Fingerprint Recognition in Forensic Scenarios.

Fingerprints are unique patterns used as biometric keys because they allow an individual to be unambiguously identified, making their application in the forensic field a common practice. The design of a system that can match the details of different images is still an open problem, especially when applied to large databases or, to real-time applications in forensic scenarios using mobile devices. Fingerprints collected at a crime scene are often manually processed to find those that are relevant to solving the crime. This work proposes an efficient methodology that can be applied in real time to reduce the manual work in crime scene investigations that consumes time and human resources. The proposed methodology includes four steps: (i) image pre-processing using oriented Gabor filters; (ii) the extraction of minutiae using a variant of the Crossing Numbers method which include a novel ROI definition through convex hull and erosion followed by replacing two or more very close minutiae with an average minutiae; (iii) the creation of a model that represents each minutia through the characteristics of a set of polygons including neighboring minutiae; (iv) the individual search of a match for each minutia in different images using metrics on the absolute and relative errors. While in the literature most methodologies look to validate the entire fingerprint model, connecting the minutiae or using minutiae triplets, we validate each minutia individually using n-vertex polygons whose vertices are neighbor minutiae that surround the reference. Our method also reveals robustness against false minutiae since several polygons are used to represent the same minutia, there is a possibility that even if there are false minutia, the true polygon is present and identified; in addition, our method is immune to rotations and translations. The results show that the proposed methodology can be applied in real time in standard hardware implementation, with images of arbitrary orientations.

Multispectral Facial Recognition in the Wild.

This work proposes a multi-spectral face recognition system in an uncontrolled environment, aiming to identify or authenticate identities (people) through their facial images. Face recognition systems in uncontrolled environments have shown impressive performance improvements over recent decades. However, most are limited to the use of a single spectral band in the visible spectrum. The use of multi-spectral images makes it possible to collect information that is not obtainable in the visible spectrum when certain occlusions exist (e.g., fog or plastic materials) and in low- or no-light environments. The proposed work uses the scores obtained by face recognition systems in different spectral bands to make a joint final decision in identification. The evaluation of different methods for each of the components of a face recognition system allowed the most suitable ones for a multi-spectral face recognition system in an uncontrolled environment to be selected. The experimental results, expressed in Rank-1 scores, were 99.5% and 99.6% in the TUFTS multi-spectral database with pose variation and expression variation, respectively, and 100.0% in the CASIA NIR-VIS 2.0 database, indicating that the use of multi-spectral images in an uncontrolled environment is advantageous when compared with the use of single spectral band images.

Multispectral Face Recognition Using Transfer Learning with Adaptation of Domain Specific Units.

Facial recognition is a method of identifying or authenticating the identity of people through their faces. Nowadays, facial recognition systems that use multispectral images achieve better results than those that use only visible spectral band images. In this work, a novel architecture for facial recognition that uses multiple deep convolutional neural networks and multispectral images is proposed. A domain-specific transfer-learning methodology applied to a deep neural network pre-trained in RGB images is shown to generalize well to the multispectral domain. We also propose a skin detector module for forgery detection. Several experiments were planned to assess the performance of our methods. First, we evaluate the performance of the forgery detection module using face masks and coverings of different materials. A second study was carried out with the objective of tuning the parameters of our domain-specific transfer-learning methodology, in particular which layers of the pre-trained network should be retrained to obtain good adaptation to multispectral images. A third study was conducted to evaluate the performance of support vector machines (SVM) and k-nearest neighbor classifiers using the embeddings obtained from the trained neural network. Finally, we compare the proposed method with other state-of-the-art approaches. The experimental results show performance improvements in the Tufts and CASIA NIR-VIS 2.0 multispectral databases, with a rank-1 score of 99.7% and 99.8%, respectively.

Enhanced Classification of Interstitial Lung Disease Patterns in HRCT Images Using Differential Lacunarity.

The analysis and interpretation of high-resolution computed tomography (HRCT) images of the chest in the presence of interstitial lung disease (ILD) is a time-consuming task which requires experience. In this paper, a computer-aided diagnosis (CAD) scheme is proposed to assist radiologists in the differentiation of lung patterns associated with ILD and healthy lung parenchyma. Regions of interest were described by a set of texture attributes extracted using differential lacunarity (DLac) and classical methods of statistical texture analysis. The proposed strategy to compute DLac allowed a multiscale texture analysis, while maintaining sensitivity to small details. Support Vector Machines were employed to distinguish between lung patterns. Training and model selection were performed over a stratified 10-fold cross-validation (CV). Dimensional reduction was made based on stepwise regression (F-test, p value < 0.01) during CV. An accuracy of 95.8 ± 2.2% in the differentiation of normal lung pattern from ILD patterns and an overall accuracy of 94.5 ± 2.1% in a multiclass scenario revealed the potential of the proposed CAD in clinical practice. Experimental results showed that the performance of the CAD was improved by combining multiscale DLac with classical statistical texture analysis.

Algorithm versus physicians variability evaluation in the cardiac chambers extraction.

Congenital heart diseases are present in eight of every 1000 newborns. The diagnosis of those pathologies usually depends on the available imaging methods. A correct diagnosis requires a detailed observation of the heart chambers, wall motions, valves function, and quantitative evaluation of the cavity volumes. For that goal numerous automatic algorithms have been proposed to segment the echocardiographic images. In this paper, the authors evaluate the performance of a level set algorithm based on the phase symmetry approach and on a new logarithmic-based stopping function to extract the heart cavity contours simultaneously, and in a fully automatic way. The extracted cardiac borders are then statistically compared with the ones manually sketched by four physicians on a set of 240 cavities. Nonparametric statistical tests are conducted on the data using several figures of merit, in order to study the inter- and intraobserver variabilities among the four physicians and the level set algorithm, concerning to the extracted contours. The results show there is a great concordance about all the used similarity indexes. A higher interobserver variability was found among the physicians than the variability obtained when the algorithm versus physician performance is compared. The statistical analysis suggests the proposed algorithm produces results similar to the ones provided by the physicians.

A method for corneal nerves automatic segmentation and morphometric analysis.

The segmentation and morphometric analysis of corneal sub-basal nerves, from corneal confocal microscopy images, has gained recently an increased interest. This interest arises from the possibility of using changes in these nerves as the basis of a simple and non-invasive method for early detection and follow-up of peripheral diabetic neuropathy, a major cause of chronic disability in diabetic patients. Here, we propose one method for automatic segmentation and analysis of corneal nerves from images obtained in vivo through corneal confocal microscopy. The method is capable of segmenting corneal nerves, with sensitivity near 90% and a percentage of false recognitions with an average of 5.3%. The nerves tortuosity was calculated and shows statistically significant differences between healthy controls and diabetic individuals, in accordance to what is reported in the literature.

Fast volumetric registration method for tumor follow-up in pulmonary CT exams.

An oncological patient may go through several tomographic acquisitions during a period of time, needing an appropriate registration. We propose an automatic volumetric intrapatient registration method for tumor follow-up in pulmonary CT exams. The performance of our method is evaluated and compared with other registration methods based on optimization techniques. We also compared the metrics behavior to inspect which metric is more sensitive to changes due to the presence of lung tumors.

Phase symmetry approach applied to children heart chambers segmentation: a comparative study.

Segmentation of echocardiographic images presents a great challenge because these images contain strong speckle noise and artifacts. Besides, most ultrasound segmentation methods are semi-automatic, requiring initial contour to be manually identified in the images. In this work, we propose an algorithm based on the phase symmetry approach and level set evolution, in order to extract simultaneously all heart cavities in a fully automatic way. The level set evolution uses a new logarithmic based stopping function, which demonstrates to perform well in the boundary extraction. We compared our method with other level set approaches, the watershed technique, and the manual segmentation made by two physicians. The experimental work was based on echocardiography images of children. Similarity metrics, namely Pratt Function, Pixel Mean Error, and Similarity Angle have been used for the performance evaluation of the different methods. The results indicate that our method has a performance at least 4% superior to the other methods able to segment the four chambers. Even for the two worst boundary extraction cases (right ventricle and left atrium) the performance of the proposed method still is better than the other techniques.

Image denoising methods for tumor discrimination in high-resolution computed tomography.

Pixel accuracy in images from high-resolution computed tomography (HRCT) is ultimately limited by reconstruction error and noise. While for visual analysis this may not be relevant, for computer-aided quantitative analysis in either densitometric, or shape studies aiming at accurate results, the impact of pixel uncertainty must be taken into consideration. In this work, we study several denoising methods: geometric mean filter, Wiener filtering, and wavelet denoising. The performance of each method was assessed through visual inspection, profile region intensity analysis, and global figures of merit, using images from brain and thoracic phantoms, as well as several real thoracic HRCT images.

Quantitative evaluation of a pulmonary contour segmentation algorithm in X-ray computed tomography images.

RATIONALE AND OBJECTIVES: Pulmonary contour extraction from thoracic x-ray computed tomography images is a mandatory preprocessing step in many automated or semiautomated analysis tasks. This study was conducted to quantitatively assess the performance of a method for pulmonary contour extraction and region identification. MATERIALS AND METHODS: The automatically extracted contours were statistically compared with manually drawn pulmonary contours detected by six radiologists on a set of 30 images. Exploratory data analysis, nonparametric statistical tests, and multivariate analysis were used, on the data obtained using several figures of merit, to perform a study of the interobserver variability among the six radiologists and the contour extraction method. The intraobserver variability of two human observers was also studied. RESULTS: In addition to a strong consistency among all of the quality indexes used, a wider interobserver variability was found among the radiologists than the variability of the contour extraction method when compared with each radiologist. The extraction method exhibits a similar behavior (as a pulmonary contour detector), to the six radiologists, for the used image set. CONCLUSION: As an overall result of the application of this evaluation methodology, the consistency and accuracy of the contour extraction method was confirmed to be adequate for most of the quantitative requirements of radiologists. This evaluation methodology could be applied to other scenarios.