• MISS. SHRADDHA VIJAY JOSHI
• Prof. Ashish B. Kharate

In many research areas, intelligent recognition and classification systems gained an important role. The reliability and the success of these systems are depend on the effectiveness of applied data pre-processing techniques and neural networks which can be used for efficient modelling of human’s visual system during the recognition or classification of patterns. In this purposed work, Sonar Image Classification System which was developed to simulate human experience in the recognition of underwater shapes by using Pattern Averaging and Back Propagation Learning Algorithm, will be presented. Experimental results suggest that automatic intelligent classification of these shapes may provide more effective researches in oceanic engineering. There are five main phases i want to used in this proposed work .They are image pre-processing, extraction of Side scan Sonar Images from segmented images, feature extraction, classification of five type of Underwater Shape sonar images. For classification neural classifiers in Fast Fourier Transformed (FFT) and WHT or DCT are used. The main aim of the method is to develop a Sonar Image Classification which was developed to simulate human experience in the recognition of underwater shapes.

Matlab, Nuero Solution Software, Microsoft excel, Various Transform Technique.

"A Review: Classification of Sonar images using neural network approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 2, page no.327-331, February-2019, Available :http://www.jetir.org/papers/JETIR1902548.pdf

"A Review: Classification of Sonar images using neural network approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 2, page no. pp327-331, February-2019, Available at : http://www.jetir.org/papers/JETIR1902548.pdf