A Novel Algorithm for Soil Image Segmentation using Color and Region Based System
Prathik A1, Anuradha J2, Uma K3
1Prathik. A, Research Associate, School of Information Technology and Engineering, Vellore Institute of Technology, Vellore, India.
2Anuradha. J, Associate Professor, School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, India.
3Uma. K, Associate Professor, School of Advanced Science and Engineering, Vellore Institute of Technology, Vellore, India.
Manuscript received on 14 August 2019 | Revised Manuscript received on 20 August 2019 | Manuscript published on 30 August 2019 | PP: 3544-3550 | Volume-8 Issue-10, August 2019 | Retrieval Number: J97620881019/19©BEIESP | DOI: 10.35940/ijitee.J9762.0881019
Open Access | Ethics and 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: In the recent research era data mining is a very essential research domain. The data mining techniques are used to extract significant knowledge in agriculture management. These techniques are time consuming and less expensive than the statistical techniques. Many Researchers develop efficient techniques to improve the productivity of agriculture. This paper developed a new segment method to segment the soil region from other information. This research introduced Color and Region Based segment method to separate the soil region from its background. To evaluate the proposed segmentation the five metrics are used dice coefficient, jaccard index, Sensitivity, Specificity and Precision. The new approach produced 98% accuracy, 98% Sensitivity and 98% Specificity.
Keywords: Data Mining, Segmentation, Classification, Jaccard Index, Sensitivity, Specificity.
Scope of the Article: Classification