Face recognition systems aim to recognize the identity of a person depicted in a photograph by comparing it against a gallery of prerecorded images. Current systems perform quite well in controlled scenarios, but they allow for none or little interaction in case of mistakes due to the low quality of images or to algorithmic limitations. Following the needs and suggestions of investigators, we present a guided user interface that allows to adjust from a fully automatic to a fully assisted modality of execution, according to the difficulty of the task and to amount of available information (gender, age, etc.): the user can generally rely on automatic execution and intervene only on a limited number of examples when a failure is automatically detected or when the quality of intermediate results is deemed unsatisfactory. The interface runs on top of a preexistent automatic face recognition algorithm in such a way to guarantee full control over the execution flow and to exploit the peculiarities of the underlying image processing techniques. The viability of the proposed solution is tested on a classic face identification task run on a standard publicly available database (the XM2VTS), assessing the improvement to user interaction over the automatic system performance.

Higher order spectra analysis can be employed to reconstruct a corrupted signal via the third-order spectrum, i.e. the bispectrum. However, this technique is plagued by an unknown misplacement of the origin of the restored signal, this being true both for 1D signals such as audio and 2D signals such as images. In this contribution we tackle and solve the misplacement in the 1D case. We first present the details of the problem and the solution adopted, then we test our method on both synthetic and real 1D signals. Finally we simulate 1D turbulent signals and restore them, showing that our algorithm, once extended to higher dimensions, could be well suited for the restoration of images affected by air turbulence distortion.

Forensic science is already taking benefits from synchrotron radiation (SR) sources in trace evidence analysis. In this contribution we show a multi-technique approach to study fingerprints from the morphological and chemical point of view using SR based techniques such as Fourier transform infrared microspectroscopy (FTIRMS), X-ray fluorescence (XRF), X-ray absorption structure (XAS), and phase contrast microradiography. Both uncontaminated and gunshot residue contaminated human fingerprints were deposited on lightly doped silicon wafers and on poly-ethylene-terephthalate foils. For the uncontaminated fingerprints an univariate approach of functional groups mapping to model FT-IRMS data was used to get the morphology and the organic compounds map. For the gunshot residue contaminated fingerprints, after a preliminary elemental analysis using XRF, microradiography just below and above the absorption edge of the elements of interest has been used to map the contaminants within the fingerprint. Finally, XAS allowed us to determine the chemical state of the different elements. The next step will be fusing the above information in order to produce an exhaustive and easily understandable evidence.

Shoe marks found on the crime scene are invaluable for the identification of the culprit when no other piece of evidence is available. Thus semi-automatic and automatic systems have been recently proposed to find the make and model of the footwear that left the shoe marks. The systems proposed up to now have two main drawbacks, as they (i) are generally not based on rotation and translation invariant descriptions, and (ii) are tested on synthetic shoe marks, i.e. on shoeprints with added synthetic noise. Here we show the results of a translation and rotation invariant description based on the Fourier transform properties: the test is made on both synthetic and real shoe marks and a comparison with algorithms proposed by others is presented.

Shoeprints found on the crime scene are useful to understand the crime dynamics. Several semi-automatic and automatic systems have already been proposed to identify the make and model of the shoe that left the mark on the crime scene, however these systems have been tested on simulated shoe marks, i.e. not coming from real crimes scene but artificially synthesized with different noise adding techniques. In this paper, we propose descriptors based on appropriate information of shoeprint pattern in the frequency domain, to retrieve the footwear that produced the shoe mark. Suitable operators, as for example the Mahalanobis distance map, are then selected and involved in the calculation of these descriptors, in order to reduce noise and enhance shoeprint textures found in real cases. In fact and differently from others, the performance test of this algorithm is done on shoe marks coming from real crime scenes, and the results are promising.

Shoeprints found on the crime scene are useful to understand the crime dynamics; currently some systems have been proposed to automatically identify the make and model of the shoe that left the mark on the crime scene. However these systems have been tested on shoe marks synthesized artificially with different noise adding techniques. Here we present an image retrieval algorithm which combines the information of the phase of the Fourier transform of the shoe mark images with the power spectral density of the Fourier transform calculated on their Mahalanobis map. Differently from others, the algorithm performance is tested on real shoe marks coming from crime scenes. The proposed method is compared with other works and some preprocessing operators are also introduced and selected to reduce noise and enhance the matching probability. (6 pages)

Shoe marks found on crime scenes can lead to the identification of the culprit, thus it is important to find the make and model of the footwear that left the marks. Some semi-automatic and automatic systems have been proposed in literature for the purpose, but they have been all tested on synthetic shoe marks, i.e. sole prints with added synthetic noise. Here we make a comparison of some of the methods reported in literature, both on synthetic and on real shoe marks coming from crime scenes: this last comparison has never been done before. Moreover we propose a new matching algorithm, based on the Mahalanobis distance, which is also compared to the other methods. Results show that simulated shoe marks are not suited to test a footwear retrieval system aimed at finding the shoe make and model of a shoe mark found on the crime scene.

Shoeprints found on the crime scene contain useful information for the investigator: being able to identify the make and model of the shoe that left the mark on the crime scene is important for the culprit identification. Semi-automatic and automatic systems have already been proposed in the literature to face the problem, however all previous works have dealt with synthetic cases, i.e. shoe marks which have not been taken from a real crime scene but are artificially generated with different noise adding techniques. Here we propose a descriptor based on the Mahalanobis distance for the retrieval of shoeprint images. The performance test of the proposed descriptor is performed on real crime scenes shoe marks and the results are promising.

Shoeprints found on the crime scene are useful to understand the crime dynamics. Several semi-automatic and automatic systems have already been proposed to identify the make and model of the shoe that left the mark on the crime scene, however these systems have been tested on simulated shoe marks, i.e. not coming from real crime scene but artificially synthesized with different noise adding techniques. In this paper, we propose a novel descriptor, based on the Mahalanobis distance, to retrieve the footwear that produced the shoe mark. Differently from others, the performance test of the selected descriptor is done on shoe marks coming from real crime scenes, and the results are promising.