G
Gerald Schaefer
Researcher at Loughborough University
Publications - 474
Citations - 8133
Gerald Schaefer is an academic researcher from Loughborough University. The author has contributed to research in topics: Image retrieval & Automatic image annotation. The author has an hindex of 35, co-authored 465 publications receiving 6835 citations. Previous affiliations of Gerald Schaefer include University of Manitoba & University of East Anglia.
Papers
More filters
Proceedings ArticleDOI
Classification of melanocytic skin lesions from non-melanocytic lesions
TL;DR: A new tumor area extraction algorithm is developed to develop a pre-processor of an automated melanoma screening system and it is confirmed that this algorithm is capable of handling different dermoscopy images not only those of NoMSLs but also MSLs as well.
Journal ArticleDOI
A hybrid classifier committee for analysing asymmetry features in breast thermograms
Bartosz Krawczyk,Gerald Schaefer +1 more
TL;DR: An approach to analysing breast thermograms based on image features and a hybrid multiple classifier system that convincingly shows the approach to provide excellent classification accuracy and sensitivity but also to outperform both canonical classification approaches as well as other classifier ensembles designed for imbalanced datasets.
Proceedings ArticleDOI
Hue that is invariant to brightness and gamma
TL;DR: It is shown that a simple photometric ratio in log RGB space cancels both brightness and gamma, and some simple manipulation reveals that the brightness/gamma invariant can usefully be interpreted as a hue in a log opponent colour space.
Journal ArticleDOI
A hybrid cost-sensitive ensemble for imbalanced breast thermogram classification
TL;DR: A hybrid cost-sensitive classifier ensemble can facilitate a highly accurate early diagnostic of breast cancer based on thermogram features and overcomes the difficulties posed by the imbalanced distribution of patients in the two analysed groups.
Proceedings ArticleDOI
Contrast enhancement in dermoscopy images by maximizing a histogram bimodality measure
TL;DR: Experiments demonstrate that this adaptive optimization scheme increases the contrast between the lesion and the background skin, and leads to a more accurate separation of the two regions using Otsu's thresholding method.