Underwater Object Recognition Using KNN Classifier
In this paper, wavelet transform based method for underwater object recognition is presented. In this approach, input images are decomposed into sub-bands using multi resolutional analysis known as Discrete Wavelet Transform (DWT). Each sub-band in the decomposed image having valuable information about the image, the mean values of every sub-band are assumed as features. This system is tested on underwater object database. The database contains 200 pictures of 100 different objects. The database is considered for the classification based on K-Means Neural Network (KNN) classifier. The outcome shows that maximum recognition accuracy of 94.65% is obtained by this method.
Underwater Object Recognition, DWT, KNN Classifier.
Copyright (c)2017   S.Murugan , Ganesh Babu T R , Srinivasan C
This work is licensed under a Creative Commons Attribution 4.0 International License.