scholarly journals Machine learnt image processing to predict weight and size of rice kernels

2019 ◽  
Author(s):  
Samrendra K Singh ◽  
Sriram K Vidyarthi ◽  
Rakhee Tiwari
Keyword(s):  
Machine Learning ◽  
Image Processing ◽  
Uncertainty Quantification ◽  
Rice Yield ◽  
Image Processing Algorithm ◽  
Rice Quality ◽  
Head Rice ◽  
Kernel Length ◽  
Head Rice Yield ◽  
The Individual

AbstractAccurate measurement of rice kernel sizes after milling is critical to design, develop and optimize rice milling operations. The size and mass of the individual rice kernels are important parameters typically associated with rice quality attributes, particularly head rice yield. In this study, we propose a novel methodology that combines image processing and machine learning (ML) ensemble to accurately measure the size and mass of several rice kernels simultaneously. We have developed an image processing algorithm with the help of recursive method to identify the individual rice kernels from an image and estimate the size of the kernels based on the pixels a kernel occupies. The number of pixels representing a rice kernel has been used as its digital fingerprint in order to predict its size and mass. We have employed a number of popular machine learning models to build a stacked ensemble model (SEM), which can predict the mass of the individual rice kernels based on the features derived from the pixels of the individual kernels in the image. The prediction accuracy and robustness of our image processing and SEM are quantified using uncertainty quantification. The uncertainty quantification showed 3.6%, 2.5%, and 2.4% for mean errors in estimating the kernel length of small-grain (Calhikari-202), medium-grain (Jupiter), and long-grain (CL153) rice, respectively. Similarly, mean errors associated with predicting the 1000 grain weight are 4.1%, 2.9%, and 4.3% for Calhikari-202, Jupiter, and CL153, respectively. Use of the developed algorithm in rice imaging analyzers could facilitate head rice yield quantifications and promote quicker rice quality appraisals.

scholarly journals Size and mass prediction of almond kernels using machine learning image processing

2019 ◽  
Author(s):  
Sriram K Vidyarthi ◽  
Rakhee Tiwari ◽  
Samrendra K Singh
Keyword(s):  
Machine Learning ◽  
Image Processing ◽  
Average Length ◽  
Ensemble Model ◽  
Image Processing Algorithm ◽  
Yield And Quality ◽  
Digital Fingerprint ◽  
The Mean ◽  
The Individual ◽  
Vital Parameters

AbstractAfter harvesting almond crop, accurate measurement of almond kernel sizes is a significant specification to plan, develop and enhance almond processing operations. The size and mass of the individual almond kernels are vital parameters usually associated with almond quality, particularly head almond yield. In this study, we propose a novel methodology that combines image processing and machine-learning ensemble that accurately measures the size and mass of whole raw almond kernels (classification - Nonpareil) simultaneously. We have developed an image-processing algorithm using recursive method to identify the individual almond kernels from an image and estimate the size of the kernels based on the occupied pixels by a kernel. The number of pixels representing an almond kernel was used as its digital fingerprint to predict its size and mass. Various popular machine learning (ML) models were implemented to build a stacked ensemble model (SEM), predicting the mass of the individual almond kernels based on the features derived from the pixels of the individual kernels in the image. The prediction accuracy and robustness of image processing and SEM were analyzed using uncertainty quantification. The mean error in estimating the average length of 1000 almond kernel was 3.12%. Similarly, mean errors associated with predicting the 1000 kernel mass were 0.63%. The developed algorithm in almond imaging in this study can be used to facilitate a rapid almond yield and quality appraisals.

Establishment of Rice Quality Prediction Model for Intermittent Drying

2021 ◽  
Vol 64 (4) ◽  
pp. 1355-1363
Author(s):  
Qi Song ◽  
Xinhua Wei
Keyword(s):  
Moisture Content ◽  
Prediction Model ◽  
Intelligent Control ◽  
Evaluation Method ◽  
Rice Yield ◽  
Drying Process ◽  
Rice Quality ◽  
Head Rice ◽  
Head Rice Yield ◽  
Rice Drying

HighlightsThis study explored the feasibility of developing an evaluation method for rice quality.A unified quality scale for different drying cycles facilitates evaluation of rice quality after drying.A head rice yield (HRY) prediction model was established that fit well with the actual HRY.The established HRY prediction model can be used as a performance index for optimization of rice drying.Abstract. Intelligent control of the drying process is important to achieve better rice quality. An effective quality evaluation method is the basis for intelligent control of rice drying. To study the effects of intermittent drying on the quality of paddy rice and explore the feasibility of establishing a quality evaluation method, intermittent drying experiments were conducted with variety Nanjing 9108 (Oryza sativa L.). The paddy samples were dried from an initial moisture content of 23.10% to 14% wet basis (w.b.). The paddy samples were initially dried at 60°C to various moisture contents without tempering. These pre-dried samples were then dried using different drying temperatures to obtain specific moisture content reductions, tempered, and then dried again at 60°C to the final moisture content of 14% w.b. without tempering. After drying, the quality parameters of the paddy samples were measured and analyzed. The R2 values of the head rice yield (HRY) prediction model, chalkiness prediction model, and protein prediction model established in this study were 0.75, 0.44, and 0.26, respectively. The HRY prediction model was shown to accurately predict HRY in the intermittent drying experiments. Within the range of the model parameters, the effectiveness of the HRY prediction model was explored by constant-temperature intermittent drying and variable-temperature intermittent drying. The results showed that if the summation of the predicted changes in HRY is large, then the measured HRY will be large. Therefore, the HRY prediction model can be used as a performance index for rolling optimization of the paddy drying process. Keywords: Head rice yield, Intermittent drying, Prediction model, Rice quality.

Estimating Head Rice Yield of Long-Grain Rice using a Bending Force Instrument

2019 ◽  
Vol 35 (3) ◽  
pp. 319-323 ◽  
Author(s):  
Zephania R. Odek ◽  
Terry J. Siebenmorgen
Keyword(s):  
Bending Strength ◽  
Rice Yield ◽  
Polarized Light ◽  
Alternative Methods ◽  
Rice Quality ◽  
Head Rice ◽  
Rough Rice ◽  
Head Rice Yield ◽  
Rice Yields ◽  
Rice Milling

Abstract. Head rice yield is an important index of rice quality. The official procedure for determining head rice yield requires a 1000-g sample of rough rice or a lesser sample of rough rice for a modified procedure. In certain situations, such amounts of rough rice may not be available for conducting an actual milling analysis; thus, there is a need to provide alternative methods of estimating head rice yield using a smaller sample. In this study, a PaddyCheck instrument was used to individually measure the three-point bending strength of approximately 250 rough rice kernels per sample. The instrument then classified the kernels as either “hard,” “soft,” or “broken by a force <17 N” (BBF). Additionally, each kernel was individually illuminated using polarized light as a means of estimating chalkiness. The kernel parameters measured using the PaddyCheck were then used to develop an equation for estimating head rice yield, based upon head rice yields determined using a modified milling procedure. The equation developed could be used in conjunction with the PaddyCheck instrument to provide estimates of head rice yield and thus, might allow the instrument to be more useful to practitioners in breeding programs and others involved in harvesting and drying operations to compare head rice yields of various samples/treatments, where the available rough rice sample or time is not sufficient to conduct an actual milling analysis. Keywords: Breaking force, Head rice yield, PaddyCheck, Rice milling, Rice quality, Rough rice.

A Study of Paddy Heating for Insect Elimination and Improving Milled Rice Quality

2012 ◽  
Vol 472-475 ◽  
pp. 1707-1713
Author(s):  
Pradit Ramatchima ◽  
Somposh Sudajan ◽  
Chaiyan Junsiri ◽  
Thavachai Thivavarnvongs
Keyword(s):  
Death Rate ◽  
Feeding Rate ◽  
Rice Yield ◽  
Feeding Rates ◽  
Milled Rice ◽  
Rice Quality ◽  
Head Rice ◽  
Head Rice Yield ◽  
Screen Height ◽  
Temperature Levels

This research was aimed at studying the effects of heating the paddy for insect killing and thereby improving subsequently milled rice quality. The experimental temperatures were in the range of 120-200°C, the paddy feeding rates were 60, 120, and 180 kg/h and the heights of the vibration screen were 5, 6, and 8 mm. The findings indicated that when the feeding rates increased between 120 and 180 kg/h, the insect death rate increased for nearly all temperature levels, whereas the feeding rate of 60 kg/h and the vibration screen height of 6 mm were found to give 100% insect killing efficiency. The resulting head rice yield increased by 0.3-0.7% for a screen height of 8 mm. The quantity of broken rice decreased whereas the total rice quantity did not vary significantly; the milled rice had a whiteness index slightly increased when compared to the reference rice.

scholarly journals Method of producing parboiled rice without steam by fluidized bed dryer

2020 ◽  
Vol 187 ◽  
pp. 01002
Author(s):  
Asadayuth Mitsiri ◽  
Somkiat Prachayawarakorn ◽  
Sakamon Devahastin ◽  
Wathanyoo Rordprapat ◽  
Somchart Soponronnarit
Keyword(s):  
Moisture Content ◽  
Fluidized Bed ◽  
Rice Yield ◽  
Experimental Result ◽  
Rice Starch ◽  
Parboiled Rice ◽  
Starch Gelatinization ◽  
Fluidized Bed Dryer ◽  
Head Rice ◽  
Head Rice Yield

A more simple methodology of producing parboiled rice is subject to be investigated in this work with proposed the method, the gelatinization of rice starch, commonly taking place at the steaming step in the traditional process, and drying are combined and replaced by a hot air fluidized bed dryer. A pilot-scale continuous fluidized bed, with a maximum capacity of 140-150 kg/h, has been designed, constructed and tested. Suphanburi 90 paddy variety with high amylose content was dipped into hot water at temperatures of 70, 80, 83°C for 4.0, 3.3, 3.2 h, respectively, to get the moisture content around 47-55% db and dried at 150-170°C using air speed of 3.5 m/s. The paddy bed depth within the dryer was 3 and 5 cm. In the dryer operation, the exhaust air was fully recycled and reheated again by 30 kW electrical heaters to the desired temperature. The experimental result has shown that parboiled rice with a different degree of starch gelatinization could be produced by this technique. The degree ranged between 80-100% as examined by differential scanning calorimeter. The exit moisture content was given in a range of 14-21% db, relying on the drying temperature and soaking time. The aforementioned exit moisture contents were not a detrimental effect on head rice yield although the tempering was not included. The head rice yield was given in the range of 59-66%, depending on the degree of starch gelatinization. The starch granules lost their original shape as revealed by scanning electron microscope.

scholarly journals Effect of temperature and mode of drying on bioactive compounds and quality of germinated parboiled rice

2018 ◽  
Author(s):  
Busarakorn Mahayothee ◽  
Supaporn Klaykruayat ◽  
Marcus Nagle ◽  
Joachim Müller
Keyword(s):  
Bioactive Compounds ◽  
Rice Yield ◽  
Aminobutyric Acid ◽  
Flow Mode ◽  
Gamma Aminobutyric Acid ◽  
Parboiled Rice ◽  
Head Rice ◽  
Through Flow ◽  
Head Rice Yield

Germinated parboiled rice (GPR) is recognized as a functional food because it is rich in bioactive compounds, especially gamma-aminobutyric acid (GABA). GPR was produced by soaking, incubating, steaming, and then drying using a high-precision hot air dryer. The results indicated that air flow mode and drying temperature had significant effects on the quality of GPR. Drying at higher temperatures and shorter times conserved GABA content. Using through-flow mode decreased drying time and prevented color change. However, a slightly lower percentage of head rice yield was observed. Moreover, using through-flow mode negatively affected the hardness loss after cooking.Keywords: Germinated parboiled rice; Drying mode; Gamma-aminobutyric acid; Head rice yield  

X-Ray Detection of Fissures in Rough Rice Kernels

2017 ◽  
Vol 33 (5) ◽  
pp. 721-728 ◽  
Author(s):  
Zephania R. Odek ◽  
Bhagwati Prakash ◽  
Terry J. Siebenmorgen
Keyword(s):  
Rice Yield ◽  
X Rays ◽  
Milled Rice ◽  
Substantial Impact ◽  
X Ray ◽  
X Ray Imaging ◽  
Head Rice ◽  
Rough Rice ◽  
Head Rice Yield ◽  
Rice Drying

Abstract. X-ray imaging is a viable method of fissure detection in rough rice kernels owing to the ability of X-rays to penetrate hulls, thus allowing visualization of internal rice kernel structure. Traditional methods of fissure detection are only applicable for brown and milled rice, and therefore cannot be used to study fissures developed during rough rice drying. In this study, the fissure detection capability of an X-ray system was evaluated and the relationship between head rice yield (HRY), as measured through laboratory milling, and the percentage of fissured rough rice kernels was determined. Long-grain rice lots of various cultivars were dried using heated air at 60°C, 10% relative humidity (RH) for five drying durations to produce different degrees of fissuring, and then milled to determine HRY. A strong linear correlation (R2 = 0.95) between HRY and the percentage of fissured rough rice kernels after drying was determined. This correlation confirms the substantial impact that kernel fissures have on milling yields. Overall, these findings show the effectiveness of X-ray imaging in rough rice fissure detection, which could allow for drying research that may provide a better understanding of kernel fissuring kinetics. Keywords: Fissures, Grainscope, Head rice yield, Rice drying, X-ray imaging.

Rice grain protein composition influences head rice yield

2018 ◽  
Vol 95 (2) ◽  
pp. 253-263 ◽  
Author(s):  
Jeanette L. Balindong ◽  
Rachelle M. Ward ◽  
Terry J. Rose ◽  
Lei Liu ◽  
Carolyn A. Raymond ◽  
...  
Keyword(s):  
Rice Yield ◽  
Protein Composition ◽  
Grain Protein ◽  
Rice Grain ◽  
Head Rice ◽  
Head Rice Yield
Sign in / Sign up

Export Citation Format

Share Document