Pattern Recognition and Machine Learning (Information Science and Statistics)
Pattern Recognition and Machine Learning (Information Science and Statistics)
Texture and color analysis for the automatic classification of the eye lipid layer
IWANN'11 Proceedings of the 11th international conference on Artificial neural networks conference on Advances in computational intelligence - Volume Part II
Hi-index | 0.00 |
The tear lipid layer is not homogeneous among the population and its classification depends on its width. Too thin or too thick films can lead to unhealthy eyes as well as create problems when interacting with contact lenses. This work proposes a preliminary methodology to classify the tear lipid layer according to its texture into four main categories. The proposed methodology works on several stages to detect the region of interest, extract the texture descriptors on colour information and classify these descriptors. The method has been tested on several images from each tear type. In some cases, we obtain classification results over the 90%.