Improving automatic face recognition with user interaction.

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.

A segmentation framework for abdominal organs from CT scans.

OBJECTIVE: Computed tomography images are becoming an invaluable mean for abdominal organ investigation. In the field of medical image processing, some of the current interests are the automatic diagnosis of liver, spleen, and kidney pathologies, and the 3D volume rendering of these abdominal organs. Their automatic segmentation is the first and fundamental step in all these studies, but it is still an open problem. METHODS: In this paper we propose a fully automatic, gray-level based segmentation framework based on a multiplanar fast marching method. The proposed segmentation scheme is general, and employs only established and not critical anatomical knowledge. For this reason, it can be easily adapted to segment different abdominal organs, by overcoming problems due to the high inter- and intra-patient gray-level, and shape variabilities; the extracted volumes are then combined to produce the final results. RESULTS: The system has been evaluated by computing the symmetric volume overlap (SVO) between the automatically segmented (liver and spleen) volumes and the volumes manually traced by radiological experts. The test dataset is composed of 60 images, where 40 images belong to a private dataset, and 20 images to a public one. Liver segmentation has achieved an average SVO congruent with94, which is comparable to the mean intra- and inter-personal variation (96). Spleen segmentation achieves similar, promising results (SVO congruent with93). The comparison of these results with those achieved by active contour models (SVO congruent with90), and topology adaptive snakes (SVO congruent with92) proves the efficacy of our system. CONCLUSIONS: The described segmentation method is a general framework that can be adapted to segment different abdominal organs, achieving promising segmentation results. It has to be noted that its performance could be further improved by incorporating shape based rules.

Liver segmentation from computed tomography scans: a survey and a new algorithm.

OBJECTIVE: In the recent years liver segmentation from computed tomography scans has gained a lot of importance in the field of medical image processing since it is the first and fundamental step of any automated technique for the automatic liver disease diagnosis, liver volume measurement, and 3D liver volume rendering. METHODS: In this paper we report a review study about the semi-automatic and automatic liver segmentation techniques, and we describe our fully automatized method. RESULTS: The survey reveals that automatic liver segmentation is still an open problem since various weaknesses and drawbacks of the proposed works must still be addressed. Our gray-level based liver segmentation method has been developed to tackle all these problems; when tested on 40 patients it achieves satisfactory results, comparable to the mean intra- and inter-observer variation. CONCLUSIONS: We believe that our technique outperforms those presented in the literature; nevertheless, a common test set with its gold standard traced by experts, and a generally accepted performance measure are required to demonstrate it.

A fully automated method for lung nodule detection from postero-anterior chest radiographs.

In the past decades, a great deal of research work has been devoted to the development of systems that could improve radiologists' accuracy in detecting lung nodules. Despite the great efforts, the problem is still open. In this paper, we present a fully automated system processing digital postero-anterior (PA) chest radiographs, that starts by producing an accurate segmentation of the lung field area. The segmented lung area includes even those parts of the lungs hidden behind the heart, the spine, and the diaphragm, which are usually excluded from the methods presented in the literature. This decision is motivated by the fact that lung nodules may be found also in these areas. The segmented area is processed with a simple multiscale method that enhances the visibility of the nodules, and an extraction scheme is then applied to select potential nodules. To reduce the high number of false positives extracted, cost-sensitive support vector machines (SVMs) are trained to recognize the true nodules. Different learning experiments were performed on two different data sets, created by means of feature selection, and employing Gaussian and polynomial SVMs trained with different parameters; the results are reported and compared. With the best SVM models, we obtain about 1.5 false positives per image (fp/image) when sensitivity is approximately equal to 0.71; this number increases to about 2.5 and 4 fp/image when sensitivity is = 0.78 and = 0.85, respectively. For the highest sensitivity (= 0.92 and 1.0), we get 7 or 8 fp/image.