Petros Kapsalas

  • Citations Per Year
Learn More
This paper examines a novel approach of corrosion damage analysis based on image processing for quantitative and qualitative evaluation of degradation effects on stone surfaces. This methodology can be applied in situ in association with a variety of nondestructive monitoring schemes, and on images acquired from several imaging modalities, capturing from(More)
A group of four organizations from the MESH consortium (www.mesh-ip.eu) participated this year for the first time in the High Level Feature Extraction track in TRECVID. The partners were Telefónica I+D (TID, Spain), Informatics & Telematics Institute (ITI, Greece), National Technical University of Athens (NTUA, Greece) and Universidad Autónoma de Madrid(More)
In this paper we propose an object detection approach that extracts a limited number of candidate local regions to guide the detection process. The basic idea of the approach is that object location can be determined by clustering points of interest and hierarchically forming candidate regions according to similarity and spatial proximity predicates.(More)
In this paper, we give an overview of the four tasks submitted to TRECVID 2007 by COST292. In shot boundary (SB) detection task, four SB detectors have been developed and the results are merged using two merging algorithms. The framework developed for the high-level feature extraction task comprises four systems. The first system transforms a set of(More)
In this paper, we give an overview of the four tasks submitted to TRECVID 2008 by COST292. The high-level feature extraction framework comprises four systems. The first system transforms a set of low-level descriptors into the semantic space using Latent Semantic Analysis and utilises neural networks for feature detection. The second system uses a(More)
The quantification of black crust formation on exposed stone has been carried out in this work with the aid of non-destructive analytical techniques. The proposed non-destructive Morphologically Fused Detection (MFD) approach, quantifies the deterioration effects encountered on marble surfaces by providing the number, location and shape of deterioration(More)
This paper approaches the non-destructive analysis of corrosion damage by testing and evaluating several image segmentation schemes for the detection of decay areas. The application test bed for algorithmic evaluation considers stonework surfaces for corrosion damage. Each of the detection approaches handles in a different way the background(More)
In this paper we present a new approach towards the extraction of affine image regions based on detecting shape-stable boundaries from a multi-scale image representation. We construct an affine morphological scale space (AMSS) representation [1], which performs anisotropic diffusion while preserving boundaries and being invariant to affine transformations.(More)
This paper presents a new structure-based interest region detector called Shape-Stable Region Boundaries (SSRB) which we use for object class recognition. The SSRB interest operator detects stable boundary regions within the multi-scale morphological image representation [1]. To detect robust boundary regions, we perform multi-scale analysis via anisotropic(More)