Research Description

The marine environment covers approximately 70% of the earth’s surface. In general, the classification of sea bottom characteristics has become an essential tool for various applications including marine resource investigations, marine environmental monitoring, coastal engineering, geotechnical engineering and scientific research. The traditional means of sediment surveying by direct sampling cannot be used on a large scale, as it is a complex and time-consuming process. Hence, the automatic processing of images with its visual contents based on different features like colour, shape and texture. In this work a texture based feature extraction method is carried to categorize the different types of ocean bottom sediments. The local feature descriptor play a significant role in texture classification. However, in the traditional local binary pattern (LBP) method, image pixels are converted into a binary pattern based on the relationship between centre and neighbourhood pixels. Here, a novel feature extraction method named LNERBP (Local Neighbourhood Edge Responsive Binary Pattern) is introduced to extract and categorize the reliable texture features from images. Initially, the local intensity difference values of pixels are extracted based on a mutual relationship between odd and even pixel value of a 3x3 image patch. Further, the edge information is extracted using the local directional pattern (LDP) method from all images. The edge response of the image is obtained using a kirsch mask in all the eight directions. Then the encoding condition is applied to both the local intensity and the edge information to create a unique descriptor value. Finally, a new learning algorithm called GMJAYA-ELM combines the Gaussian mutated JAYA (GMJAYA) with an extreme learning machine (ELM) for texture classification. The GMJAYA is used to optimize the input weights and hidden biases of single-hidden-layer feed-forward neural networks (SLFN). The experimental results demonstrate that the proposed approach produces higher performance in terms of accuracy and sensitivity across different classes. The proposed algorithm is validated by comparing the results with traditional learning schemes such as PSO-ELM, GA-ELM, ABC-ELM, Birds fly-ELM, and JAYA-ELM, and the result indicates GMJAYA-ELM superiority.

Publications:

Journals:

1. Annalakshmi Ganesan, & Sakthivel Murugan Santhanam, "Fractal adaptive weight synthesized–local directional pattern–based image classification using enhanced tree seed algorithm", Environmental Science and Pollution Research, June 2022, Springer.

2. Annalakshmi G, Sakthivel Murugan S, " A novel feature descriptor based coral image classification using extreme learning machine with ameliorated chimp optimization algorithm", Ecological Informatics, December 2021, Elseiver.

3. Annalakshmi Ganesan, Sakthivel Murugan Santhanam, "Local Neighborhood Edge Responsive Image Descriptor for Texture Classification using Gaussian Mutated JAYA Optimization Algorithm", 2021, Arab. Journ. Sci. & Engi., Springer.

4. Annalakshmi G, Sakthivel Murugan S, Venugopal P, Swetha V, Vaishali S, “Coherence analysis of ambient noises in shallow water for underwater Communication” Journal of Marine Science and Technology, July 2017, Vol. 25, No.3, pp. 311- 318.

5. Harshitha K, Annalakshmi G, Sakthivel Murugan S, "Model predicting sediment transport" in Sea technology Journal, June 2017, Vol.54,pp.22-24.

6. Annalakshmi G, Sakthivel Murugan S, “Underwater acoustic Modem – Challenges, Technology and Applications – A review Survey” International Journal of Oceanography and fisheries, May 2017, Issue No.4, Vol No.2, pp. 001 – 010.

Conferences:

1. Annalakshmi G, Sakthivel Murugan S, “Side Scan Sonar Images Based Ocean Bottom Sediment Classification”, International Symposium on Ocean Technology (SYMPOL 2019), 11 - 13 December 2019, Kochi, India.

2. Annalakshmi G, Sakthivel Murugan S, “Investigations on the geo acoustic properties of sediment in poompuhar”, International Conference on Sonar Systems and sensors (ICONS 2018), 22 - 24 February 2018, Naval physical and Oceanographic Laboratory (NPOL), Kochi, India.

3. Annalakshmi G, Sakthivel Murugan S,"Analyzing the Physical and Chemical Properties of Water Column Nutrients and Sediments along Southeast Coast of India", 4th International Conference on Ocean Engineering (ICOE 2018)", 19 -21 February 2018, Indian Institute of Technology (IIT) Madras, India.

4. Annalakshmi G, Sakthivel Murugan S , “Geo Acoustic Inversion method for analyzing impact due to sediments in underwater channel” 39th Indian Geotechnical Conference 2017 GeoNEst - 2017, 14 - 16 December 2017, IIT Guwahati, India.

5. Annalakshmi G, Sakthivel Murugan S,“Implementation of acoustic Propagation model for predicting ocean bottom in geo - acoustic inversion”, 5th International Conference on Ship and Offshore Technology - India, ICSOT 2017: Innovation in ocean structures”, 7-8 December 2017, IIT Kharagpur, India.

6. Annalakshmi G , Sakthivel Murugan S,“Development of high frequency underwater acoustic modem”, under the theme of Make in India in Young Scientist Conclave of 2^nd India International Science Festival, December 7 - 11, 2016, National Physical laboratory, New Delhi.