Publications by Costantino Grana

In this paper we present an overview of the historical evolution of connected component labeling algorithms, and in particular the ones applied on images stored in raster scan order. This brief survey aims at providing a comprehensive comparison of their performance on modern architectures, since the high availability of memory and the presence of caches make some solutions more suitable and fast. Moreover we propose a new strategy for label propagation based on a 2x2 blocks, which allows to improve the performance of many existing algorithms. The tests are conducted on high resolution images obtained from digitized historical manuscripts and a set of transformations is applied in order to show the algorithms behavior at different image resolutions and with a varying number of labels.

This article presents a framework for automatic semantic annotation of video streams with an ontology that includes concepts expressed using linguistic terms and visual data.

In this paper we present a new optimization technique for the neighborhood computation in connected component labeling focused on images stored in raster scan order. This new technique is based on a 2x2 square block analysis of the image, and it exploits the fact that, when using 8-connection, the pixels of a 2x2 square are all connected to each other. This implies that they will share the same label at the end of the computation. To prove the effectiveness of our proposal, we show a comprehensive comparison of the most used and advanced connected components labeling techniques presented so far. The tests are conducted on high resolution images obtained from digitized historical manuscripts and a set of transformations is applied in order to show the algorithms behavior at different image resolutions and with a varying number of labels.

This work proposes a general approach to optimize the time required to perform a choice in a decision support system, with particular reference to image processing tasks with neighborhood analysis. The decisions are encoded in a decision table paradigm that allows multiple equivalent procedures to be performed for the same situation. An automatic synthesis of the optimal decision tree is implemented in order to generate the most efficient order in which conditions should be considered to minimize the computational requirements.To test out approach, the connected component labeling scenario is considered. Results will show the speedup introduced using an automatically built decision system able to efficiently analyze and explore the neighborhood.

In this work we propose a system for automatic document segmentation to extract graphical elements from historical manuscripts and then to identify significant pictures from them, removing floral and abstract decorations. The system performs a block based analysis by means of color and texture features. The Gradient Spatial Dependency Matrix, a new texture operator particularly effective for this task, is proposed. The feature vectors are processed by an embedding procedure which allows increased performance in later SVM classification. Results for both feature extraction and embedding based classification are reported, supporting the effectiveness of the proposal.

In this paper we present a system for automatic segmentation, annotation and image retrieval based on content, focused on illuminated manuscripts and in particular the Borso D'Este Holy Bible. To enhance the interaction possibilities with this work, full of decorations and illustrations, we exploit some well known document analysis techniques in addition to some new approaches, in order to achieve good segmentation of pages into meaningful visual objects with the relative annotation. We wanted to extend the standard keyword-based retrieval approach in a commentary with a modern visual-based retrieval by appearance similarity: an entire software user interface for exploration and visual search of illuminated manuscripts.

In this work we describe a new approach for texture characterization. Starting from the autocorrelation matrix an elegant description through a mixture of Von Mises distributions is proposed. A compact 6 valued descriptor is produced for each block and served as input to an SVM classifier. Tests are carried out on high resolution illuminated manuscripts images.

Background: To overcome subjectivity and variability in the interpretation of dermoscopic images, image analysis programs, enabling the numerical description of melanocytic lesion images, have been developed. Objectives: Our aim was to assess a method for the description of colours in melanocytic lesion images, based on the subdivision of image colours into red, green and blue clusters. Methods: Melanomas and naevi of the test set were described by means of 23 colour clusters previously selected by a training set comprising 369 melanocytic lesion images. The diagnostic performance obtained by this automated method was compared to sensitivity and specificity of diagnosis of 4 dermatologists. Results: Colour cluster values significantly differed between melanomas and naevi. Moreover, sensitivity and specificity values of computer diagnosis were similar to those achieved by the dermatologists. Conclusion: Our image analysis program based on the assessment of one single parameter has the diagnostic accuracy of dermatologists employing dermoscopy on a regular basis.

In this work, we propose a system for shot comparison directly working on the MPEG-1 stream in the compressed domain, extracting both color, texture and motion features considering all frames with a reasonable computational cost, and results comparable to those obtained on uncompressed keyframes. In particular a summary descriptor for each Group Of Pictures (GOP) is computed and employed for shot characterization and comparison. The Mallows distance allows to match different length clips in a unified framework.

In this paper, we present the dynamic pictorial ontology paradigm for video annotation. Ontologies are often used to describe a given domain for different goals, including description of multimedia data. In the case of video annotation, the visual knowledge cannot be described using only abstract concepts but is more effectively represented in a visual form. To this aim, we introduce visual concepts, elicited from the data set as the most representative prototypes that specialize abstract concepts. The ontology created is intrinsically dynamic since it must embrace the perceptual and visual experience during annotation. Thus visual concepts can change, adapting to the multimedia content analyzed. Motivation for this new ontology paradigm are discussed together with a proposal of a framework for ontology creation, maintenance, and automatic annotation of video. The creation and usage of dynamic pictorial ontologies have been tested for soccer domain exploiting low level perceptual features and higher level domain features.