Hyperspectral imaging for accurate determination of rice variety using a deep learning network with multi-feature fusion.

07:00 EST 6th March 2020 | BioPortfolio

Summary of "Hyperspectral imaging for accurate determination of rice variety using a deep learning network with multi-feature fusion."

The phenomena of rice adulteration and shoddy rice arise continuously in high-quality rice and reduce the interests of producers, consumers and traders. Hyperspectral imaging (HSI) was conducted to determine rice variety using a deep learning network with multiple features, namely, spectroscopy, texture and morphology. HSI images of 10 representative high-quality rice varieties in China were measured. Spectroscopy and morphology were extracted from HSI images and binary images in region of interest, respectively. And texture was obtained from the monochromatic images of characteristic wavelengths which were highly correlated with rice varieties. A deep learning network, namely principal component analysis network (PCANet), was adopted with these features to develop classification models for determining rice variety, and machine learning methods as K-nearest neighbour and random forest were used to compare with PCANet. Meanwhile, multivariate scatter correction, standard normal variate, Savitzky-Golay smoothing and Savitzky-Golay's first-order were applied to eliminate spectral interference, and principal component analysis (PCA) was performed to obtain the main information of high-dimensional features. Multi-feature fusion improved recognition accuracy, and PCANet demonstrated considerable advantage in classification performance. The best result was achieved by PCANet with PCA-processed spectroscopic and texture features with correct classification rates of 98.66% and 98.57% for the training and prediction sets, respectively. In summary, the proposed method provides an accurate identification of rice variety and can be easily extended to the classification, attribution and grading of other agricultural products.


Journal Details

This article was published in the following journal.

Name: Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy
ISSN: 1873-3557
Pages: 118237


DeepDyve research library

PubMed Articles [16185 Associated PubMed Articles listed on BioPortfolio]

Hyperspectral imaging technology combined with deep forest model to identify frost-damaged rice seeds.

In recent years, deep learning models have been widely used in the field of hyperspectral imaging. However, the training of deep learning models requires not only a large number of samples, but also t...

Developing deep learning based regression approaches for determination of chemical compositions in dry black goji berries (Lycium ruthenicum Murr.) using near-infrared hyperspectral imaging.

Black goji berry (Lycium ruthenicum Murr.) has great commercial and nutritional values. Near-infrared hyperspectral imaging (NIR-HSI) was used to determine total phenolics, total flavonoids and total ...

Qualitative and quantitative diagnosis of nitrogen nutrition of tea plants under field condition using hyperspectral imaging coupled with chemometrics.

Rapid and accurate diagnosis of nitrogen (N) status in field crops is of great significance for site-specific N fertilizer management. This study aimed to evaluate the potential of hyperspectral imagi...

Optimization of Band Selection in Multispectral and Narrow-Band Imaging: An Analytical Approach.

Hyperspectral imaging is a promising clinical imaging modality with multiple applications in wound care, dermatology, and ophthalmology. However, with current technologies, hyperspectral imagers are r...

Cognitive spectroscopy for wood species identification: near infrared hyperspectral imaging combined with convolutional neural networks.

From the viewpoint of combating illegal logging and examining wood properties, there is a contemporary demand for a wood species identification system. Several nondestructive automatic identification ...

Clinical Trials [8127 Associated Clinical Trials listed on BioPortfolio]

Intraoperative Hyperspectral Imaging in Gastrointestinal Anastomoses

In this study, gastrointestinal anastomoses are examined with a hyperspectral camera.

Tissue Characterization With Hyperspectral Maging (HSI)

Hyperspectral Imaging (HSI) is a contact free method to analyse the from the tissue reflected light in the range of 500-1000nm. Aim of the study is to identify special reflex patterns to i...

ICG vs. HSI in Gastrointestinal Resections

In this study, gastrointestinal anastomoses are examined with a hyperspectral camera and after this the investigators use the Standard Routine ICG-Imaging. At the end, both methods will be...

Enhancing the Lucentis (Ranibizumab) Management of Choroidal Neovascular Membranes With Hyperspectral Imaging

Clinical trial investigating the role of hyperspectral imaging in the management of patients undergoing standard clinical treatment for naive neovascular choroidal membranes in age-related...

Determination of the PPG and Insulin Responses of Rice Alone and Rice Consumed With Sugardown™

This study was a partly controlled laboratory-based study comparing the short-term postprandial blood glucose and insulin responses produced by 3 test meals containing white rice alone or ...

Medical and Biotech [MESH] Definitions

Descriptive anatomy based on three-dimensional imaging (IMAGING, THREE-DIMENSIONAL) of the body, organs, and structures using a series of computer multiplane sections, displayed by transverse, coronal, and sagittal analyses. It is essential to accurate interpretation by the radiologist of such techniques as ultrasonic diagnosis, MAGNETIC RESONANCE IMAGING, and computed tomography (TOMOGRAPHY, X-RAY COMPUTED). (From Lane & Sharfaei, Modern Sectional Anatomy, 1992, Preface)

The anamorphic form of the fungus MAGNAPORTHE GRISEA and the most important pathogen of rice worldwide. It causes rice blast which prevents maturation of the rice grains.

The use of molecularly targeted imaging probes to localize and/or monitor biochemical and cellular processes via various imaging modalities that include RADIONUCLIDE IMAGING; ULTRASONOGRAPHY; MAGNETIC RESONANCE IMAGING; fluorescence imaging; and MICROSCOPY.

A technique applicable to the wide variety of substances which exhibit paramagnetism because of the magnetic moments of unpaired electrons. The spectra are useful for detection and identification, for determination of electron structure, for study of interactions between molecules, and for measurement of nuclear spins and moments. (From McGraw-Hill Encyclopedia of Science and Technology, 7th edition) Electron nuclear double resonance (ENDOR) spectroscopy is a variant of the technique which can give enhanced resolution. Electron spin resonance analysis can now be used in vivo, including imaging applications such as MAGNETIC RESONANCE IMAGING.

A type of MAGNETIC RESONANCE IMAGING that uses only one nuclear spin excitation per image and therefore can obtain images in a fraction of a second rather than the minutes required in traditional MRI techniques. It is used in a variety of medical and scientific applications.

Quick Search

DeepDyve research library

Searches Linking to this Article