The Experts below are selected from a list of 122652 Experts worldwide ranked by ideXlab platform
Feng Xiaoyi - One of the best experts on this subject based on the ideXlab platform.
-
Face detection based on a novel skin model
Journal of Computer Applications, 2006Co-Authors: Feng XiaoyiAbstract:Face detection based on gray information would lose some useful information of the original image while RGB was changed into gray. A novel skin model was proposed based on the skin chromaticities distribution in YCbCr color space. It was used in face detection combined with face's geometrical structure. The physics-based face database of Oulu university, Finland was used to test our Method. The experiment results show that our Method Performs well in wide illumination changes.
He Dong-jian - One of the best experts on this subject based on the ideXlab platform.
-
Face Detection Method Based on Skin Model and Regional Feature
Computer Engineering, 2008Co-Authors: He Dong-jianAbstract:Precision and speed are two appraisal criterions of face detection system. In order to get accurate precision and fast speed, this paper presents a novel Method based on skin model and regional feature. This Method extracts face pixels using skin model, then gets the face region through an extension Method of mosaic, extracts the lip and eyes utilizing the built models and locates the central points based on the regional feature. Experiments show that the Method Performs easily and locates points accurately.
Joydeep Chandra - One of the best experts on this subject based on the ideXlab platform.
-
COMSNETS - An unsupervised heuristic based approach for author name disambiguation
2018 10th International Conference on Communication Systems & Networks (COMSNETS), 2018Co-Authors: K M Pooja, Samrat Mondal, Joydeep ChandraAbstract:Author name disambiguation is one of the very important problems in scientometrics. Plenty of approaches have been proposed for solving this problem. However, none of the proposed approaches is complete so there is still scope for improvement. In this regard, we have proposed an unsupervised heuristic-based approach for author name disambiguation. The technique also uses the information collected from the web as auxiliary information. Experimental results show that our Method Performs better than the existing Methods.
-
an unsupervised heuristic based approach for author name disambiguation
Communication Systems and Networks, 2018Co-Authors: K M Pooja, Samrat Mondal, Joydeep ChandraAbstract:Author name disambiguation is one of the very important problems in scientometrics. Plenty of approaches have been proposed for solving this problem. However, none of the proposed approaches is complete so there is still scope for improvement. In this regard, we have proposed an unsupervised heuristic-based approach for author name disambiguation. The technique also uses the information collected from the web as auxiliary information. Experimental results show that our Method Performs better than the existing Methods.
Gerrit Sobottka - One of the best experts on this subject based on the ideXlab platform.
-
a gabor filter based approach to leaf vein extraction and cultivar classification
International Conference on Computational Science and Its Applications, 2013Co-Authors: Dominik L Michels, Gerrit SobottkaAbstract:We devise a new algorithm for the extraction of vine leaf veins. Our Method Performs a directional edge tracing on the responses of appropriate adaptive Gabor filters in order to extract the network of the main veins. The respective curvature vectors are used for the classification of different cultivars using support vector machines. We evaluate the advantageous behavior and the robustness of our approach on a test set consisting of 150 light transmitted images of different vine leaves.
-
ICCSA (2) - A Gabor Filter-Based Approach to Leaf Vein Extraction and Cultivar Classification
Lecture Notes in Computer Science, 2013Co-Authors: Dominik L Michels, Gerrit SobottkaAbstract:We devise a new algorithm for the extraction of vine leaf veins. Our Method Performs a directional edge tracing on the responses of appropriate adaptive Gabor filters in order to extract the network of the main veins. The respective curvature vectors are used for the classification of different cultivars using support vector machines. We evaluate the advantageous behavior and the robustness of our approach on a test set consisting of 150 light transmitted images of different vine leaves.
Yannick Charretier - One of the best experts on this subject based on the ideXlab platform.
-
rapid bacterial identification resistance virulence and type profiling using selected reaction monitoring mass spectrometry
Scientific Reports, 2015Co-Authors: Yannick Charretier, Olivier Dauwalder, Christine Franceschi, Elodie Degoutcharmette, Gilles Zambardi, Tiphaine Cecchini, Chloe Bardet, Xavier LacouxAbstract:Mass spectrometry (MS) in Selected Reaction Monitoring (SRM) mode is proposed for in-depth characterisation of microorganisms in a multiplexed analysis. Within 60–80 minutes, the SRM Method Performs microbial identification (I), antibiotic-resistance detection (R), virulence assessment (V) and it provides epidemiological typing information (T). This SRM application is illustrated by the analysis of the human pathogen Staphylococcus aureus, demonstrating its promise for rapid characterisation of bacteria from positive blood cultures of sepsis patients.