Estimation of rice milling degree using image processing and Adaptive Network Based Fuzzy Inference System (ANFIS)

Shiddiq, Deden. M.F.; Nazaruddin, Yul Y.; Muchtadi, Farida I.; Raharja, Sapta

doi:10.1109/ica.2011.6130137

Cited by 13 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, some systems based on the changes of color, light or image already exist. For example, Shiddiq et al (2011) presented a measurement system of rice milling degree using image processing. Bhashyam and Srinivas (1984) described the determination of degree of milling by measuring whiteness using a photovoltaic reflectance meter.…”

Section: Introductionmentioning

confidence: 99%

Correlation Analysis between Color Parameters and Sensory Characteristics of Rice with Different Milling Degrees

Zhong

Liu

et al. 2013

Journal of Food Processing and Preservation

View full text Add to dashboard Cite

The effects of degrees of milling on color parameters and sensory characteristics of rice were evaluated, and their relationships were established by the method of Pearson correlation analysis and regression analysis. Results showed that with the increase of milling degree, color value a* and b* gradually decreased while L* value and eating quality correspondingly increased. The correlation analysis revealed that sensory characteristics were significantly negatively correlated with a* and b* value, and significantly positively correlated with L* value. In terms of color parameters, L* value had a significant negative correlation with a* and b* value, while a* and b* values were significantly positively correlated. Eating quality showed a linear relationship with a*, b* and L* value, and the R 2 values for the relationship were in the range of 0.90-0.99. Regression equations had high R 2 values and could be used to predict the eating quality of cooked rice. PRACTICAL APPLICATIONSThe traditional method of judging sensory characteristics of rice, which mainly conducted by experienced inspector, needs plenty of people and time for measurement. New measurement system, based on the establishment of relationship between color parameters and sensory characteristics, assists in quick locating the optimum degrees of milling to prevent poor judgment and increasing the accuracy and efficiency of working, meanwhile helps to predict the eating quality of cooked rice.

show abstract

Section: Introductionmentioning

confidence: 99%

Correlation Analysis between Color Parameters and Sensory Characteristics of Rice with Different Milling Degrees

Zhong

Liu

et al. 2013

Journal of Food Processing and Preservation

View full text Add to dashboard Cite

show abstract

“…As humans are highly variable in their perception of color, the colors determined by a colorimeter are used as standards. In image processing, a number of color spaces are available, including RGB [red-green-blue;(OuYang et al 2010)], HIS [hue-saturation-intensity; (Golpour et al 2014)]and CIE L*a*b* (Shiddiq et al 2011). Most food color measurements use the CIE L * a * b * color space because of its uniform distribution of colors and similarity to human perception of color (Leo ´n et al 2006).…”

Section: Introductionmentioning

confidence: 99%

Genetic variation underlying kernel size, shape, and color in two interspecific S. bicolor2 × S. halepense subpopulations

Nabukalu

Kong

Cox

et al. 2021

Genet Resour Crop Evol

View full text Add to dashboard Cite

Throughout the history of sorghum domestication, kernel traits have been subject to extensive selection. Breeding of grain sorghum is highly dependent on kernel morphology, which influences yield and quality. This study examined the genetic variation and architecture of kernel size, shape, and color among two BC 1 F 2 subpopulations, H4 and H6, derived from crossing Sorghum bicolor BTx623 and Sorghum halepense Gypsum 9E. We phenotyped 246 BC 1 F 2 families and their parents in two locations for two years using high-throughput digital imaging techniques, to determine fourteen kernel traits in five broad categories: size (area, length, width, and aspect ratio), shape (circularity and PC1), density (factor form density; FFD), weight (1000kernel weight) and color (RGB and CIE-L*a*b*). Based on single-trait, interval mapping, we identified 76 and 71 significant QTLs in the H4 and H6 subpopulations, respectively. Both parent genotypes contributed QTL alleles that conferred positive additive effects, indicating that Sorghum halepense contains alleles that may enhance some kernel-related traits of elite sorghums. Some genomic regions affect many traits-for example, a linkage group 6 homolog in the H4 subpopulation was associated with several kernel traits in the region between 0 and 57.3 cM, including FFD, area, length, and width; and in H6 between 56.8 and 185.9 cM contained QTLs associated with kernel color parameters (R, G, L* and B*), FFD, kernel shape (PC1), kernel area, aspect ratio, kernel width, and 1000-kernel weight. These results contribute to a better understanding of genetic factors governing sorghum kernel traits, providing a foundation for improving grain and quality traits in both annual and perennial sorghums using genomic tools.

show abstract

“…In such cases, fuzzy approach [23] is more convenient for discrimination of head and broken rice grains [24]. Shiddiq et al [25] investigated the rice milling degree using colour features (RGB) with an adaptive network-based fuzzy inference model. It was reported an error of 3.55-5.62% in milling degree using this process.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Neuro-Fuzzy Inference System Based Grading of Basmati Rice Grains Using Image Processing Technique

Mandal

2018

ASI

View full text Add to dashboard Cite

Grading of rice intents to discriminate broken and whole grain from a sample. Standard techniques for image-based rice grading using advanced statistical methods seldom take into account the domain knowledge associated with the data. In the context of a high product value basmati rice with an image based grading process, one ought to consider the physical properties of grain and the associated knowledge. In this present work, a model of quality grade testing and identification is proposed using a novel digital image processing and knowledge-based adaptive neuro-fuzzy inference system (ANFIS). The rationale behind adopting a grading system based on fuzzy rules relies on capabilities of ANFIS to simulate the behaviour of an expert in the characterization of rice grain using the physical properties of rice grains. The rice kernels are characterized with the help of morphological descriptors and geometric features which are derived from sample images of milled basmati rice. The predictive capability of the proposed technique has been tested on a sufficient number of training and test images of basmati rice grain. The proposed method outperforms with a promising result in an evaluation of rice quality with >98.5% classification accuracy for broken and whole grain as compared to standard machine learning technique viz. support vector machine (SVM) and K-nearest neighbour (KNN). The milling efficiency is also assessed using the ratio between head rice and broken rice percentage and it is 77.27% for the test sample. The overall results of the adopted methodology are promising in terms of classification accuracy and efficiency.

show abstract

Estimation of rice milling degree using image processing and Adaptive Network Based Fuzzy Inference System (ANFIS)

Cited by 13 publications

References 8 publications

Correlation Analysis between Color Parameters and Sensory Characteristics of Rice with Different Milling Degrees

Correlation Analysis between Color Parameters and Sensory Characteristics of Rice with Different Milling Degrees

Genetic variation underlying kernel size, shape, and color in two interspecific S. bicolor2 × S. halepense subpopulations

Adaptive Neuro-Fuzzy Inference System Based Grading of Basmati Rice Grains Using Image Processing Technique

Contact Info

Product

Resources

About