Leaf Extraction from Complicated Background

Tang, Xiaodong; Liu, Manhua; Zhao, Hui; Tao, Wei

doi:10.1109/cisp.2009.5304424

Cited by 27 publications

(15 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various strategies have been proposed to segment plant images, depending on whether the background is homogeneous (Janssens et al ., ; Soares and Jacobs, ; Pape and Klukas, ; Aksoy et al ., ) or inhomogeneous (Tang et al ., ), and whether colour information is available (Neto et al ., ; Tang et al ., ; Soares and Jacobs, ; Pape and Klukas, ) or not (Janssens et al ., ; Pape and Klukas, ; Aksoy et al ., ). The light‐field camera provides grey‐scale focus images with a high contrast between the rosette and a homogenous background, due to use of black quartz sand (Figure a).…”

Section: Resultsmentioning

confidence: 99%

Phytotyping^4D: a light‐field imaging system for non‐invasive and accurate monitoring of spatio‐temporal plant growth

et al. 2015

View full text Add to dashboard Cite

SUMMARYIntegrative studies of plant growth require spatially and temporally resolved information from high-throughput imaging systems. However, analysis and interpretation of conventional two-dimensional images is complicated by the three-dimensional nature of shoot architecture and by changes in leaf position over time, termed hyponasty. To solve this problem, Phytotyping 4D uses a light-field camera that simultaneously provides a focus image and a depth image, which contains distance information about the object surface. Our automated pipeline segments the focus images, integrates depth information to reconstruct the threedimensional architecture, and analyses time series to provide information about the relative expansion rate, the timing of leaf appearance, hyponastic movement, and shape for individual leaves and the whole rosette. Phytotyping 4D was calibrated and validated using discs of known sizes, and plants tilted at various orientations. Information from this analysis was integrated into the pipeline to allow error assessment during routine operation. To illustrate the utility of Phytotyping 4D, we compare diurnal changes in Arabidopsis thaliana wild-type Col-0 and the starchless pgm mutant. Compared to Col-0, pgm showed very low relative expansion rate in the second half of the night, a transiently increased relative expansion rate at the onset of light period, and smaller hyponastic movement including delayed movement after dusk, both at the level of the rosette and individual leaves. Our study introduces light-field camera systems as a tool to accurately measure morphological and growth-related features in plants.

show abstract

Section: Resultsmentioning

confidence: 99%

Phytotyping^4D: a light‐field imaging system for non‐invasive and accurate monitoring of spatio‐temporal plant growth

et al. 2015

View full text Add to dashboard Cite

show abstract

“…Most of existing approaches for leaf extraction require manual operations or prior information and images taken in controlled environments and cannot deal with complicated background. We have first used marker-controlled watershed segmentation [13,14] to separate the target leaf from the background. The marker-controlled watershed algorithm uses operations of mathematical morphology to place foreground markers in the blob and background markers for the areas without blobs.…”

Section: Leaf Extraction From the Complicated Backgroundmentioning

confidence: 99%

Automatic Detection and Severity Assessment of Crop Diseases Using Image Pattern Recognition

Han

Haleem

Taylor

2016

Studies in Computational Intelligence

View full text Add to dashboard Cite

Disease diagnosis and severity assessment are necessary and critical for predicting the likely crop yield losses, evaluating the economic impact of the disease, and determining whether preventive treatments are worthwhile or particular control strategies could be taken. In this work, we propose to make advances in the field of automatic detection and diagnosis and severity assessment of crop diseases using image pattern recognition. We have developed a two-stage crop disease pattern recognition system which can automatically identify crop diseases and assess sevrity based on combination of marker-controlled watershed segmentation, superpixel based feature analysis and classification. We have conducted experimental evaluation using different feature selection and classification methods. The experimental result shows that the proposed approach can accurately detect crop diseases (i.e. Septoria and Yellow rust, which are the two most important and major types of wheat diseases in UK and across the world) and assess the disease severity with efficient processing speed.

show abstract

“…Most of existing approaches for leaf extraction require manual operations or prior information and images taken in controlled environments and cannot deal with complicated background. We have first used marker-controlled watershed segmentation [12], [13] to separate the target leaf from the background. The markercontrolled watershed algorithm uses operations of mathematical morphology to place foreground markers in the blob and background markers for the areas without blobs.…”

Section: ) Segmentation Based On Marker Controlled Watershed Transfomentioning

confidence: 99%

A novel computer vision-based approach to automatic detection and severity assessment of crop diseases

Han

Haleem

Taylor

2015

2015 Science and Information Conference (SAI)

View full text Add to dashboard Cite

Accurate detection and identification of crop diseases plays an important role in effectively controlling and preventing diseases for sustainable agriculture and food security. In this work, we have developed a novel computer vision-based approach for automatically identifying crop diseases based on marker-controlled watershed segmentation, superpixel based feature analysis and classification. The experimental result demonstrates that the proposed approach can accurately detect crop diseases (i.e. Septoria and Yellow rust. Two types of most important and major wheat diseases in UK and across the world) and assess the disease severity with efficient processing speed.

show abstract

Leaf Extraction from Complicated Background

Cited by 27 publications

References 6 publications

Phytotyping^4D: a light‐field imaging system for non‐invasive and accurate monitoring of spatio‐temporal plant growth

Phytotyping^4D: a light‐field imaging system for non‐invasive and accurate monitoring of spatio‐temporal plant growth

Automatic Detection and Severity Assessment of Crop Diseases Using Image Pattern Recognition

A novel computer vision-based approach to automatic detection and severity assessment of crop diseases

Contact Info

Product

Resources

About

Leaf Extraction from Complicated Background

Cited by 27 publications

References 6 publications

Phytotyping4D: a light‐field imaging system for non‐invasive and accurate monitoring of spatio‐temporal plant growth

Phytotyping4D: a light‐field imaging system for non‐invasive and accurate monitoring of spatio‐temporal plant growth

Automatic Detection and Severity Assessment of Crop Diseases Using Image Pattern Recognition

A novel computer vision-based approach to automatic detection and severity assessment of crop diseases

Contact Info

Product

Resources

About

Phytotyping^4D: a light‐field imaging system for non‐invasive and accurate monitoring of spatio‐temporal plant growth

Phytotyping^4D: a light‐field imaging system for non‐invasive and accurate monitoring of spatio‐temporal plant growth