Filippo Stanco

A locally adaptive zooming algorithm for digital images

Abstract In this paper we address the problem of producing an enlarged picture from a given digital image (zooming). We propose a method that tries to take into account information about discontinuities or sharp luminance variations while doubling the input picture. This is realized by a nonlinear iterative procedure of the zoomed image and could hence be implemented with limited computational resources. The algorithm works on monochromatic images, RGB color pictures and Bayer data images acquired by CCD/CMOS camera sensor. Our experiments show that the proposed method beats in quality classical simple zooming techniques (e.g. pixel replication, simple interpolation). Moreover our algorithm is competitive both for quality and efficiency with bicubic interpolation.

Smart interpolation by anisotropic diffusion

To enlarge a digital image from a single frame preserving the perceptive cues is a relevant research issue. The best known algorithms take into account the presence of edges in the luminance channel, to interpolate correctly the samples/pixels of the original image. This approach allows the production of pictures where the interpolated artifacts (aliasing blurring effect,...) are limited but where high frequencies are not properly preserved. The zooming algorithm proposed in this paper on the other hand reduces the noise and enhances the contrast to the borders/edges of the enlarged picture using classical anisotropic diffusion improved by a smart heuristic strategy. The method requires limited computational resources and it works on gray-level images, RGB color pictures and Bayer data. Our experiments show that this algorithm outperforms in quality and efficiency the classical interpolation methods (replication, bilinear, bicubic).

A Benchmark Dataset to Study the Representation of Food Images

It is well-known that people love food. However, an insane diet can cause problems in the general health of the people. Since health is strictly linked to the diet, advanced computer vision tools to recognize food images (e.g. acquired with mobile/wearable cameras), as well as their properties (e.g., calories), can help the diet monitoring by providing useful information to the experts (e.g., nutritionists) to assess the food intake of patients (e.g., to combat obesity). The food recognition is a challenging task since the food is intrinsically deformable and presents high variability in appearance. Image representation plays a fundamental role. To properly study the peculiarities of the image representation in the food application context, a benchmark dataset is needed. These facts motivate the work presented in this paper. In this work we introduce the UNICT-FD889 dataset. It is the first food image dataset composed by over \(800\) distinct plates of food which can be used as benchmark to design and compare representation models of food images. We exploit the UNICT-FD889 dataset for Near Duplicate Image Retrieval (NDIR) purposes by comparing three standard state-of-the-art image descriptors: Bag of Textons, PRICoLBP and SIFT. Results confirm that both textures and colors are fundamental properties in food representation. Moreover the experiments point out that the Bag of Textons representation obtained considering the color domain is more accurate than the other two approaches for NDIR.

Virtual restoration of vintage photographic prints affected by foxing and water blotches

We propose a new algorithm to digitally restore vintage photographic prints affected by foxing and water blotches. It semi- automatically recovers the defects utilizing the features of the stains. The restoration process enhances the residual image information still present in the area. It is composed of three different steps: in- painting, additive-multiplicative (A-M) modeling, and interpolation.

An efficient Re-indexing algorithm for color-mapped images

The efficiency of lossless compression algorithms for fixed-palette images (indexed images) may change if a different indexing scheme is adopted. Many lossless compression algorithms adopt a differential-predictive approach. Hence, if the spatial distribution of the indexes over the image is smooth, greater compression ratios may be obtained. Because of this, finding an indexing scheme that realizes such a smooth distribution is a relevant issue. Obtaining an optimal re-indexing scheme is suspected to be a hard problem and only approximate solutions have been provided in literature. In this paper, we restate the re-indexing problem as a graph optimization problem: an optimal re-indexing corresponds to the heaviest Hamiltonian path in a weighted graph. It follows that any algorithm which finds a good approximate solution to this graph-theoretical problem also provides a good re-indexing. We propose a simple and easy-to-implement approximation algorithm to find such a path. The proposed technique compares favorably with most of the algorithms proposed in literature, both in terms of computational complexity and of compression ratio.

Towards the automated restoration of old photographic prints: a survey

The ubiquitous fruition of cultural and artistic heritage in the field of photography requires as a first step the conversion of a huge amount of old printed material into digital form, for successive manipulation and data management. This process is particularly delicate for photographic prints, which often show the effects of aging. This paper reports a list of the principal defects that can be detected in an old photography; the different origins of them, and their different features, suggest different restoration approaches.

Retrieval and classification of food images

Automatic food understanding from images is an interesting challenge with applications in different domains. In particular, food intake monitoring is becoming more and more important because of the key role that it plays in health and market economies. In this paper, we address the study of food image processing from the perspective of Computer Vision. As first contribution we present a survey of the studies in the context of food image processing from the early attempts to the current state-of-the-art methods. Since retrieval and classification engines able to work on food images are required to build automatic systems for diet monitoring (e.g., to be embedded in wearable cameras), we focus our attention on the aspect of the representation of the food images because it plays a fundamental role in the understanding engines. The food retrieval and classification is a challenging task since the food presents high variableness and an intrinsic deformability. To properly study the peculiarities of different image representations we propose the UNICT-FD1200 dataset. It was composed of 4754 food images of 1200 distinct dishes acquired during real meals. Each food plate is acquired multiple times and the overall dataset presents both geometric and photometric variabilities. The images of the dataset have been manually labeled considering 8 categories: Appetizer, Main Course, Second Course, Single Course, Side Dish, Dessert, Breakfast, Fruit. We have performed tests employing different representations of the state-of-the-art to assess the related performances on the UNICT-FD1200 dataset. Finally, we propose a new representation based on the perceptual concept of Anti-Textons which is able to encode spatial information between Textons outperforming other representations in the context of food retrieval and Classification.

Augmented Perception of the Past. The Case of Hellenistic Syracuse

The aim of this paper is to present a real-time interaction system for ancient artifacts digitally restored in a virtual environment. Using commercial hardware and open source software, Augmented Reality versions of archaeological artifacts are experienced on mobile devices both in a real outdoor site as well as an indoor museum. The case study for this project is represented by two artifacts of Syracuse, Italy, a statue and an altar, dated back to Hellenistic time. Virtual replicas of the two artifacts were produced applying different techniques. Later the two projects became part of the same research plan aimed to virtually rebuild the most significant artistic and architectural features of Hellenistic Syracuse. Besides the simple production of 3D models, via laserscanning and 3D modelling, a digital process of visual improvement of the statue was preliminary carried out based on photographic documentation of some archetypes. The commercial framework for mobile devices, ARToolworks, has been used for developing Augmented Reality applications. Using a pattern that is recognized by the device, the virtual model is shown as it is in the real world. The novelty of this work is that graduate students in virtual archaeology and non computer programmers such as museum staff, could benefit of this work and implement such a system.

Self Organizing Motor Maps for Color-Mapped Image Re-Indexing

Palette re-ordering is an effective approach for improving the compression of color-indexed images. If the spatial distribution of the indexes in the image is smooth, greater compression ratios may be obtained. As is already known, obtaining an optimal re-indexing scheme is not a trivial task. In this paper, we provide a novel algorithm for palette re-ordering problem making use of a motor map neural network. Experimental results show the real effectiveness of the proposed method both in terms of compression ratio and zero-order entropy of local differences. Also, its computational complexity is competitive with previous works in the field.

Virtual restoration of fragmented glass plate photographs

In this paper we address the problem of restoration of fragmented glass plate photographs. We propose an algorithm based on the roto-translation of the fragments. A preprocessing adjustment in the contour combined with final interpolation is necessary to avoid artifacts.