Search results for "methodologie"
showing 10 items of 2141 documents
A Dual Taxonomy for Defects in Digitized Historical Photos
2009
Old photos may be affected by several types of defects. Manual restorers use their own taxonomy to classify damages by which a photo is affected, in order to apply the proper restoration techniques for a specific defect. Once a photo is digitally acquired, defects become part of the image, and their aspect change. This paper wants to be a first attempt to correlate real defects of printed photos, and digital defects of their digitized versions. A dual taxonomy is proposed, for real and digital defects, and used to classify an image dataset, for a posteriori comparative study. Furthermore, a set of digital features is analyzed for digitized images, to identify which of them could be useful f…
Convolutional Neural Network for Blind Mesh Visual Quality Assessment Using 3D Visual Saliency
2018
In this work, we propose a convolutional neural network (CNN) framework to estimate the perceived visual quality of 3D meshes without having access to the reference. The proposed CNN architecture is fed by small patches selected carefully according to their level of saliency. To do so, the visual saliency of the 3D mesh is computed, then we render 2D projections from the 3D mesh and its corresponding 3D saliency map. Afterward, the obtained views are split to obtain 2D small patches that pass through a saliency filter to select the most relevant patches. Experiments are conducted on two MVQ assessment databases, and the results show that the trained CNN achieves good rates in terms of corre…
SVG rendering for internet imaging
2006
The SVG (scalable vector graphics) standard allows representing complex graphical scenes by a collection of graphic vectorial-based primitives, offering several advantages with respect to classical raster images such as: scalability, resolution independence, etc. In this paper we present a full comparison between some advanced raster to SVG algorithms: SWaterG, SVGenie, SVGWave and some commercial tools. SWaterG works by a watershed decomposition coupled with some ad-hoc heuristics, SVGenie and SVGWave use a polygonalization based respectively on data dependent and wavelet triangulation. The results obtained by SWaterG, SVGenie and SVGWave are satisfactory both in terms of perceptual measur…
Mining Interpretable Rules for Sentiment and Semantic Relation Analysis Using Tsetlin Machines
2020
Tsetlin Machines (TMs) are an interpretable pattern recognition approach that captures patterns with high discriminative power from data. Patterns are represented as conjunctive clauses in propositional logic, produced using bandit-learning in the form of Tsetlin Automata. In this work, we propose a TM-based approach to two common Natural Language Processing (NLP) tasks, viz. Sentiment Analysis and Semantic Relation Categorization. By performing frequent itemset mining on the patterns produced, we show that they follow existing expert-verified rule-sets or lexicons. Further, our comparison with other widely used machine learning techniques indicates that the TM approach helps maintain inter…
Detection of TV commercials
2004
This paper presents a system that labels TV shots either as commercial or program shots. The system uses two observations: logo presence and shot duration. These observations are modeled using HMMs, and a Viterbi decoder is finally used for shot labeling. The system has been tested on several hours of real video, achieving more than 99% correct labeling.
MedAI: Transparency in Medical Image Segmentation
2021
MedAI: Transparency in Medical Image Segmentation is a challenge held for the first time at the Nordic AI Meet that focuses on medical image segmentation and transparency in machine learning (ML)-based systems. We propose three tasks to meet specific gastrointestinal image segmentation challenges collected from experts within the field, including two separate segmentation scenarios and one scenario on transparent ML systems. The latter emphasizes the need for explainable and interpretable ML algorithms. We provide a development dataset for the participants to train their ML models, tested on a concealed test dataset.
<title>Dynamic integration of multiple data mining techniques in a knowledge discovery management system</title>
1999
One of the most important directions in improvement of data mining and knowledge discovery, is the integration of multiple classification techniques of an ensemble of classifiers. An integration technique should be able to estimate and select the most appropriate component classifiers from the ensemble. We present two variations of an advanced dynamic integration technique with two distance metrics. The technique is one variation of the stacked generalization method, with an assumption that each of the component classifiers is the best one, inside a certain sub area of the entire domain area. Our technique includes two phases: the learning phase and the application phase. During the learnin…
Automatic identification of word translations from unrelated English and German corpora
1999
Algorithms for the alignment of words in translated texts are well established. However, only recently new approaches have been proposed to identify word translations from non-parallel or even unrelated texts. This task is more difficult, because most statistical clues useful in the processing of parallel texts cannot be applied to non-parallel texts. Whereas for parallel texts in some studies up to 99% of the word alignments have been shown to be correct, the accuracy for non-parallel texts has been around 30% up to now. The current study, which is based on the assumption that there is a correlation between the patterns of word co-occurrences in corpora of different languages, makes a sign…
Robotic Platform for Automated Search and Rescue Missions of Humans
2013
We present a novel type of model incorporating a special remote life signals sensing optical system on top of a controllable robotic platform. The remote sensing system consists of a laser and a camera. By properly adapting our optics and by applying a proper image processing algorithm we can sense within the field of view, illuminated by the laser and imaged by the camera, the heartbeats and the blood pulse pressure of subjects (even several simultaneously). The task is to use the developed robotic system for search and rescue mission such as saving survivals from a fire.
3D Scene Reconstruction Using Kinect
2014
The issue of the automatic reconstruction of 3D scenes has been addressed in several chapters over the last few years. Many of them describe techniques for processing stereo vision or range images captured by high quality range sensors. However, due to the high price of such input devices, most of the methods proposed in the literature are not suitable for real-world scenarios. This chapter proposes a method designed to reconstruct 3D scenes perceived by means of a cheap device, namely the Kinect sensor. The scene is efficiently represented as a composition of superquadric shapes so as to obtain a compact description of environment, however complex it may be. The approach proposed here is i…