An Automated Image Processing Module for Quality Evaluation of Milled Rice

Abstract

The paper demonstrates a low-cost rice quality assessment system based on image processing and machine learning (ML) algorithms. A Raspberry-Pi based image acquisition module was developed to extract the structural and geometric features from 3081 images of eight different varieties of rice grains. Based on features such as perimeter, area, solidity, roundness, compactness, and shape factor, an automatic identification system is developed to segment the grains based on their types and classify them by using seven machine learning algorithms. These ML models are trained using the images and are compared using different ML models. ROC curves are plotted for each model for quantitative analysis to assess the model’s performance. It is concluded that the random forest classifier presents an accuracy of 77 percent and is the best-performing model for the classification of rice varieties. Furthermore, the same algorithm is efficiently employed to determine the price of adulterated rice samples based upon the market price of individual rice.

Design and Use of Deep Confidence Network Based on Crayfish Optimization Algorithm in Automatic Assessment Method of Hearing Effectiveness

“…Literature [11] focuses on the total strategy guidance of listening pedagogy, analyzes the development trend of listening teaching, and puts forward the concept of multistrategy listening teaching; Literature [12] takes the data of non-English majors' graduate students as the research samples to test and evaluate the effect and feasibility of the integration of listening strategies into the teaching classroom; Literature [13] constructs the model of the process of listening comprehension and the model of the training of learning strategies through methodological surveys and other methods. Random Forest method is used to construct an automatic listening evaluation method, which confirms the feasibility of listening strategies in the Chinese foreign language classroom environment; Literature [14] analyzes the automatic scoring process of listening, combines machine learning algorithms, and proposes a scoring method based on multivariate current regression and Random Forest; Literature [15] analyzes the characteristics of the scoring of the effect of English listening from the English listening strategies, and proposes a multi-intelligence method fusion of the automatic scoring method of the listening system; Literature [16] proposed the whole process of the English listening classroom in three aspects, such as teaching preparation, teaching application and teaching evaluation, and at the same time, constructed an automatic evaluation system of English listening and proposed an automatic evaluation method based on deep learning algorithms; Literature [17], on the basis of reflecting on the traditional English listening strategies, discussed language proficiency, critical thinking ability and intercultural competence as the listening learning strategy goals, and proposed a neural network-based English listening assessment method; Literature [18] analyzed different listening strategies in multimedia environments. According to the analysis of the above literature, the existing listening assessment methods have the following defects [19]: 1) the selection of influencing factors of the listening assessment system is not standard enough and cannot reflect the characteristics of the whole process; 2) the listening assessment methods lack generalization.…”

New Insights into Recent Trends and Emerging Technologies in Apple Sorting

“…The term “digital image processing (DIP)” often refers to employing a digital computer algorithm to process a two-dimensional image, as opposed to “analogical image processing”, which modifies an image using electrical impulses (such as a television image) . Researchers have extensively employed DIP for apple sorting based on the size, shape, color, texture, and flaws in the stem and calyx, as summarized in Table . ,,,, …”

Identification of Turmeric Rhizomes Using Image Processing and Machine Learning

“…The proposed classifier was tested with visually similar turmeric rhizome varieties. The performances of classifiers were evaluated with a confusion matrix and an ROC curve [18,19]. According to the confusion matrix, all five varieties of turmeric rhizome were classified with the highest accuracy by using the SVM classifier.…”