Classification of Basmati Rice Grain Variety using Image Processing and Principal Component Analysis

Kambo, Rubi; Yerpude, Amit

doi:10.14445/22312803/ijctt-v11p117

Cited by 28 publications

(12 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dubey, Bhagwat, Shouche, and Sainis (2006) discriminating the three wheat varieties based on morphometric features using image analysis, observed total accuracy equal up to 87.67%, including accuracies ranged from 81.67 to 94.00% for individual varieties. For varietal discrimination of basmati rice based on morphological features computed using image analysis, the overall accuracy of 79%, including the accuracy ranged from 75 to 80%, was obtained (Kambo & Yerpude, 2014). According to Chen, Xun, Li, and Zhang (2010), the seeds of five corn varieties were classified with total accuracy of over 90%, based on selected variables from the shape, geometric, and color features.…”

Section: Resultsmentioning

confidence: 99%

Identification of sorghum genotypes using a machine vision system

Nazari

Shaker

Karimi

et al. 2021

J Food Process Engineering

View full text Add to dashboard Cite

The aim of this study was to develop an innovative machine vision system based on seed texture and geometric parameters to evaluate their efficacy in the identification of sorghum genotypes. The images of sorghum grain were acquired by a digital camera. Texture parameters were calculated for images converted to individual color channels. The geometric features including length, width, perimeter, area as well as 10 shape factors were determined. The seeds of individual genotypes were classified using the discriminative classifiers. In the case of discriminant analysis performed using texture parameters, the total accuracy reached 95.6% for the model built based on textures selected from all color channels. The complete separation of some genotypes was confirmed by scatterplots. The results of discrimination based on textures selected from color space Lab revealed a total accuracy of up to 94.8%. Discriminative models based on textures selected from color space RGB resulted in a total accuracy of up to 93.5%. Models built based on geometric features provided the accuracy of up to 99% for comparison selected genotypes. Practical Applications The classification models developed in this study can efficiently be used for the identification of sorghum seeds. The results of the studies can be used in practice for the assessment of the authentication of seeds of sorghum cultivars in a rapid, nondestructive and cost‐effective way and it can be an alternative to chemical or molecular methods, which are more expensive, long‐lasting and more complicated. Therefore, the application of image analysis is a great novelty of the research for the identification of cereal grain genotype.

show abstract

Section: Resultsmentioning

confidence: 99%

Identification of sorghum genotypes using a machine vision system

Nazari

Shaker

Karimi

et al. 2021

J Food Process Engineering

View full text Add to dashboard Cite

show abstract

“…The number of cultivars is low for proving the performance of the proposed method. Kambo and Yerpude [17] classified common Basmati rice using PCA and employed a digital camera to capture an image of the seeds and transpose it onto a black background. They developed algorithms in MATLAB 2016a (MathWorks, Inc.) to extract morphologic specificities of each seed, including area, long axis length, small axle length, distance from the center, and circumference.…”

Section: Introductionmentioning

confidence: 99%

A Combined Method of Image Processing and Artificial Neural Network for the Identification of 13 Iranian Rice Cultivars

et al. 2020

View full text Add to dashboard Cite

Due to the importance of identifying crop cultivars, the advancement of accurate assessment of cultivars is considered essential. The existing methods for identifying rice cultivars are mainly time-consuming, costly, and destructive. Therefore, the development of novel methods is highly beneficial. The aim of the present research is to classify common rice cultivars in Iran based on color, morphologic, and texture properties using artificial intelligence (AI) methods. In doing so, digital images of 13 rice cultivars in Iran in three forms of paddy, brown, and white are analyzed through pre-processing and segmentation of using MATLAB. Ninety-two specificities, including 60 color, 14 morphologic, and 18 texture properties, were identified for each rice cultivar. In the next step, the normal distribution of data was evaluated, and the possibility of observing a significant difference between all specificities of cultivars was studied using variance analysis. In addition, the least significant difference (LSD) test was performed to obtain a more accurate comparison between cultivars. To reduce data dimensions and focus on the most effective components, principal component analysis (PCA) was employed. Accordingly, the accuracy of rice cultivar separations was calculated for paddy, brown rice, and white rice using discriminant analysis (DA), which was 89.2%, 87.7%, and 83.1%, respectively. To identify and classify the desired cultivars, a multilayered perceptron neural network was implemented based on the most effective components. The results showed 100% accuracy of the network in identifying and classifying all mentioned rice cultivars. Hence, it is concluded that the integrated method of image processing and pattern recognition methods, such as statistical classification and artificial neural networks, can be used for identifying and classification of rice cultivars.

show abstract

“…It has been reported that rice has been cultivated in China and Thailand dating from about 6000 B.C. [1,2] There are different cultivars of rice grown throughout the world, [3] each cultivar exhibiting distinct physico-chemical properties, and the type of the starch present influencing the cooking quality. [4] Consumer preference is normally dependent on the growing location and this is a crucial factor for the selection and utilization of rice cultivars in a given location.…”

Section: Introductionmentioning

confidence: 99%

Effect of Different Cooking Conditions on the Pasting Properties of Flours of Glutinous Rice Varieties from Lao People’s Democratic Republic

Nawaz

Fukai

Bhandari

2016

International Journal of Food Properties

View full text Add to dashboard Cite

The effect of different rehydration temperatures (30, 40, and 50°C) and cooking times (2.7, 4.7, 6.7, 8.7, and 10.7 min) at 95°C on the pasting properties of three glutinous varieties (Thadokkham-11, Thadokkham-8, and Hom Mali Niaw) from Lao People's Democratic Republic was investigated using rapid visco analyzer. Non-glutinous varieties (IR64 and Doongara) were also analyzed to compare glutinous (amylose <4.5%) and non-glutinous (amylose >15%) varieties. All rice flours took up water at significantly (p < 0.05) higher rates in the case of increased temperature and soaking time, resulting in a decrease in the onset temperature for pasting. Among the glutinous rices, Thadokkham-8 showed a significant (p < 0.05) decrease in peak viscosity in response to increased rehydration time and temperature. For this variety maximum viscosity (2403.3 mPas) was observed at 1 min of rehydration at 30°C and minimum viscosity (1852.0 mPas) at 15 min of rehydration at 50°C. The viscosity values of Thadokkham-11 and Hom Mali Niaw varieties increased to their highest values (1608.7 and 1477.7 mPa.s, respectively) with an increase in temperature to 40°C for 1 min. In general, the glutinous rices produced weaker gel than non-glutinous rices. Extended holding at cooking temperature (95°C) had a more significant (p < 0.05) effect on the glutinous varieties Thadokkham-8 and Thadokkham-11 than on the non-glutinous varieties (IR64 and Doongara) used in this study.

show abstract

Classification of Basmati Rice Grain Variety using Image Processing and Principal Component Analysis

Cited by 28 publications

References 0 publications

Identification of sorghum genotypes using a machine vision system

Identification of sorghum genotypes using a machine vision system

A Combined Method of Image Processing and Artificial Neural Network for the Identification of 13 Iranian Rice Cultivars

Effect of Different Cooking Conditions on the Pasting Properties of Flours of Glutinous Rice Varieties from Lao People’s Democratic Republic

Contact Info

Product

Resources

About