Image Processing & Applications

Furniture glass tiles are increasingly used for covering walls and facades or for conferring fashionable aesthetical properties to buildings. Companies that produce furniture glass tiles of a desired colour are devoted to performing a colour comparison between the manufactured glass tiles and the ones desired by a customer, or provided by a catalogue. Still today, such a comparison, known as 'colour matching', is mainly performed by company experts by means of a visual inspection, thus leading to a subjective and qualitative colour assessment. A number of methods for colour matching have been afforded in the literature in several industrial fields such as textile, plastics or food; unfortunately, to the best of author's knowledge, no practical method for glass tiles colour matching has been devised until today. The present work provides an image processing-based method capable of carrying out nonpatterned glass tiles colour matching. The method is devised using an appositely developed hardware so as to extract a series of statistical data from scanned images of 10 mm sized glass tiles and, on the basis of the definition of two novel colour distance formulas, endows with colour matching. The achieved colour matching performance agrees in 91% of tests with expertperformed colour classification. The provided formulas are meant to be of general usage for assessing glass tiles colour matching. © RPS 2013.

Keywords: Colour gaussian , Colour matching , Glass , Image processing , Mahalanobis

Minimisation techniques are commonly adopted methodologies for retrieving a 3D surface starting from its shaded representation (image), i.e., for solving the widely known shape from shading (SFS) problem. Unfortunately, depending on the imaged object to be reconstructed, retrieved surfaces often results to be completely different from the expected ones. In recent years, a number of interactive methods have been explored with the aim of improving surface reconstruction; however, since most of these methods require user interaction performed on a tentative reconstructed surface which often is significantly different from the desired one, it is advisable to increase the quality of the surface, to be further processed, as much as possible. Inspired by such techniques, the present work describes a new method for interactive retrieving of shaded object surface. The proposed approach is meant to recover the expected surface by using easy-to-set boundary conditions, so that the human-computer interaction primarily takes place prior to the surface retrieval. The method, tested on a set of case studies, proves to be effective in achieving sufficiently accurate reconstruction of scenes with both front and side illumination. © 2013 Inderscience Enterprises Ltd.

Keywords: Boundary conditions , Computational vision , Human-computer interaction , Minimisation techniques , SFS , Shape from shading

Multispectral imaging techniques are widely used to analyse and restore digital images of ancient documents degraded over time. In particular, acquisitions in infrared and ultraviolet bands can reveal information invisible by naked eye, which is not captured by conventional RGB imaging. Multispectral acquisitions are usually performed with filter-wheel cameras that mount a series of interference filters in front of the sensor to select the spectral band in which the document has to be acquired. Due to the use of different filters, the focus of the lens changes and it is necessary to adjust it manually for each filter, because such imaging systems are devoid of automatic focusing. Thus the acquired images may not be perfectly in-focus and have misalignments. In this work we present an automatic solution to acquire a multispectral data cube of aligned images that can be used in document analysis to extract and/or separate information through enhancement techniques. A custom-made motorized autofocus system controlled by software has been installed on a filter-wheel camera, which allows us to acquire in-focus images automatically at each filter changing, and a registration method based on Fourier-Mellin transform aligns these images. A preliminary calibration is performed to set the focusing of each filter with the working distance. As a result, the camera can capture images independently from the contrast of the scene, also in presence of documents with homogeneous texture. The proposed solution reduces considerably the acquisition time and offers a tool to acquire automatically the data cube to be used in further image analysis techniques. The results of experimentations are hereby presented and discussed. © 2012 Elsevier Masson SAS.

Keywords: Document analysis , Focusing , Image registration , Multispectral imaging

This paper is about the development of an expert system for automatic classification of granite tiles through computer vision. We discuss issues and possible solutions related to image acquisition, robustness against noise factors, extraction of visual features and classification, with particular focus on the last two. In the experiments we compare the performance of different visual features and classifiers over a set of 12 granite classes. The results show that classification based on colour and texture is highly effective and outperforms previous methods based on textural features alone. As for the classifiers, Support Vector Machines show to be superior to the others, provided that the governing parameters are tuned properly. © 2012 Elsevier Ltd. All rights reserved.

Keywords: Classification , Colour , Grading , Granite , Texture

The actual foam density affects its mechanical energy absorption capabilities. Making structural elements starting from the cutting of semi-finished items may produce uneven results due to the lack of homogeneity in the foam. The subject of this work is the study of AlSi7 metallic foams, the focus being on the evaluation of the effective density distribution throughout large ingots. This is the first step required to establish a correlation between manufacturing process parameters and mechanical properties. The results highlighted that the void density increases from the centre toward the ingot outer wall and that specimens coming from different regions of the ingot have a very different mechanical behaviour. This is probably due to the difficulty in controlling temperature gradients and cooling rates throughout big mould cavities during the production process. © 2012 Elsevier B.V.

Keywords: Aluminium alloy foams , Cellular materials , Mechanical characterisation

We present a novel approach to the early diagnosis of lung tumors that considers new malignancy indexes by using a metaball-based representation of this neoplasia. Starting from CT data we extract the suspected tumors represented as approximating metaballs and calculate malignancy indexes based on precise volume and surface irregularity evaluation. The mentioned approximation is performed resolving a constraint problem using a genetic algorithm whose objective function is a mathematical representation of the metaball. Compared to existing art, the metaball approximation provides a consistent reference surface for the evaluation of novel diagnosis parameters borrowed from engineering surface analysis. We have implemented the method in a demonstrator software and analyzed three different test cases. Copyright 2012 ACM.

Keywords: Biomedical computation , Genetic algorithm constrained optimization problem , GENOCOP III , Lung Tumor diagnosis , Surface analysis

Yarn hairiness and yarn hand represent key parameters to be strictly assessed and controlled in textile processes since they affect many aspects such as visual appearance of yarns (and consequently of fabrics), handle, thermal insulation, pleasant sensation during touch and smoothness. This is particularly true when fancy yarns, such as jaspè or frisè, are produced using ring spinning: colored natural fibers composing the fancy yarns are required to protrude, to some extent, from the yarn core, usually composed by synthetic material, so as to impart the desired properties in terms of smoothness and luster. With the aim of realizing highest performing fancy yarns, a novel ring spinning system, equipped with a double drafting unit, has been realized by Università di Firenze thanks to the contribute of Tuscany Region (Italy). Once the fancy yarns are obtained, the performance of this innovative ring spinning is evaluated by means of a Computer Aided analysis of yarn geometry able to provide a novel measurement of yarn hairiness and to quantitatively define a yarn hand-related parameter. A Machine Vision system has been devised in order to acquire yarn geometry so that an accurate analysis can be carried out. Such computer aided-based analysis allows to determine two parameters used for determining hairiness and hand: the "equivalent yarn hairiness" and the "yarn hand index". Such parameters are evaluated for yarns obtained using both the innovative and a conventional ring spinning machine so that the yarns quality can be effectively compared. Based on the obtained results that the proposed method proved to be suitable and effective for evaluating yarn hairiness within an average error of about 5.40% with respect to the Uster tester. Furthermore, a good correlation (93%) between objective and subjective assessment of yarn hand was reached.

Keywords: Computer Aided analysis , Image processing , Yarn geometry , Yarn hairiness , Yarn hand

Distance measures and geometrical features are widely used to describe faces. Generally, they are extracted punctually from landmarks, namely anthropometric reference points. The aims are various, such as face recognition, facial expression recognition, face detection, study of changes in facial morphology due to growth, or dysmorphologies. Most of the time, landmarks were extracted with the help of an algorithm or manually located on the faces. Then, measures are computed or geometrical features are extracted to perform the scope of the study. This paper is intended as a survey collecting and explaining all these features, in order to provide a structured user database of the potential parameters and their characteristics. Firstly, facial soft-tissue landmarks are defined and contextualized; then the various measures are introduced and some results are given; lastly, the most important measures are compared to identify the best one for face recognition applications. © 2012 Elsevier B.V. All rights reserved.

Keywords: 3D models , 3D scanners , Face morphology , Soft tissue landmarks

The fatigue behaviour is examined in terms of calorimetric effects. Aluminum alloy and steel have been chosen as reference materials. Heat sources accompanying the fatigue mechanisms are derived from thermal images provided by an infrared camera. A processing method allows identifying separately thermoelastic and dissipative sources. Thermoelastic effects are compared to theoretical predictions given by the basic, linear, isotropic thermoelastic model. Dissipation amplitudes are analyzed as a function of the loading frequency and stress amplitude applied to the fatigue specimen. Finally, the heterogeneous character of the fatigue development is studied both in terms of thermoelastic and dissipation sources.

Objective: In restored teeth, stresses at the tooth-restoration interface during masticatory processes may fracture the teeth or the restoration and cracks may grow and propagate. The aim was to apply numerical methodologies to simulate the behavior of a restored tooth and to evaluate fatigue lifetimes before crack failure. Materials and methods: Using a CAD-FEM procedure and fatigue mechanic laws, the fatigue damage of a restored molar was numerically estimated. Tessellated surfaces of enamel and dentin were extracted by applying segmentation and classification algorithms, to sets of 2D image data. A user-friendly GUI, which enables selection and visualization of 3D tessellated surfaces, was developed in a MatLab® environment. The tooth-boundary surfaces of enamel and dentin were then created by sweeping operations through cross-sections. A class II MOD cavity preparation was then added into the 3D model and tetrahedral mesh elements were generated. Fatigue simulation was performed by combining a preliminary static FEA simulation with classical fatigue mechanical laws. Results: Regions with the shortest fatigue-life were located around the fillets of the class II MOD cavity, where the static stress was highest. Significance: The described method can be successfully adopted to generate detailed 3D-FE models of molar teeth, with different cavities and restorative materials. This method could be quickly implemented for other dental or biomechanical applications. © 2010 Academy of Dental Materials.

Keywords: 3D fatigue simulation , 3D image acquisition , CAD-FEM modeling , Class II MOD restoration , Micro-CT

Current research on underwater 3D imaging methods is mainly addressing long range applications like seafloor mapping or surveys of archeological sites and shipwrecks. Recently, there is an increasing need for more accessible and precise close-range 3D acquisition technologies in some application fields like, for example, monitoring the growth of coral reefs or reconstructing underwater archaeological pieces that in most cases cannot be recovered from the seabed. This paper presents the first results of a research project that aims to investigate the possibility of using active optical techniques for the whole-field 3D reconstructions in an underwater environment. In this work we have tested an optical technique, frequently used for in air acquisition, based on the projection of structured lighting patterns acquired by a stereo vision system. We describe the experimental setup used for the underwater tests, which were conducted in a water tank with different turbidity conditions. The tests have evidenced that the quality of 3D reconstruction is acceptable even with high turbidity values, despite the heavy presence of scattering and absorption effects. © 2011 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS).

Keywords: 3D reconstruction , Imaging in turbid medium , Photogrammetry , Structured light , Underwater imaging

Chronic wounds represent a particular debilitating health care problem, mainly affecting elderly people. A full and correct diagnosis of tissue damage should be carried out considering both dimensional, chromatic, and thermal parameters. A great variety of methods have been proposed with the aim of producing objective assessment of skin lesions, but none of the existing technologies seem to be robust enough to work for all ulcer typologies. This paper describes an innovative and non-invasive system that allows the automatic measurement of non-healing chronic wounds. The methodology involves the integration of a three-dimensional (3D) optical scanner, based on a structured light approach, with a thermal imager. The system enables the acquisition of geometrical data, which are directly related to chromatic and temperature patterns through a mapping procedure. Damaged skin areas are detected by combining visible and thermal imaging. This approach allows for the automatic measurement of extension and depth of ulcers, even in the absence of significant and well-defined chromatic patterns. The proposed technology has been tested in the measurement of ulcers on human legs. Clinical tests have demonstrated the effectiveness of this methodology in supporting medical experts for the assessment of chronic wounds. © 2011 Authors.

Keywords: 3D model reconstruction , 3D thermography , image processing , wound assessment

Automatic on-line signature recognition has been investigated by several authors in order to allow machines to recognize an user from its own biometric traits. The following paper deals with features and models required in order to allow a machine to learn and discriminate signatures. The proposed solution approaches the signature making process as the motion of a point in a bi-dimensional space and model s statistic properties of the motion via the well known Maximum a Posteriori training of Gaussian Mixture Models. Comparing our approach to state-of-the-art solutions, major advancements have been found. As first, both system accuracy in signature discrimination and system resistance to forgeries have been double. Eventually, the proposed modeling technique leads to smaller templates, whose size is halved with respect to state-of-theart alternatives.

Keywords: Biometry , Maximum a posteriori , On-line signature recognition , Pattern recognition

The evolution of olive oil technology is related to research raised to deepen the understanding of biological and biophysical phenomena during the machining process olives, thus allowing the introduction of sensors able to monitoring the parameters and the process according to the characteristics of olives themselves. Current research has identified manufacturing protocols that can enable the achievement levels of product quality required by the market, mainly by reducing the time between collection and processing of olives and raising the technological level of extraction lines. In this context, the present paper aims to describe some of the results of a three-years project developed by the PIN-University of Florence (Italy) in collaboration with the Tuscan Regional Agricultural Development, the Florence Commerce Chamber "Laboratorio Chimico Merceologico-Azienda Speciale CCIAA di Firenze" and the SME "TEM" (Toscana Enologica Mori). The paper will describe the development of an innovative Machine Vision system able to 1) acquire, in real-time, images of olives in the conferring phase and 2) to process the acquired images in order to evaluate the ripeness of olives on the basis of their colour and the eventual presence of superficial defects. The devised system has been tested with the data extracted by olives in the harvesting period of year 2006. © 2011 by Nova Science Publishers, Inc. All rights reserved.

Automatic on-line signature identification is a procedure which allows a machine to identify a subject among a cohort of individuals by using only the subject's signature. The following paper deals with features and models required in order to allow a machine to learn and discriminate people on the basis of such a biometric trait. The proposed solution presents a neural network based framework for template adaptation which has demonstrated to improve the resilience of a system, when it has to face with forgeries, that is, fake signatures which are used in order to attack the system and grant unauthorized access to services. The proposed framework provides an improved security level of 35% with respect to non adapted systems.

Keywords: Adaptation , Artificial neural networks , Identification , Signature

Offshore wind farms are undergoing unprecedented development as EU member states focus on complying with 2020 renewable energy mandates. However, wind farm site placement requires great care, to avoid compromising protected habitats, such as Sabellaria spinulosa reefs. This paper presents an investigation into the potential of different feature generation methods for identifying sidescan sonar image textures characteristic of Sabellaria spinulosa colonies. We propose an extensible test methodology and carry out a detailed comparison of several textural features. Our results show that Gabor filter bank features yield good (up to 89.4% overall) classification accuracies and often outperform other methods in identifying the Sabellaria spinulosa textural class. A Dual- Tree Complex Wavelet Transform, Ring filters and some statistical methods also produce encouraging results. © 2011 IEEE.

Keywords: Sabellaria spinulosa , Sonar , Texture analysis

The aim of the paper is to conduct a performance evaluation where several texture descriptors such as Local Binary Patterns (LBP), Coordinated Clusters Representation (CCR) and (Improved Local Binary Patterns) ILBP are applied for granite texture classification. In our work we were particularly interested to assess the robustness of the analysed texture descriptors to image rotation when they were implemented in both the standard and rotation-invariant forms. In order to attain this goal, we have generated a database of granite textures that were rotated using hardware and software procedures. The experimental data indicate that the ILBP features return improved performance when compared with those achieved by the LBP and CCR descriptors. Another important finding resulting from this investigation reveals that the classification results obtained when the texture analysis techniques were applied to granite image data rotated by software procedures are inconsistent with those achieved when the hardware-rotated data are used for classification purposes. This discovery is surprising and suggests that the results obtained when the texture analysis techniques are evaluated on synthetically rotated data need to be interpreted with care, as the principal characteristics of the texture are altered by the data interpolation that is applied during the image rotation process. © 2010 Springer-Verlag.

Keywords: CCR , Granite grading , ILBP , LBP , Rotation invariance , Texture classification

Color texture classification has been an area of intensive research activity. From the very onset, approaches to combining color and texture have been the subject of much discussion, and in particular, whether they should be considered joint or separately. We present a comprehensive comparison of the most prominent approaches both from a theoretical and experimental standpoint. The main contributions of our work are: (i) the establishment of a generic and extensible framework to classify methods for color texture classification on a mathematical basis, and (ii) a theoretical and experimental comparison of the most salient existing methods. Starting from an extensive set of experiments based on the Outex dataset, we highlight those texture descriptors that provide good accuracy along with low dimensionality. The results suggest that separate color and texture processing is the best practice when one seeks for optimal compromise between accuracy and limited number of features. We believe that our work may serve as a guide for those who need to choose the appropriate method for a specific application, as well as a basis for the development of new methods. © 2011 SPIE and IST.

It is well-known that local binary pattern (LBP) histograms of real textures exhibit a markedly uneven distribution, which is dominated by the so-called uniform patterns. The widely accepted interpretation of this phenomenon is that uniform patterns correspond to texture microfeatures, such as edges, corners, and spots. In this paper we present a theoretical study about the relative occurrence of LBPs based on the consideration that the LBP operator partitions the set of grayscale patterns into an ensemble of disjoint multidimensional polytopes. We derive exact prior probabilities of LBPs by calculating the volume of such polytopes. Our study puts in evidence that both the uneven distribution of the LBP histogram and the high occurrence of uniform patterns are direct consequences of the mathematical structure of the method rather than an intrinsic property of real textures. © 2011 Springer Science+Business Media, LLC.

Keywords: Local binary patterns , Polytopes , Texture

In this work we present a new family of computationally simple texture descriptors, referred to as binary gradient contours (BGC). The BGC methodology relies on computing a set of eight binary gradients between pairs of pixels all along a closed path around the central pixel of a 3×3 grayscale image patch. We developed three different versions of BGC features, namely single-loop, double-loop and triple-loop. To quantitatively assess the effectiveness of the proposed approach we performed an ensemble of texture classification experiments over 10 different datasets. The obtained results make it apparent that the single-loop version is the best performer of the BGC family. Experiments also show that the single-loop BGC texture operator outperforms the well-known LBP. Statistical significance of the achieved accuracy improvement has been demonstrated through the Wilkoxon signed rank test. © 2011 Elsevier Ltd. All rights reserved.

Keywords: BGC , LBP , Texture features