Evaluation and analysis the chalkiness of connected rice kernels based on image processing technology and support vector machine

Sun, Chengming; Liu, Tao; Ji, Chengxin; Jiang, Min; Tian, Ting; Guo, Doudou; Wang, Lijian; Chen, Yingying; Liang, Xinlian

doi:10.1016/j.jcs.2014.04.009

Cited by 49 publications

(20 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A challenge for automatic detection is the connected grains that are invariably present in the sample and separating them manually would significantly reduce process efficiency. Sun et al (2014) proposed an automated system for analysis of the percentage of grains in rice. The algorithm deals with the separation of grains automatically.…”

Section: Analysis Of Milled Rice Grains Using Svmmentioning

confidence: 99%

Computer vision and artificial intelligence in precision agriculture for grain crops: A systematic review

Patrício

Rieder

2018

Computers and Electronics in Agriculture

666

257

View full text Add to dashboard Cite

Grain production plays an important role in the global economy. In this sense, the demand for efficient and safe methods of food production is increasing. Information Technology is one of the tools to that end. Among the available tools, we highlight computer vision solutions combined with artificial intelligence algorithms that achieved important results in the detection of patterns in images. In this context, this work presents a systematic review that aims to identify the applicability of computer vision in precision agriculture for the production of the five most produced grains in the world: maize, rice, wheat, soybean, and barley. In this sense, we present 25 papers selected in the last five years with different approaches to treat aspects related to disease detection, grain quality, and phenotyping. From the results of the systematic review, it is possible to identify great opportunities, such as the exploitation of GPU (Graphics Processing Unit) and advanced artificial intelligence techniques, such as DBN (Deep Belief Networks) in the construction of robust methods of computer vision applied to precision agriculture.

show abstract

Section: Analysis Of Milled Rice Grains Using Svmmentioning

confidence: 99%

Computer vision and artificial intelligence in precision agriculture for grain crops: A systematic review

Patrício

Rieder

2018

Computers and Electronics in Agriculture

666

257

View full text Add to dashboard Cite

show abstract

“…Rice chalkiness has been scanned into 2D images based on grayscale value differences between chalky and normal regions in the rice kernel, and the chalky part in the kernel has been nely classi ed and marked in the image (Yoshioka et al, 2007;ISO 7301:2011). Some image processing software have been previously employed to analyze rice chalkiness by using multiple images captured from different angles of milled rice (Yoshioka et al, 2007;Chen et al, 2013;Sun et al, 2014). Scanning electron microscopy has been usually employed to reveal the density of starch at the µm-scaled level and then indirectly re ect the differences between the chalky and normal regions in the image (Li et al, 2014;Yu et al, 2017).…”

Section: Introductionmentioning

confidence: 99%

3D visualization and volume based quantification of rice chalkiness in vivo by using high resolution micro-CT

Xiao

2020

Preprint

View full text Add to dashboard Cite

Background: Rice quality research attracts attention worldwide. Rice chalkiness is one of the key indexes determining rice kernel quality. The traditional rice chalkiness measurement methods are mainly based on naked-eye observation or two-dimensional (2D) image analysis and the results could not represent the three-dimensional (3D) characteristics of chalkiness in the rice kernel. These methods are neither in vivo thus are unable to provide technical support for high throughput screening of rice chalkiness phenotype. Results: Here, we introduced a novel method for 3D visualization and accurate volume-based quantification of rice chalkiness in vivo by using X-ray microcomputed tomography (micro-CT). This approach not only develops a novel method to measure the rice chalkiness index, but also provides a high throughput solution for rice chalkiness phenotype analysis. Conclusions: Our method could be a new powerful tool for rice chalkiness measurement, which would greatly help the research of rice chalkiness traits as well as the quality evaluation in rice production practice.

show abstract

“…There are also several other commercial image analysis software programs available, for example, ImageJ and GrainScan (Abramoff, Magalhães, & Ram, 2004;Whan et al, 2014). Improved image processing methods have improved the measurement of rice chalk (Guangrong, 2011;Marschalek et al, 2017;Sun, Liu, et al, 2014;Xiaopeng & Yong, 2011;Yoshioka, Iwata, Tabata, Ninomiya, & Ohsawa, 2007).…”

Section: Introductionmentioning

confidence: 99%

Detection of chalk in single kernels of long‐grain milled rice using imaging and visible/near‐infrared instruments

et al. 2019

View full text Add to dashboard Cite

Background and objectives:To maintain the competitiveness of U.S. long-grain rice in U.S. and foreign markets, having translucent whole milled grain is critical. An objective technique to detect grain chalk, opaque areas in the grain, will provide breeders and industry with an effective tool for developing low-chalk varieties or agronomic practices that reduce chalk occurrence. Two instruments developed at Service (USDA-ARS), a single-kernel near-infrared (SKNIR) tube instrument and a silicon-based light-emitting diode (SiLED) high-speed sorter, were compared with two commercially available imaging instruments, WinSEEDLE and SeedCount used for chalk quantification. Three 2-way chalk classifications were defined for single kernels based on visual inspection: (a) <50% or ≥50% opacity or chalk (modified Grain Inspection, Packers & Stockyards Administration [GIPSA]), (b) <10% or ≥10% opacity (10% cutoff), and (c) 100% opacity or 100% translucent (MaxLevel). Findings: The SKNIR method provided the best classification for the modified GIPSA definition with an 82.4% average correct classification (CC), that is, 89% and 76% for nonchalky and chalky kernels, respectively. The WinSEEDLE had the best classification for the 10% cutoff definition, with an 84% CC for nonchalky kernels and a 96% CC for chalky kernels. For the MaxLevel definition, average CCs of both the SKNIR and SiLED methods were similar, at 93% and 95%, respectively. The average CCs were lower for both the WinSEEDLE method and the SeedCount method at 14% and 58%, respectively. These low CC values are a result of using a threshold of 100% for chalky or nonchalky kernels, where a single misclassified pixel within the image will cause misclassification. Calibration models developed for both the SKNIR and SiLED methods indicate that their classifications were based mainly on spectral differences near the adsorption bands for starch, protein, and water content. Conclusions: All of the instruments can be used to classify chalk, but their level of accuracy depends on how chalk is defined.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Evaluation and analysis the chalkiness of connected rice kernels based on image processing technology and support vector machine

Cited by 49 publications

References 8 publications

Computer vision and artificial intelligence in precision agriculture for grain crops: A systematic review

Computer vision and artificial intelligence in precision agriculture for grain crops: A systematic review

3D visualization and volume based quantification of rice chalkiness in vivo by using high resolution micro-CT

Detection of chalk in single kernels of long‐grain milled rice using imaging and visible/near‐infrared instruments

Contact Info

Product

Resources

About