Publications by Costantino Grana

Typical processes of image representation comprehend initial region segmentation followed by a description of single regions’ feature and their relationships. Then a graph model can be exploited in order to integrate the knowledge of the specific regions (that are the attributed relational graph’s (ARG) nodes) and the regions’ relations (that are the ARG’s edges). In this work we use color features to guide region segmentation, geometric features to characterize regions one by one and topological features (and in particular inclusion) to describe regions’ relationships. Guided by the inclusion property we define the Topological Tree (TT) as an image representation model that exploiting the transitive property of inclusion, uses the adjacency and inclusion topological features. We propose an approach based on a recursive version of fuzzy c-means to construct the topological tree directly from the initial image, performing both segmentation and TT construction. The TT can be exploited in many applications of image analysis and image retrieval by similarity in those contexts where inclusion is a key feature: we propose an applicative case of analysis of dermatological images to support the melanoma diagnosis.In this paper describe details of the TT algorithm, including the management of not ideality and an approximate measure of tree similarity in order to retrieve skin lesion with a similar TT-based description.

In this work we present a framework for on-the-fly video transcoding that exploits computer vision-based techniques to adapt the Web access to the user requirements. Theproposed transcoding approach aims at coping with both user bandwidth and resources capabilities, and with user interests in the video's content. We propose an object-basedsemantic transcoding that, according to the user-dened classes of relevance, applies different transcoding techniques to the objects segmented in a scene. Object extraction is provided by on-the-fly video processing, without manual annotation. Multiple transcoding policies are reviewed and a performance evaluation metric based on the Weighted Mean Square Error (and corresponding PSNR), that takes into account the perceptual user requirements by means of classes of relevance, is dened. Results are analyzed by varying transcoding techniques, bandwidth requirements and video types (with indoor and outdoor scenes), showing that the use of semantics can dramatically improve the bandwidth to distortion ratio.

In this work we present a transcoding framework and an object-based technique to adapt live and stored videos to the user bandwidth and resources capabilities.Multiple transcoding policies are reviewed and a performance evaluation metric based on the Weighted Mean Square Error that allows different classes of relevance is presented.We present results for different transcoding policies and for different bandwidth requirements, showing that the use of semantic can improve the bandwidth to distortion ratio.

In this paper we define a Topological Tree (TT) as a knowledge representation method that aims to describe important visual and spatial features of image regions, namely the color similarity, the inclusion and the spatial adjacency. The topological tree exhibits some interesting properties that can be exploited to extract knowledge from images for information retrieval, image understanding and diagnosis purposes. Examples of applications in dermatology are described. The TT can be constructed after segmentation, by computing the spatial relationships of regions or can be generated directly during the segmentation: to this aim we present a novel recursive fuzzy c-means (FCM) clustering algorithm based on the Principal Component Analysis of the color space. The recursive FCM proves to be effective for underlining the adjacency and inclusion property of regions.

Clinical evaluation of pigmented skin lesion images is subjective and can lead to different results depending on the examiner’s experience, also applying semiquantitative methods such as the ABCD rule for dermatoscopy. In order to increase the reproducibility of clinical judgement, a method to automatically reproduce the A (Asymmetry) and the B (Border) parameters of the ABCD rule was developed. One hundred and fourteen images of melanomas acquired by a digital videomicroscope with a 20x magnification were studied.Clinical evaluation: a clinical judgement of asymmetry of the shape and pigment distribution along 2 axes were performed by 0–2 scoring system. For the evaluation of the border cut-off, a score ranging to 0 from 8 was attributed to each lesion on the basis of the number of segments with an abrupt edge interruption of the pigmentation. Computer elaboration: after automatic border detection, major and minor axes were obtained and ‘shape asymmetry’ on each axis was calculated considering the proportion of overlapping pixels. A correspondence lower than 90% was selected as the threshold for asymmetry. The ‘pigment distribution asymmetry’ on each axis was calculated comparing the portion of the dark area, obtained by the median cut algorithm, in the two halves of the lesion. A correspondence lower than 80% was considered as the threshold for asymmetry. In order to numerically describe the gradient at the border, the lesion border was divided into 8 segments and the change in lightness values along a 30 pixel long segment centered on the lesion border, expressed as the slope of the curve, was considered. Threshold for abrupt border cut-off was set by a slope greater than 3.609Results: a good correlation between clinical evaluation and computer elaboration was found for shape asymmetry (rho=0.698;p<0.001), pigment distribution asymmetry (rho=0.428;p<0.001) and number of borders with an abrupt cut-off (rho=0.834;p<0.001).

This work presents a general-purpose method for moving visual object segmentation in videos and discusses results attained on sequences of PETS2002 datasets. The proposed approach, called Sakbot, exploits color and motion information to detect objects, shadows and ghosts, i.e. foreground objects with apparent motion. The method is based on background suppression in the color space. The main peculiarity of the approach is the exploitation of motion and shadow information to selectively update the background, improving the statistical background model with the knowledge of detected objects. The approach is able to detect Moving Visual Objects (MVOs), and stopped objects too, since the motion status is maintained at the level of tracking module. HSV color space is exploited for shadow detection in order to enhance both segmentation and background update. Time measures and precision performance analysis in tracking and counting people is provided for surveillance and monitoring purposes.

Although an improvement of the diagnostic accuracy of pigmented skin lesions (PSL) has been achieved by the epiluminescence technique (ELM), the interpretation of ELM criteria is often confusing, especially for inexperienced observers. To enhance the reproducibility and accuracy of clinical judgement and the training of inexperienced operators, programs for PSL image analysis and algorithms for automatic diagnosis have been developed. The aim of our study was to develop a new program for PSL image analysis, able to describe different aspects of PSLs and to test its descriptive capability on PSL acquired by means of a digital videomicroscope (VMS 110A, Scalar Mitsubishi, Japan) using 20-fold magnification. After automatic border identification and baricentre determination, some geometric parameters, describing shape characteristics of the lesion, were calculated. A mathematical description of the border cut-off was obtained. The texture of the lesion was calculated applying the co-occurrence matrix at different image resolutions. Dark areas and colour areas, referring to selected colour groups, were obtained and their aspect and distribution were mathematically defined and calculated. 281 common nevi and 117 melanomas were numerically described by our program and the capability of the mathematical parameters to distinguish between benign and malignant lesion was tested by means of discriminant analysis. Significant differences were observed for most parameters between different PSL populations. The automatic classification enabled the distinction between melanomas and nevi with a 100% sensitivity and a 82.9% specificity.

In this paper we define a novel approach for image segmentation into regions which focuses on both visual and topological cues, namely color similarity, inclusion and spatial adjacency. Many color clustering algorithms have been proposed in the past for skin lesion images but none exploits explicitly the inclusion properties between regions. Our algorithm is based on a recursive version of fuzzy c-means (FCM) clustering algorithm in the 2D color histogram constructed by Principal Component Analysis (PCA) of the color space. The distinctive feature of the proposal is that recursion is guided by the evaluation of adjacency and mutual inclusion properties of extracted regions; then, the recursive analysis addresses only included regions or regions with a not-negligible size. This approach allows a coarse-to-fine segmentation which focuses the attention on the inner parts of the images, in order to highlight the internal structure of the object depicted in the image. This could be particularly useful in many applications, especially in the biomedical image analysis. In this work we apply the technique to the segmentation of skin lesions in dermatoscopic images. It could be a suitable support for the diagnosis of skin melanoma, since dermatologists are interested in the analysis of the spatial relations, the symmetrical positions and the inclusion of regions.

Image analysis tools are spreading in dermatology since the introduction of dermoscopy (epiluminescence microscopy), in the effort of algorithmically reproducing clinical evaluations. Color-based region segmentation of skin lesions is one of the key steps for correctly collecting statistics that can help clinicians in their diagnosis. Nevertheless, an efficient and accurate region segmentation algorithm has not been proposed in the literatureyet. This work proposes an iterative fuzzy c-means clustering algorithm based on PCA with the Karhunen-Loève transform of the color space. A topological tree is provided to store the mutual inclusions of the regions and then used to summarize the structural properties of the skin lesion. Preliminary experimental results are presented and discussed.

In this paper we present transcoding techniques for a video server architecture that enables the user to access live video streams by using different devices with different capabilities. For live videos, annotation methods cannot be exploited. Instead we propose methods of on-the-fly transcoding that adapt the video content with respect to the user resources and the video semantic. Thus we propose an object-based transcoding with "classes of relevance" (for instance People, Face and Background). To compare the different strategies we propose a metric based on the Weighted Mean Square Error that allows the analysis of different application scenarios by means of a class-wise distortion measure. The obtained results show that the use of semantic can improve the bandwidth to distortion ratio significantly.