Abstract
The Mel-Frequency Cepstral Coefficients (MFCCs) feature extraction approach can be used for corneal pattern recognition, and hence in the diagnosis of corneal diseases. In this method, cepstral features are extracted from a group of corneal images. Images are first transformed to 1-D signals by lexicographic ordering, and then MFCCs and polynomial shaping coefficients are extracted to form a database of features, which can be used to train a neural network. With the same method used in the training phase, features are extracted from a new group of images. These features can be tested with the neural network. Different transform domains can be used for this purpose. Experimental results show that the Discrete Cosine Transform (DCT) is the most suitable domain for feature extraction. The method in this paper is limited to feature extraction for pattern recognition and the automatic diagnosis case is left for future work.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
