Wild Chrysanthemums Core Collection: Studies on Leaf Identification

Abstract

Wild chrysanthemums mainly present germplasm collections such as leaf multiform, flower color, aroma, and secondary compounds. Wild chrysanthemum leaf identification is critical for farm owners, breeders, and researchers with or without the flowering period. However, few chrysanthemum identification studies are related to flower color recognition. This study contributes to the leaf classification method by rapidly recognizing the varieties of wild chrysanthemums through a support vector machine (SVM). The principal contributions of this article are: (1) an assembled collection method and verified chrysanthemum leaf dataset that has been achieved and improved; (2) an adjusted SVM model that is offered to deal with the complex backgrounds presented by smartphone pictures by using color and shape classification results to be more attractive than the original process. As our study presents, the proposed method has a viable application in real-picture smartphones and can help to further investigate chrysanthemum identification.

VPBR: An Automatic and Low-Cost Vision-Based Biophysical Properties Recognition Pipeline for Pumpkin

“…Furthermore, previous research has often relied on contour detection [ 25 ] or bounding box/mask methods [ 26 ] to measure the width and length traits of fruits. However, these approaches are not accurate for fruits and plants with irregular shapes.…”

Utilizing Deep Neural Networks for Chrysanthemum Leaf and Flower Feature Recognition

“…It accomplishes this by fitting the training data optimally and achieving precise classification of unseen datasets [17]. SVM excels at maximizing the separation margin between training samples across different classes, a key advantage stemming from its robust performance in high-dimensional spaces [1,18]. Moreover, SVM can yield superior results in scenarios where the dimensionality of the data exceeds the number of samples, depending on the choice of kernel functions tailored to specific analytical objectives [18].…”

“…The Asteraceae boasts a presentative floricultural genus, chrysanthemum, which has a significant rate in terms of economic value and ranks second behind roses in the floral market worldwide [1]. The proliferation of diverse breeding cultivars of chrysanthemums worldwide has made their identification increasingly challenging, even for experienced researchers, due to the complexities inherent in chrysanthemum cultivars, which pose significant challenges in their management and authorized protection.…”

“…The deep learning method for image-based studies has been progressively produced as a convenience tool for plant identification with highly rapid machine learning developments that use self-learning based on huge image materials to determine the key setting features [7]. Based on the comparison with previous manual measuring methods, image capture could rapidly transform morphologic data of plants into two-dimensional figure information; thus, these processes of data collection can be substantially interpreted in morphologic phenotypes of plants [1]. Machine learning (ML) algorithms serve as a crucial tool for training computers to recognize various features from images and perform tasks robustly.…”

“…Our strategy to overcome the phenotype problems utilized visual recognition as the essential tool. Heretofore, applying and modifying ML algorithms [8] using Support Vector Machine (SVM) [1,9], Multilayer Perceptron (MLP) [10], and spectral vegetation [9] contributed to the creation of automatically gigantic recognized systems. Two frameworks were applied to process the imaging identifying methods and ML to classify chrysanthemum cultivars.…”