Utilizing Deep Neural Networks for Chrysanthemum Leaf and Flower Feature Recognition

被引:2
作者
Nguyen, Toan Khac [1 ]
Dang, Minh [2 ,3 ]
Doan, Tham Thi Mong [1 ]
Lim, Jin Hee [1 ]
机构
[1] Sejong Univ, Dept Plant Biotechnol, Seoul 05006, South Korea
[2] Sejong Univ, Dept Informat & Commun Engn, Seoul 05006, South Korea
[3] Sejong Univ, Convergence Engn Intelligent Drone, Seoul 05006, South Korea
关键词
chrysanthemum image; clustering; flower recognition; image processing; leaf recognition; CLASSIFICATION;
D O I
10.3390/agriengineering6020065
中图分类号
S2 [农业工程];
学科分类号
0828 ;
摘要
Chrysanthemums, a significant genus within the Asteraceae, hold a paramount position in the global floricultural industry, second only to roses in market demand. The proliferation of diverse chrysanthemum cultivars presents a formidable challenge for accurate identification, exacerbated by the abundance of varieties, intricate floral structures, diverse floret types, and complex genetic profiles. Precise recognition of chrysanthemum phenotypes is indispensable to navigating these complexities. Traditional methods, including morphology studies, statistical analyses, and molecular markers, have fallen short due to their manual nature and time-intensive processes. This study presents an innovative solution employing deep learning techniques for image-based chrysanthemum phenotype recognition. Leveraging machine learning, our system autonomously extracts key features from chrysanthemum images, converting morphological data into accessible two-dimensional representations. We utilized Support Vector Machine (SVM) and Multilayer Perceptron (MLP) algorithms to construct frameworks for processing image data and classifying chrysanthemum cultivars based on color, shape, and texture. Experimental results, encompassing 10 cultivars, 10 flower colors, and five flower shapes, consistently demonstrated recognition accuracy ranging from 79.29% up to 97.86%. This tool promises streamlined identification of flower traits, and we anticipate its potential for real-time identification enhancements in future iterations, promising advances in chrysanthemum cultivation and exportation processes. Our approach offers a novel and efficient means to address the challenges posed by the vast diversity within chrysanthemum species, facilitating improved management, breeding, and marketing strategies in the floricultural industry.
引用
收藏
页码:1133 / 1149
页数:17
相关论文
共 39 条
[1]  
Agarwal Ritu, 2021, Advances in Mechanical Engineering. Select Proceedings of CAMSE 2020. Lecture Notes in Mechanical Engineering (LNME), P663, DOI 10.1007/978-981-16-0942-8_62
[2]   Plant species identification using color learning resources, shape, texture, through machine learning and artificial neural networks [J].
Bambil D. ;
Pistori H. ;
Bao F. ;
Weber V. ;
Alves F.M. ;
Gonçalves E.G. ;
de Alencar Figueiredo L.F. ;
Abreu U.G.P. ;
Arruda R. ;
Bortolotto I.M. .
Environment Systems and Decisions, 2020, 40 (4) :480-484
[3]  
Burges CJC, 1997, ADV NEUR IN, V9, P375
[4]   Review of Image Classification Algorithms Based on Convolutional Neural Networks [J].
Chen, Leiyu ;
Li, Shaobo ;
Bai, Qiang ;
Yang, Jing ;
Jiang, Sanlong ;
Miao, Yanming .
REMOTE SENSING, 2021, 13 (22)
[5]   2D and 3D object detection algorithms from images: A Survey [J].
Chen, Wei ;
Li, Yan ;
Tian, Zijian ;
Zhang, Fan .
ARRAY, 2023, 19
[6]   Deep Learning Based Underground Sewer Defect Classification Using a Modified RegNet [J].
Chen, Yu ;
Sharifuzzaman, Sagar A. S. M. ;
Wang, Hangxiang ;
Li, Yanfen ;
Dang, L. Minh ;
Song, Hyoung-Kyu ;
Moon, Hyeonjoon .
CMC-COMPUTERS MATERIALS & CONTINUA, 2023, 75 (03) :5451-5469
[7]   Allometric Individual Leaf Area Estimation in Chrysanthemum [J].
Fanourakis, Dimitrios ;
Kazakos, Filippos ;
Nektarios, Panayiotis A. .
AGRONOMY-BASEL, 2021, 11 (04)
[8]   Genetic Analysis of Leaf Traits in Small-Flower Chrysanthemum Chrysanthemum x morifolium Ramat.) [J].
Gao, Kang ;
Song, Xuebin ;
Kong, Deyuan ;
Dai, Silan .
AGRONOMY-BASEL, 2020, 10 (05)
[9]   Modifications of the Multi-Layer Perceptron for Hyperspectral Image Classification [J].
He, Xin ;
Chen, Yushi .
REMOTE SENSING, 2021, 13 (17)
[10]   Variation in morphological characters, chemical composition, and anthocyanin content of different Chrysanthemum morifolium cultivars from Iran [J].
Hodaei, Mahboobeh ;
Rahimmalek, Mehdi ;
Arzani, Ahmad .
BIOCHEMICAL SYSTEMATICS AND ECOLOGY, 2017, 74 :1-10