Texture recognition for frog identification
MetadataShow full item record
CitationCannavo, F., Nunnari, G., Kale, I., & Tek, F. B. (2012). Texture recognition for frog identification. Paper presented at the 25-30. doi:10.1145/2390832.2390839
This paper describes a visual processing technique for automatic frog (Xenopus Laevis sp.) localization and identification. The problem of frog identification is to process and classify an unknown frog image to determine the identity which is recorded previously on an image database. The frog skin pattern (i.e. texture) provides a unique feature for identification. Hence, the study investigates three different kind of features (i.e. Gabor filters, granulometry, threshold set compactness) to extract texture information. The classifier is built on nearest neighbor principle; it assigns the query feature to the database feature which has the minimum distance. Hence, the study investigates different distance measures and compares their performance. The detailed results show that the most successful feature and distance measure is granulometry and weighted L1 norm for the frog identification using skin texture features.