-based framework for illuminant chromaticity estimation

Several algorithms were proposed in the literature to re- cover the illuminant chromaticity of the original scene. These algo- rithms work well only when prior assumptions are satisfied, and the best and the worst algorithms may be different for different scenes. We investigate the idea of not relying on a single method but instead consider a consensus decision that takes into account the re- sponses of several algorithms and adaptively chooses the algo- rithms to be combined. We investigate different combining strate- gies of state-of-the-art algorithms to improve the results in the illuminant chromaticity estimation. Single algorithms and combined ones are evaluated for both synthetic and real image databases using the angular error between the RGB triplets of the measured illuminant and the estimated one. Being interested in comparing the performance of the methods over large data sets, experimental re- sults are also evaluated using the Wilcoxon signed rank test. Our experiments confirm that the best and the worst algorithms do not exist at all among the state-of-the-art ones and show that simple combining strategies improve the illuminant estimation.

Color correction for digital photographs

The paper describes a reliable and rapid method for detecting and removing a color cast (i.e. a superimposed dominant color) in a digital image without any a priori knowledge of its semantic content. A multi-step algorithm classifies the input images as having no cast, evident cast, ambiguous cast, or intrinsic cast (images presenting a cast due to a predominant color that must be preserved). If an evident or ambiguous cast is found, a cast remover step, a modified version of the white balance algorithm, is then applied in the two cases of evident or ambiguous casts. The method we propose has been tuned and tested with positive results on a data set of over 650 images.

Contrast image correction method

A method for contrast enhancement is proposed. The algorithm is based on a local and image-dependent exponential cor- rection. The technique aims to correct images that simultaneously present overexposed and underexposed regions. To prevent halo artifacts, the bilateral filter is used as the mask of the exponential correction. Depending on the characteristics of the image (piloted by histogram analysis), an automated parameter-tuning step is intro- duced, followed by stretching, clipping, and saturation preserving treatments. Comparisons with other contrast enhancement tech- niques are presented. The Mean Opinion Score (MOS) experiment on grayscale images gives the greatest preference score for our algorithm.

A New Method for RGB to XYZ Transformation Based on Pattern Search Optimization

In this paper we present an RGB to XYZ transformation method based on a pattern search optimization algorithm. Whatever strategy is adopted to initialize the color transformation, our method is able to optimize it in order to minimize the color error on a given training set, also taking into account a color mapping constraint. We report experimental results on simulated and real data sets showing that our method significantly outperforms existing ones.

Polynomial modeling and optimization for colorimetric characterization of scanners

We present different computational strategies for colorimetric characterization of scanners using multidimensional polynomials. The designed strategies allow us to determine the coefficients of an a priori fixed polynomial, taking into account different color error statistics. Moreover, since there is no clear relationship between the polynomial chosen for the characterization and the intrinsic characteristics of the scanner, we show how genetic programming could be used to generate the best polynomial. Experimental results on different devices are reported to confirm the effectiveness of our methods with respect to others in the state of the art.

Automatic redeye removal for smart enhancement of photos of unknown origin

The paper describes a modular procedure for automatic correction of redeye artifact in images of unknown origin, maintaining the natural appearance of the eye. First, a smart color balancing procedure is applied. This phase not only facilitates the subsequent steps of processing, but also improves the overall appearance of the output image. Combining the results of a color-based face detector and of a face detector based on a multi-resolution neural network the most likely facial regions are identified. Redeye is searched for only within these regions, seeking areas with high “redness” satisfying some geometric constraints. A novel redeye removal algorithm is then applied automatically to the red eyes identified, and opportunely smoothed to avoid unnatural transitions between the corrected and original parts. Experimental results on a set of over 450 images are reported.