• N.Jayachandra
• Dr. A. R. Nadira Banu Kamal

An efficient underwater imaging technique will help the aquaculture industry to intelligently and automatically control the marine species. The major challenges faced with marine animal detection system were limited dataset preparation, low frame rate, poor illumination, segmentation error, large dataset, overlap and occlusion, etc. The proposed preprocessing technique will automatically generate the image dataset for any input undersea water videos taken using different digital technologies like Remotely Operated Vehicle (ROV), Scuba Diving cameras with various image qualities and removes the unwanted frames without region of interest automatically. The dataset includes the following characteristics like image quality, shape, transformation, rotational effect, turbulent effect, two marine species in single frame and the more. Live marine animal in the open sea can be investigated to promote environmental applications like fish farming, meteorological monitoring, animal biometric analysis and monitoring. The proposed methodology incorporates acquiring the video images of the marine species and converting them into frames. Image Pre-processing techniques are applied to remove the artifacts present in the video frame. This method works in uncontrolled objects and environment, as well as difficult situations in acquiring representative samples. The proposed pre-processing method enhances the quality of the image without losing necessary and relevant information in the image. The Point Spread function is used to differentiate noisy and noiseless frames.

Preprocessing, Point spread function, Poor Illumination and Frame Separation

"Real time marine video image preprocessing technique", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.463-470, June-2019, Available :http://www.jetir.org/papers/JETIR1906F71.pdf

"Real time marine video image preprocessing technique", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp463-470, June-2019, Available at : http://www.jetir.org/papers/JETIR1906F71.pdf