Open AccessImage Analysis Techniqueson Phenotype for Plant System
Author(s) -
K. Sudha Rani
Publication year - 2019
Publication title -
international journal of engineering and advanced technology
Language(s) - English
Resource type - Journals
ISSN - 2249-8958
DOI - 10.35940/ijeat.a1125.1291s419
Subject(s) - phenomics , artificial intelligence , convolutional neural network , deep learning , computer science , automation , machine learning , economic shortage , phenotypic trait , identification (biology) , phenotype , field (mathematics) , data science , biology , engineering , genomics , ecology , mathematics , mechanical engineering , biochemistry , linguistics , philosophy , genome , government (linguistics) , gene , pure mathematics
In recent years, there is a rapid advancement in computer vision technology which is much effective in extracting useful information from plant images in the field of plant phenomics. Phenomic approaches are widely used in the identification of relationship between phenotypic traits and genetic diversities among the plant species. The need for automation and precision in phenotyping have been accelerated by the significant advancement in genotyping. Regardless of its significance, the shortage of freely available research databases having plant imageries has significantly obstructed the plant image analysis advancement. There were several existing computer vision techniques employed in the analysis of plant phenotypes. Conversely, recent trends in image analysis with the use of machine learning and deep learning based approaches including convolutional neural networks have increased their expansion for providing high-efficiency phenotyping of plant species. Thus, to enhance the efficiency of phenotype analysis, various existing machine learning and deep learning algorithms have been reviewed in this paper along with their methods, advantages, and limitations.