Contact
+49 9131 85 27882
+49 9131 85 27270
Address
Chair of Computer Science 5 (Pattern Recognition)
Martensstr. 3
91058 Erlangen
Germany
Powered by
AmirAbbas Davari M. Sc.
Researcher in the Computer Vision (CV) group at the Pattern Recognition Lab of the Friedrich-Alexander-Universität Erlangen-Nürnberg
-
The amount of training data that is required to train a classifier scales with the dimensionality of the feature data. In hyperspectral remote sensing, feature data can potentially become very high dimensional. However, the amount of training data is oftentimes limited. Thus, one of the core challenges in hyperspectral remote sensing is how to perform multi-class classification using only relatively few training data points. In this project, we try to address this issue by more informative features and enriching the feature matrix with synthetically generated sample points.
GMM supervectors for limited data HS image classification 
Synthetic sample generation for limited data HS image classification 
Journal ArticlesIEEE Geoscience and Remote Sensing Letters, vol. 15, no. 6, pp. 942-946, 2018 (BiBTeX, Who cited this?)Articles in Conference ProceedingsFast Sample Generation with Variational Bayesian for Limited Data Hyperspectral Image ClassificationInternational Geoscience and Remote Sensing Symposium (IGARSS), Valencia, Spain, 22-27.07, pp. tbd, 2018 (BiBTeX, Who cited this?)Computer Analysis of Images and Patterns (17th international Conference on Computer Analysis of Images and Patterns (CAIP)), Ystad, Sweden, 22-24.8.2017, vol. 2, pp. 296-306, 2017 (BiBTeX, Who cited this?)Signal Processing and Communications Applications Conference (SIU), 2015 23th (23th Signal Processing and Communications Applications Conference (SIU)), Malatya, Turkey, 2015, pp. 653-656, 2015 (BiBTeX, Who cited this?)
-
Layers of a phantom drawing 
Old master drawings were mostly created step by step in several layers using different materials. To art historians and restorers, examination of these layers brings various insights into the artistic work process and helps to answer questions about the object, its attribution and its authenticity.
However, these layers typically overlap and are oftentimes difficult to differentiate with the unaided eye. For example, a common layer combination is red chalk under ink. In this project, we investigate image processing pipeline that operate on hyperspectral images to separate such layers.
Articles in Conference ProceedingsHyper-Hue and EMAP on Hyperspectral Images for Supervised Layer Decomposition of Old Master DrawingsInternational Conference on Image Processing (ICIP), Athens, Greece, 7-10.10, pp. tbd, 2018 (BiBTeX, Who cited this?)Extended Papers of the International Symposium on Digital Humanities (DH 2016) (Digital Humanities 2016 (DH 2016)), Linnaeus University, Växjö, Sweden, 7-8/2016, vol. 1, pp. 147-160, 2017 (BiBTeX, Who cited this?)Technical ReportsPattern Recognition Lab, Friedrich-Alexander University, 2017 (BiBTeX, Who cited this?)