Computerized Growth Analysis of Seeds Using Deep Learning Method
D. Sivakumar1, K. Suriya Krishnaan2, P. Akshaya3, G. V. Anuja4, G. T. Devadharshini.5
1D.Sivakumar, Professor, Department of Electronics and Communication Engineering, Easwari Engineering College, Chennai (Tamil Nadu), India.
2K.Suriya Krishnaan, Asst. Professor, Department of Electronics and Communication Engineering, Easwari Engineering College, Chennai (Tamil Nadu), India.
3P. Akshaya, U.G. Students, Department of Electronics and Communication Engineering, Easwari Engineering College, Chennai (Tamil Nadu), India.
4G. V. Anuja, U.G. Students, Department of Electronics and Communication Engineering, Easwari Engineering College, Chennai (Tamil Nadu), India.
5G. T. Devadharshini, U.G. Students, Department of Electronics and Communication Engineering, Easwari Engineering College, Chennai (Tamil Nadu), India.
Manuscript received on 12 May 2019 | Revised Manuscript received on 19 May 2019 | Manuscript Published on 23 May 2019 | PP: 1885-1892 | Volume-7 Issue-6S5 April 2019 | Retrieval Number: F13380476S519/2019©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Seed Germination is ideal and most important for seed quality which has an impact on its production as well as its yield. Presently germination rate calculation is done manually with the help of trained persons which is a very tiresome process. Through this project, we present a system for computerized and automatic determination of germination rate using some high-level techniques in computer vision and machine learning. We analyze the germination rate of seeds by comparing it with a large number of datasets comprising of germinated and non-germinated samples using neural networks. This analysis is done by considering the root of the germinated seed. Therefore this method is known as Multi-Level Root Metric Ratio(MLRM) method.
Keywords: Computer Vision, Machine Learning, Multi-Level Root Metric Ratio Method.
Scope of the Article: Deep Learning