Individual leaf identification from horticultural crop images based on the leaf skeleton

Zhang, Liankuan; Weckler, Paul; Wang, Ning; Xiao, Di; Chai, Xirong

doi:10.1016/j.compag.2016.06.017

Cited by 16 publications

(10 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The accuracy of the proposed main leaf-skeleton scheme was subsequently compared with that of our previously reported method (Zhang et al, 2016). Three complex plant images from Zhang et al (2016) were used to examine the accuracy of the two methods. Figure 12a shows 20 leaves on the soil background and Fig.…”

Section: Resultsmentioning

confidence: 99%

“…Although the sophisticated leaf segmentation approaches have shown excellent performance in complicated environments, these approaches greatly rely on initialisation accuracy, such as position, size, or orientation. Leaf tips, boundaries, and skeletons have been adopted to estimate the approximate positions of leaves (Manh et al, 2001;Xia et al, 2013;Zhang et al, 2016). Recently, deep learning approaches have achieved promising performance in counting plant leaves.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A coarse-to-fine leaf detection approach based on leaf skeleton identification and joint segmentation

Zhang

Xia

Xiao

et al. 2021

Biosystems Engineering

Self Cite

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A coarse-to-fine leaf detection approach based on leaf skeleton identification and joint segmentation

Zhang

Xia

Xiao

et al. 2021

Biosystems Engineering

Self Cite

View full text Add to dashboard Cite

“…Thus, smooth, clear and accurate edges of the target leaf are obtained. Similarly, a study based on the challenges of the identification of single leaves in complex backgrounds is presented in [19]. The tangential direction (TD) segmentation approach is used to retrieve the leaf skeleton in the image and to determine the distribution of the leaf based on the number of pixels and its relative moment.…”

Section: Introductionmentioning

confidence: 99%

Development of Hybrid Automatic Segmentation Technique of a Single Leaf from Overlapping Leaves Image

et al. 2021

View full text Add to dashboard Cite

The segmentation of a single leaf from an image with overlapping leaves is an important step towards the realization of effective precision agricultural systems. A popular approach used for this segmentation task is the hybridization of the Chan-Vese model and the Sobel operator CV-SO. This hybridized approach is popular because of its simplicity and effectiveness in segmenting a single leaf of interest from a complex background of overlapping leaves. However, the manual threshold and parameter tuning procedure of the CV-SO algorithm often degrades its detection performance. In this paper, we address this problem by introducing a dynamic iterative model to determine the optimal parameters for the CV-SO algorithm, which we dubbed the Dynamic CV-SO (DCV-SO) algorithm. This is a new hybrid automatic segmentation technique that attempts to improve the detection performance of the original hybrid CV-SO algorithm by reducing its mean error rate. The results obtained via simulation indicate that the proposed method yielded a 1.23% reduction in the mean error rate against the original CV-SO method.

show abstract

“…This system further added a new step in the conventional Otsu algorithm by determining the B threshold of the RGB image and morphological operations and multiplications as post image processing steps which results in a more significant increase in the clarity of segmentation. Individual leaf segmentation and identification were implemented based on leaf skeleton transformed imaging (Zhang, Weckler, Wang, Xiao, & Chai, 2016). The algorithm involves tangential direction (TD), multi-thresholding, and successive denoising procedures.…”

Section: Introductionmentioning

confidence: 99%

Lettuce Canopy Area Measurement Using Static Supervised Neural Networks Based on Numerical Image Textural Feature Analysis of Haralick and Gray Level Co-Occurrence Matrixs

et al. 2020

View full text Add to dashboard Cite

Journal of Agricultural Science www.agrivita.ub.ac.id based on the Bureau of Plant Industry-National Crop Research and Development Center (BPI-NCRDC) of the Department of Agriculture (DOA) due to its significant impact on medicinal, culinary, and health perspectives. Loose-leaf lettuce makes up its harvest growth stage after 45 to 90 days after transplanting that normally takes 12 to 14 days from germination. The sensitive way of growing lettuce is inclusive to the beneficial application of smart farming (Ge, Zhou, Kellomäki, Peltola, & Wang, 2011; Jindarat & Wuttidittachotti, 2015). It also demands a heuristic approach of monitoring to enhance its agricultural process. The lettuce growth, similar to the other higher value leafy crops, is primarily affected by light-dependent and gas-dependent reactions. The growth and development changes are verified to the changes occurred on its fresh weight, dry weight, volume, height, surface area, root zone depth ARTICLE INFO

show abstract

Individual leaf identification from horticultural crop images based on the leaf skeleton

Cited by 16 publications

References 25 publications

A coarse-to-fine leaf detection approach based on leaf skeleton identification and joint segmentation

A coarse-to-fine leaf detection approach based on leaf skeleton identification and joint segmentation

Development of Hybrid Automatic Segmentation Technique of a Single Leaf from Overlapping Leaves Image

Lettuce Canopy Area Measurement Using Static Supervised Neural Networks Based on Numerical Image Textural Feature Analysis of Haralick and Gray Level Co-Occurrence Matrixs

Contact Info

Product

Resources

About