1,720,982 research outputs found
A fair ranking method for image database retrieval
No full textThis work aims at organizing the results of query-by-example image database management system so that also the less relevant objects still representing a minority, are presented to the user. Usually, during image retrieval, the objects very similar to the query are ranked in the frist positions and shown to the user. On the contrary, objects that slightly difer from the target image, and that are less numerous, are hardly ever shown to the user. The proposed method increases the chances for a fair retrieval of multimedia data from digital databases
ADAPTIVE RIESZ BASIS DECOMPOSITION FOR IMAGE SEARCH
No full textPublication in the conference proceedings of EUSIPCO, Glasgow, Scotland, 200
SVM for historical sport video classification
No full text""In this work the authors propose a classification method based on Support Vector Machine (SVM) and key frames features extraction to classify historical sport video contents. In the context of the Italian Project, IRMA (Information Retrieval in Multimedia Archives), with the goal to recover and preserve historical videos of proven cultural interest, a data set made up of several hours of videos from the 1960 Olympic games, provided by RAI and Teche RAI, is adopted as testbed. Each video is summarized by its key frames and represented by the features vectors computed in the Laguerre Gauss transformed domain. The high-level video classification starts from these vectors that are the input of the SVM classifier. The experimental results show the effectiveness of the proposed method."
Robust Detail Recognition and Location Technique for Image Retrieval in Digital Repositories
No full textThe polar edge coherence: a quasi blind metric for video quality assessment
No full textAn extremely reduced reference video quality assessment method for video sequences is presented. It is based on the comparison of indices independently calculated for the examined video sequence and for the reference one. The employed metric is based on a cumulative measure of both frame by frame and interframe local edge coherence measures made with pairs of circular harmonic functions. © EURASIP, 2009
Robust detail recognition and location technique for image retrieval in digital repositories
No full textSmooth image inpainting by least square oriented edge prediction
No full text""This paper introduces a new spatial edge oriented algorithm for automatic digital inpainting. The approach is based on the Laguerre Gauss analysis of the structure information of the regions surrounding the damaged portions of the image, extrapolating in automatic way the gradient of the luminance and color in missing areas this estimation is made of a least square fitting algorithm from simplified edge lines that stood on the boundary of missing region. The reconstruction of the unknown parts is automatically obtained by a variational method that uses the predicted gradient information imposing smoothing constraints on luminance and color level. Experiments on a number of images show the effectiveness of the proposed algorithm in smooth areas, as well as in areas with edges and\\\/or textured."
- …
