Feature Extraction and Selection for Pattern Recognition of Two-Dimensional Hydrometeor Images

Rahman, Mizanur; Quincy, E.; Jacquot, Raymond G.; Magee, Michael

doi:10.1175/1520-0450(1981)020<0521:feasfp>2.0.co;2

Cited by 8 publications

(8 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After the development of Optical Array Probes (OAP) for aircraft platforms, large databases on cloud particle shapes were obtained, to which several new classification techniques were applied. Rahman et al [1981]developed a technique for extracting features of two‐dimensional binary images of ice particles and raindrops. From such features derived from OAP images, Hunter et al [1984] developed a classification algorithm that distinguished six categories of ice crystals.…”

Section: Introductionmentioning

confidence: 99%

Ice‐cloud particle habit classification using principal components

et al. 2012

View full text Add to dashboard Cite

[1] A novel automatic classification method is proposed for identifying the habits of large ice-cloud particles and deriving the shape distribution of particle ensembles. This IC-PCA (Ice-crystal Classification with Principal Component Analysis) tool is based on a principal component analysis of selected physical and statistical features of ice-crystal perimeters.The method is developed and tested using image data obtained with a Cloud Particle Imager, but can be applied to other silhouette data as well. For three randomly selected test cases of 222, 200, and 201 crystals from tropical, midlatitude, and arctic ice clouds, the combined classification accuracy of the IC-PCA is 81.1%. Since previous, semiautomatic classification methods are more time-consuming and include a subjective phase, the automatic and objective IC-PCA offers a notable improvement in retrieving the shapes of the individual crystals. As the habit distributions of ice-cloud particles can be applied to computations of radiative impact of cirrus, it is also demonstrated how classification uncertainties propagate into the radiative transfer computations by using the arctic test case as an example. Computations of shortwave radiative fluxes show that the flux differences between clouds of manually and automatically classified crystals can be as large as 10 Wm À2 but also that two manual classifications of the same image data result in even larger differences, implying the need for a systematic and repeatable classification method.Citation: Lindqvist, H., K. Muinonen, T. Nousiainen, J. Um, G. M. McFarquhar, P. Haapanala, R. Makkonen, and H. Hakkarainen (2012), Ice-cloud particle habit classification using principal components,

show abstract

Section: Introductionmentioning

confidence: 99%

Ice‐cloud particle habit classification using principal components

et al. 2012

View full text Add to dashboard Cite

show abstract

“…For this purpose, shapes were classified as round, hexagonal, rectangular (aspect ratios 1, 1.5, and 2), stellar, or unclassifiable. In this procedure, we did not use terminology such as plate, column, or needle, which refer to particle habits (Korolev and Sussman 2000;Moss and Johnson 1994;Rahman et al 1981), because the automated recognition applies strictly only to geometric shapes. While there is no strict correspondence between a given habit and a geometric shape, there are similarities that can be used in application to natural ice crystals (vide infra).…”

Section: Automated Shape Recognitionmentioning

confidence: 99%

“…Cunningham (1978) used maximum crystal size and equivalent circle ratio. Rahman et al (1981) compared classification methods based on different features extracted from the images and concluded that the Bayes classifier used with four moment invariants is most efficient. Holroyd (1987) used size, linearity, area, perimeter, and image density to classify images into nine classes.…”

Section: Introductionmentioning

confidence: 99%

Improved Imaging and Image Analysis System for Application to Measurement of Small Ice Crystals

Kühn

Grishin

Sloan

2012

Journal of Atmospheric and Oceanic Technology

View full text Add to dashboard Cite

Accurate knowledge of ice particle size and shape distribution is required for understanding of atmospheric microphysical processes. While larger ice particles are easily measured with a variety of sensors, the measurement of small ice particles with sizes down to a few micrometers remains challenging. Here the authors report the development of a system that measures the size and shape of small ice particles using a novel combination of high-resolution imaging and high-speed automated image classification. The optical system has a pixel resolution of 0.2 mm and a resolving power of approximately 1 mm. This imaging instrument is integrated into a cryogenic flow tube that allows precise control of experimental conditions. This study also describes an automated method for the high-speed analysis of high-resolution particle images. Each particle is located in the image using a Sobel edge detector, the border is vectorized, and a polygon representing the border is found. The vertices of this polygon are expressed in complex coordinates, and an analytic implementation of Fourier shape descriptors is used for piecewise integration along the edges of the polygon.The authors demonstrate the capabilities of this system in a study of the early-stage growth of ice particles, which are grown for approximately 1 min at fixed temperature and saturated water vapor concentrations in the cryogenic flowtube. Ice particle shapes and size distributions are reported and compared with habit diagrams found in the literature. The capability of the shape recognition system is verified by comparison with manual classification.

show abstract

“…Since OAPs were developed in the 1970s (Knollenberg, 1970), several attempts have been made to produce highperformance classification algorithms based on morphological descriptors. While mathematically simple, the feature extraction for pattern recognition of 2D hydrometeor images developed by Rahman et al (1981) and Duroure (1982) gives insight on how morphological image analysis is useful to automatically categorize OAP images into different classes. Their approach works well with synthetic images of singular crystals that exhibit completely unambiguous orientations and idealized shapes (see Rahman et al, 1981).…”

Section: Introductionmentioning

confidence: 99%

Ice crystals images from Optical Array Probes: classification with Convolutional Neural Networks

Jaffeux¹,

Schwarzenböck²,

Coutris³

et al. 2022

Preprint

View full text Add to dashboard Cite

Abstract. Although airborne optical array probes (OAP) have existed for decades, our ability to maximize extraction of meaningful morphological information out of the images produced by these probes has been limited by the lack of automatic, unbiased and reliable classification tools. The present study describes a methodology for automatic ice crystal recognition using innovative machine learning. Convolutional Neural Network (CNN) have recently been perfected for computer vision and have been chosen as the method to achieve the best results together with the use of finely tuned dropout layers. For the purposes of this study, CNN has been adapted for the Precipitation Imaging Probe (PIP) and the 2DS-Stereo Probe (2DS), two commonly used probes that differ in pixel resolution and measurable maximum size range for hydrometeors. Six morphological crystal classes have been defined for the PIP and eight crystal classes and an artifact class, for the 2DS. The PIP and 2DS classifications have five common classes. In total more than 8000 images from both instruments have been manually labelled, thus allowing for the initial training. For each probe the classification design tries to account for the three primary ice crystal growth processes: vapor deposition, riming and aggregation. We included classes such as fragile aggregates and rimed aggregates with high intra-class shape variability and commonly found in convective clouds. The trained network is finally tested through human random inspections on actual data to show its real performance in comparison to what humans can achieve.

show abstract

Feature Extraction and Selection for Pattern Recognition of Two-Dimensional Hydrometeor Images

Cited by 8 publications

References 0 publications

Ice‐cloud particle habit classification using principal components

Ice‐cloud particle habit classification using principal components

Improved Imaging and Image Analysis System for Application to Measurement of Small Ice Crystals

Ice crystals images from Optical Array Probes: classification with Convolutional Neural Networks

Contact Info

Product

Resources

About