Contrastive analysis of rice grain classification techniques: multi-class support vector machine vs artificial neural network

Ibrahim, Shafaf; Kamaruddin, Saadi Bin Ahmad; Zabidi, Azlee; Ghani, Nor Azura Md

doi:10.11591/ijai.v9.i4.pp616-622

Cited by 4 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In comparison, study made by (8) , the previous author used SVM classifier. SVM has limited to two class classifiers.…”

Section: Resultsmentioning

confidence: 99%

“…b) Freeman code: Features into four regions after dividing the grain image as shown in Figure 2(a). We perform the freeman code for every region (8) . It's the very old contour descriptor and mostly used today.…”

Section: Morphological Featuresmentioning

confidence: 99%

“…Consuming the function "TRAINLM" the training is done from the Matlab neural network toolbox. The hyperbolic tangent and linear Matlab functions "tang" and "pure" are Activation functions (8) . We decide on the training error during the training phase, we mixed the neurons' numbers in the hidden layer.…”

Section: Training Phase and Network Architecturementioning

confidence: 99%

See 2 more Smart Citations

A Novel Algorithm for Identifying Organic Cereals by Optimal Features and Intelligent Classifiers

Bhensjaliya,

Dalwadi

2023

IJST

View full text Add to dashboard Cite

Objectives: To develop a suitable algorithm with artificial neural network, wavelet transforms for image classification problem using cereal dataset and to make a performance comparison against different features. The major objective of this study is to perform image classification on cereals dataset images. Methods: This study used Statistical classification and the fuzzy logic-based methods. Image classification is performed on the cereals dataset using morphological, color, and wavelet components with different features. 70 number of images used for testing and 30 number of images for training. The performance of the working of morphological, color, and wavelet components in classifying images from the cereals dataset is compared against different features namely major axis length, minor axis length, area, centroid, and perimeter. Findings: The study found that (Artificial Neural Network) ANN worked better with training accuracy of 95%, testing accuracy of 91% compared to MSVM (Multiclass support vector machine) and (K -Nearest neighbor) KNN algorithm. Novelty: This study presents a comparative aspect of image classification using morphological, color, and wavelet components using different features since not many studies or research articles showed the performance comparison of different classification methods along with different features. Since the real-world scenarios of today require enormous data to be processed, ANN can fit well to diversify applications since they highly reduce the number of parameters to be trained that speeds up the training process. Moreover, to be specific on image classification problems they require the best and most prominent features to be detected and uncovered. This can be achieved using ANN since it has the concept of classification using training and testing at its Core. Hence, ANN is highly recommended for such image classification applications than the traditional artificial-neural-networks because of the aforementioned reasons.

show abstract

“…In comparison, study made by (8) , the previous author used SVM classifier. SVM has limited to two class classifiers.…”

Section: Resultsmentioning

confidence: 99%

Section: Morphological Featuresmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Algorithm for Identifying Organic Cereals by Optimal Features and Intelligent Classifiers

Bhensjaliya,

Dalwadi

2023

IJST

View full text Add to dashboard Cite

show abstract

“…Using the watershed algorithm, touching and overlapped objects can recognize. Due to the noise and non-uniform illumination watershed algorithm gives over the segmented image (8) . Therefore, the marker-based watershed algorithm is used in this method.…”

Section: Segmentationmentioning

confidence: 99%

Performance Analysis of Cereals Grains using Neural Network & Multi Support Vector Machine

Bhensjaliya¹,

Dalwadi²

2022

IJST

View full text Add to dashboard Cite

Objectives: To classify cereal grain using a multi-support vector machine and artificial neural network for better accuracy. To build a system for cereals grains classification with the use of image processing techniques. Methods: Using a CCD camera, the method starts with image acquisition. To acquire images Grayscale conversion, noise reduction, binarization, edge detection, and morphological operations are applied. Using the edge detection technique edge of the objects is predictable. The watershed algorithm is used for the segmentation of touching and overlapping cereals kernels. Local Binary Pattern (LBP) texture feature and color features extracted from segmented images. For image classification, the features extraction method is used. Findings: We have incorporated various parameters like shape, size, length, width, major axis length, and minor axis lengths on different cereals like rice, barley, millet, sorghum, wheat, and millet. There are a total of 96 images of the data set are used to train or test the model. Out of that 70% are training and 30% are testing. Improvements: In the proposed MSVM technique, we have achieved 89.7% accuracy and in the ANN technique the accuracy is 92.3% which is higher than the conventional SVM technique. Novelty: The proposed technique is based on the Multi Support Vector Machine (MSVM) and Artificial Neural Network (ANN). We have compared the MSVM and ANN with the SVM technique.

show abstract

Deep CNN-based damage classification of milled rice grains using a high-magnification image dataset

Bhupendra

Moses

Miglani

et al. 2022

Computers and Electronics in Agriculture

View full text Add to dashboard Cite

Contrastive analysis of rice grain classification techniques: multi-class support vector machine vs artificial neural network

Cited by 4 publications

References 21 publications

A Novel Algorithm for Identifying Organic Cereals by Optimal Features and Intelligent Classifiers

A Novel Algorithm for Identifying Organic Cereals by Optimal Features and Intelligent Classifiers

Performance Analysis of Cereals Grains using Neural Network & Multi Support Vector Machine

Deep CNN-based damage classification of milled rice grains using a high-magnification image dataset

Contact Info

Product

Resources

About