Luca Costantini

RedDots replayed: A new replay spoofing attack corpus for text-dependent speaker verification research

This paper describes a new database for the assessment of automatic speaker verification (ASV) vulnerabilities to spoofing attacks. In contrast to other recent data collection efforts, the new database has been designed to support the development of replay spoofing countermeasures tailored towards the protection of text-dependent ASV systems from replay attacks in the face of variable recording and playback conditions. Derived from the re-recording of the original RedDots database, the effort is aligned with that in text-dependent ASV and thus well positioned for future assessments of replay spoofing countermeasures, not just in isolation, but in integration with ASV. The paper describes the database design and re-recording, a protocol and some early spoofing detection results. The new “RedDots Replayed” database is publicly available through a creative commons license.

Space-time Zernike moments and pyramid kernel descriptors for action classification

Action recognition in videos is a relevant and challenging task of automatic semantic video analysis. Most successful approaches exploit local space-time descriptors. These descriptors are usually carefully engineered in order to obtain feature invariance to photometric and geometric variations. The main drawback of space-time descriptors is high dimensionality and efficiency. In this paper we propose a novel descriptor based on 3D Zernike moments computed for space-time patches. Moments are by construction not redundant and therefore optimal for compactness. Given the hierarchical structure of our descriptor we propose a novel similarity procedure that exploits this structure comparing features as pyramids. The approach is tested on a public dataset and compared with state-of-the art descriptors.

Performances evaluation of a novel Hadoop and Spark based system of image retrieval for huge collections

A novel system of image retrieval, based on Hadoop and Spark, is presented. Managing and extracting information from Big Data is a challenging and fundamental task. For these reasons, the system is scalable and it is designed to be able to manage small collections of images as well as huge collections of images. Hadoop and Spark are based on the MapReduce framework, but they have different characteristics. The proposed system is designed to take advantage of these two technologies. The performances of the proposed system are evaluated and analysed in terms of computational cost in order to understand in which context it could be successfully used.The experimental results show that the proposed system is efficient for both small and huge collections.

SVM for historical sport video classification

In this work the authors propose a classification method based on Support Vector Machine (SVM) and key frames features extraction to classify historical sport video contents. In the context of the Italian Project, IRMA (Information Retrieval in Multimedia Archives), with the goal to recover and preserve historical videos of proven cultural interest, a data set made up of several hours of videos from the 1960 Olympic games, provided by RAI and Teche RAI, is adopted as testbed. Each video is summarized by its key frames and represented by the features vectors computed in the Laguerre Gauss transformed domain. The high-level video classification starts from these vectors that are the input of the SVM classifier. The experimental results show the effectiveness of the proposed method.

Texture segmentation based on Laguerre Gauss functions and k-means algorithm driven by Kullback–Leibler divergence

Abstract. A new technique for texture segmentation is presented. The method is based on the use of Laguerre Gauss (LG) functions, which allow an efficient representation of textures. In particular, the marginal densities of the LG expansion coefficients are approximated by the generalized Gaussian densities, which are completely described by two parameters. The classification and the segmentation steps are performed by using a modified k-means algorithm exploiting the Kullback–Leibler divergence as similarity metric. This clustering method is a more efficient system for texture comparison, thus resulting in a more accurate segmentation. The effectiveness of the proposed method is evaluated by using mosaic image sets created by using the Brodatz dataset, and real images.

Image clustering fusion technique based on BFS

With the increasing in number and size of databases dedicated to the storage of visual content, the need for effective retrieval systems has become crucial. The proposed method makes a significant contribution to meet this need through a technique in which sets of clusters are fused together to create an unique and more significant set of clusters. The images are represented by some features and then are grouped by these features, that are considered one by one. A probability matrix is then built and explored by the breadth first search algorithm with the aim of select an unique set of clusters. Experimental results, obtained using two different datasets, show the effectiveness of the proposed technique. Furthermore, the proposed approach overcomes the drawback of tuning a set of parameters that fuse the similarity measurement obtained by each feature to get an overall similarity between two images.

Textured areas detection and segmentation in circular harmonic functions domain

In this work a novel technique for detecting and segmenting textured areas in natural images is presented. The method is based on the circular harmonic function, and, in particular, on the Laguerre Gauss functions. The detection of the textured areas is performed by analyzing the mean, the mode, and the skewness of the marginal densities of the Laguerre Gauss coefficients. By using these parameters a classification of the patch and of the pixel, is performed. The feature vectors representing the textures are built using the parameters of the Generalized Gaussian Densities that approximate the marginal densities of the Laguerre Gauss functions computed at three different resolutions. The feature vectors are clustered by using the K-means algorithm in which the symmetric Kullback-Leibler distance is adopted. The experimental results, obtained by using a set of natural images, show the effectiveness of the proposed technique.

Impact of edges characterization on image clustering

In this work a novel technique for representing the edges of an image is presented and the impact of this on image clustering is investigated. The characterization is performed in two steps: the “most important” edges are first selected by using both the Laplace operator and the Laguerre Gauss functions, and then the phase distribution of each edge point is estimated. The similarity is measured by using the Euclidean distance. The query-by-example systems usually rank in the first positions objects very similar to the query. If many almost identical copies of the query object are present in the database, all of them are shown. However, some object that are interesting are not ranked in the first positions. To this aim a clustering method is used. This method is based on the low level features, such as edges, texture, and color.

A comparison between space-time video descriptors

The description of space-time patches is a fundamental task in many applications such as video retrieval or classification. Each space-time patch can be described by using a set of orthogonal functions that represent a subspace, for example a sphere or a cylinder, within the patch. In this work, our aim is to investigate the differences between the spherical descriptors and the cylindrical descriptors. In order to compute the descriptors, the 3D spherical and cylindrical Zernike polynomials are employed. This is important because both the functions are based on the same family of polynomials, and only the symmetry is different. Our experimental results show that the cylindrical descriptor outperforms the spherical descriptor. However, the performances of the two descriptors are similar.

CHIP — Cultural heritage image processing tool

In this paper the authors present the CHIP tool, an image processing software specifically designed for Cultural Heritage applications. The tool offers a wide range of functionalities to carry out analysis and virtual restoration of cultural objects, and fine tuning of the parameters to customize the performance. Simple operations such as color histograms or image features extraction and visualization are made possible for experts in a very simple graphic interface, together with sophisticated and efficient image processing algorithms such as enhancement, dynamic compression and inpainting.