The article presents the results of improving endoscopic image classification algorithms in an effort towards applying them in a real-time diagnosis supporting system. Methods for the detection and removal of personal data are presented and discussed. The currently developed recognition algorithms have been improved in terms of accuracy and performance to make them suitable for a real-life implementation. Their test results are shown, which indicate that the performance characteristics required for on-line processing are within reach of the developed methods. Finally, signi ficant differences between the characteristics of images in medical databases and pictures acquired from endoscopic examination videos are discussed together with their in fluence on the classifi cation results.
Authors
Additional information
- Category
- Aktywność konferencyjna
- Type
- publikacja w wydawnictwie zbiorowym recenzowanym (także w materiałach konferencyjnych)
- Language
- angielski
- Publication year
- 2012
