An expert botanical feature extraction technique based on phenetic features for identifying plant species

Kolivand, Hoshang; Fern, Bong Mei; Rahim, Mohd Shafry Mohd; Sulong, Ghazali; Baker, Thar; Tully, David

doi:10.1371/journal.pone.0191447

Cited by 11 publications

(4 citation statements)

References 22 publications

(13 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…VGG16 [42] and VGG19 [42] are the pre-trained models based on CNN architecture with logistic regression. MLAB (Margin, lobes, apex and base) [43] is the phenetic features of leaf. MLBP [44] is the method of extracting texture features based on modified local binary patterns.…”

Section: Comparison Of Different Methodsmentioning

confidence: 99%

Leaf Image Recognition Based on Bag of Features

et al. 2020

View full text Add to dashboard Cite

Plants are ubiquitous in human life. Recognizing an unknown plant by its leaf image quickly is a very interesting and challenging research. With the development of image processing and pattern recognition, plant recognition based on image processing has become possible. Bag of features (BOF) is one of the most powerful models for classification, which has been used for many projects and studies. Dual-output pulse-coupled neural network (DPCNN) has shown a good ability for texture features in image processing such as image segmentation. In this paper, a method based on BOF and DPCNN (BOF_DP) is proposed for leaf classification. BOF_DP achieved satisfactory results in many leaf image datasets. As it is hard to get a satisfactory effect on the large dataset by a single feature, a method (BOF_SC) improved from bag of contour fragments is used for shape feature extraction. BOF_DP and LDA (linear discriminant analysis) algorithms are, respectively, employed for textual feature extraction and reducing the feature dimensionality. Finally, both features are used for classification by a linear support vector machine (SVM), and the proposed method obtained higher accuracy on several typical leaf datasets than existing methods.

show abstract

Section: Comparison Of Different Methodsmentioning

confidence: 99%

Leaf Image Recognition Based on Bag of Features

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The leaves of the rubber plant show similarities to each other and contain the same information such as color, texture, and shape. Unique traits can be used to differentiate between different clones/species [9][10]. The difference in leaf size, leaf area, leaf length and width ratio, leaf angle was assessed as significantly different among different clones so that it could be used as a marker in clone identification [11].…”

Section: Introductionmentioning

confidence: 99%

Leaf Characterizations of IRR 400 Series, BPM 24, and RRIC 100 Rubber (Hevea brasiliensis Muell. Arg.) Clone Using Leafgram Method

Pasaribu¹,

Basyuni²,

Purba³

et al. 2022

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

Leaf characterization of rubber clones needs to be done from the start, especially for plants in the budwood garden. This function is to produce genetically pure and original plants. The purpose of this study was to characterize the IRR series 400, RRIC 100, and BPM 24 clones based on leaf character using the leafgram method. The types of clones that were characterized were IRR 425, IRR 428, IRR 429, IRR 434, IRR 440, RRIC 100, and BPM 24. The leaves characterized were the middle leaves of each clone as many as 50 leaves per clone, divided into three replications. The leaf characters observed were length, width, top fold point, center point, left strand, large, apex angle, vein angle, basal angle, apex kite angle, basal kite angle, ratio length/width, ratio length/top fold point, ratio left strand/large/ ratio left strand top fold point, ratio left strand/center point, ratio top fold point/large, ratio top fold point/center point, ratio apex/basal angle, ratio vein/apex angle, ratio vein/basal angle and ratio apex kite/basal kite angle. Data were analyzed using MINITAB 16 software and Microsoft Office 2010. The characterization results showed that the distinguishing characters that can be used as characteristic of characters are width, left strand, apex angle, basal angle, ratio length /width, ratio left strand/top fold point, ratio left strand ratio/center point, ratio top fold point/large, ratio apex/basal angle, ratio vein/apex angle, and ratio vein/ basal angle.

show abstract

“…Since the traditional identification methods are strenuous, there arises a need to automate the process of species identification. Scientific and technological challenges in identifying species (Kolivand et al 2018) or even subs below them such as varieties or clones of plants, against a wide variety of plants and countless taxonomic characteristics. The conditions of equatorial tropical forests have a high diversity of plants (Bruno et al 2008), making traditional and very special taxonomic techniques difficult, slow, as most later manuals.…”

Section: Introductionmentioning

confidence: 99%

Short Communication: Digital identification approach to characterize Hevea brasiliensis leaves

et al. 2021

View full text Add to dashboard Cite

Abstract. Pratomo B, Lisnawita, Nisa TC, Basyuni M. 2021. Short Communication: Digital identification approach to characterize Hevea brasiliensis leaves. Biodiversitas 22: 1006-1013. The purity of clones is a key factor to obtain uniform growth of Hevea brasiliensis Muell Arg in the field. Crop uniformity has an impact on production patterns that can be predicted in latex content. Basically, H. brasiliensis tree leaves show similarities to each other such as the color, texture, or shape of the leaves. Identification of clones that have been very common by the morphology of H. brasiliensis leaves. This study links the results of previous research on digital methods used. A total of 27 clones were sampled in this study which came from the garden collection of entres, which can be used as a source of elders for assisted pollination or source of planting materials for the needs of production-scale seeds in the field. Here, we used a database of 540 leaves from 27 clones and 10 quantitative characters to address these issues The analysis data used a randomized complete block design (RCBD) factorial. The result showed the identification method digitally on characterizing of leaves by using Software Adobe Photoshop, depicting that the characteristics contained in H. brasiliensis leaves are very proper to be used as the first character in identifying an H. brasiliensis clone. The present work provided a piece of important information on the characterization of H. brasiliensis leaves to enhance the selection of parent clones.

show abstract

An expert botanical feature extraction technique based on phenetic features for identifying plant species

Cited by 11 publications

References 22 publications

Leaf Image Recognition Based on Bag of Features

Leaf Image Recognition Based on Bag of Features

Leaf Characterizations of IRR 400 Series, BPM 24, and RRIC 100 Rubber (Hevea brasiliensis Muell. Arg.) Clone Using Leafgram Method

Short Communication: Digital identification approach to characterize Hevea brasiliensis leaves

Contact Info

Product

Resources

About