Discrimination of wheat grain varieties using image analysis and neural networks. Part I. Single kernel texture

Zapotoczny, Piotr

doi:10.1016/j.jcs.2011.02.012

Cited by 61 publications

(32 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Table 3 shows the results of a tested number of hidden neurons. Based on the neural network training utilizing the training and testing dataset using 5,10,15,20,25,30,35,40 and 45 hidden neurons. The lowest MSE value of 0.1966 was obtained using the 40 hidden neurons with the accuracy of 64.6% and 70.0% for testing and training data sets respectively.…”

Section: E Identification Of Rice Seed Varietiesmentioning

confidence: 99%

Rice Seed Varieties Identification based on Extracted Colour Features using Image Processing and Artificial Neural Network (ANN)

Aznan

Ruslan

Rukunudin

et al. 2017

International Journal on Advanced Science, Engineering and Information Technology

View full text Add to dashboard Cite

Abstract-Determination of rice seed varieties is very important to ensure varietal purity in the production of high-quality seed. To date, manual seed inspection is carried out to separate foreign rice seed varieties in rice seed sample in the laboratory as there is lack of an automatic seed classification system. This paper describes a simple approach of using image processing technique and artificial neural network (ANN) to determine rice seed varieties based on extracted colour features of individual seed images. The experiment was conducted using 200 individual seed images of two Malaysian rice seed varieties namely MR 219 and MR 269. The acquired seed images were processed using a set of image processing procedure to enhance the image quality. Colour feature extraction was carried out to extract the red (R), green (G), blue (B), hue (H), saturation (S), value (V) and intensity (I) levels of the individual seed images. The classification using ANN was carried out by dividing the data sets into training (70% of data), validation (15%) and testing (15%) dataset respectively. The best ANN model to determine the rice seed varieties was developed, and the accuracy levels of the classification results were 67.5% and 76.7% for testing and training data sets using 40 hidden neurons.

show abstract

Section: E Identification Of Rice Seed Varietiesmentioning

confidence: 99%

Rice Seed Varieties Identification based on Extracted Colour Features using Image Processing and Artificial Neural Network (ANN)

Aznan

Ruslan

Rukunudin

et al. 2017

International Journal on Advanced Science, Engineering and Information Technology

View full text Add to dashboard Cite

show abstract

“…Digital image analysis supports the determination of the morphological, textural and optical parameters in the acquired images, and their qualitative and quantitative interpretation [19][20][21][22][23]. Jirsa and Polišenska [15] relied on digital image analysis to distinguish between Fusarium-infected and healthy wheat kernels based on a classification model with colour descriptors R (red), G (green), B (blue) in the RGB colour space and descriptor H (Hue) in the HSL (Hue, Saturation, Luminance) colour space.…”

Section: Introductionmentioning

confidence: 99%

Classification of Fusarium-infected and healthy wheat kernels based on features from hyperspectral images and flatbed scanner images: a comparative analysis

Ropelewska

Zapotoczny

2018

Eur Food Res Technol

Self Cite

View full text Add to dashboard Cite

Wheat infections caused by fungi of the genus Fusarium decrease yields and have serious economic consequences. The produced mycotoxins have harmful effects on human and animal health. The aim of this study was to develop classification models based on selected textural parameters to distinguish between infected and healthy wheat kernels. The classification accuracy of kernels positioned on the ventral side was determined at 78-100% in the model based on textural parameters from hyperspectral images, and at 95-100% based on images generated by a flatbed scanner. Kernels positioned on the dorsal side were correctly classified in 78-98% based on hyperspectral images, and in 92-100% based on colour images. In the models combining textural parameters from the ventral and dorsal sides of wheat kernels, classification accuracy reached 76-98% in hyperspectral images, and 94-100% in images generated by a flatbed scanner. The imaging technique-flatbed scanner and the ventral side of the kernels provided higher classification accuracy results. The results will contribute to further research aiming to develop models for the determination of fungal chemotypes and/or fungal species based on selected textural features of wheat kernels.

show abstract

“…For example, the efficiency of texture-based classification of 11 wheat cultivars grown in Poland reached 100% (Zapotoczny, 2011 a;. Pazoki and Pazoki (2011), using texture, morphology and colour features coupled with ANN classified rain fed wheat grain cultivars with an accuracy of 87%.…”

mentioning

confidence: 99%

Grain morphology, texture and colour-related compounds of bread wheat cultivars in relation to cultivation regimes and growing location

Tańska

Buczek

Jarecki

et al. 2018

Zemdirbyste-Agriculture

View full text Add to dashboard Cite

Digital wheat grain classification systems are primarily based on kernel image and texture features. These traits are highly environment-dependent, so sample-to-sample variation may affect results of grain classification, grading, or discrimination. The main aim of this study was to determine the intra-cultivar variation of wheat kernel size, shape, colour, endosperm hardness and selected chemical compounds (carotenoids, phlobaphenes and proteins) associated with kernel colour. In the study, four winter bread wheat cultivars: two self-pollinated 'Bogatka' and 'Batuta' and two hybrid cultivars 'Hybred' and 'Hymack' were grown in different environments (extensive and intensive cultivation regimes, and three growing locations) to create variation in the kernel image, hardness and chemical compounds to simulate the range of variations encountered in reality. Measurements of kernel colour and dimensions were conducted using digital image analysis, hardness and protein content were analysed using nearinfrared reflectance (NIR) spectroscopy, while carotenoids and phlobaphenes were examined using colorimetric assays. The results showed that kernel dimensions and shape were highly intra-cultivar constant, with the highest variation of thickness (up to 7.59%) and volume (up to 10.10%). Surface colour was also relatively constant, with saturation as the most variable feature (up to 11.44%). In contrast, endosperm colour revealing an approx. 2-3-fold higher variation of colour attributes than surface colour, and the highest variation was observed in the case of saturation of the colour (up to 19.67%). Among the tested chemical compounds, carotenoids were the least intra-cultivar variable (up to 14.39%), while phlobaphenes the most intra-cultivar variable (up to 31.87%). Grain hardness was the most intra-cultivar variable feature of the tested grain samples and reached the highest value of 49.02% for cultivar 'Hymack'. The genotype had the greatest effect on kernel colour (up to 50.49% of the source of variation) and carotenoids (52.97%). The environment affected mostly the grain proteins (82.20%) and hardness (72.61%).

show abstract

Discrimination of wheat grain varieties using image analysis and neural networks. Part I. Single kernel texture

Cited by 61 publications

References 28 publications

Rice Seed Varieties Identification based on Extracted Colour Features using Image Processing and Artificial Neural Network (ANN)

Rice Seed Varieties Identification based on Extracted Colour Features using Image Processing and Artificial Neural Network (ANN)

Classification of Fusarium-infected and healthy wheat kernels based on features from hyperspectral images and flatbed scanner images: a comparative analysis

Grain morphology, texture and colour-related compounds of bread wheat cultivars in relation to cultivation regimes and growing location

Contact Info

Product

Resources

About