<span>Presently, the demands for rice are increasing. This will affects the need for producing and sorting rice grain in faster and exceed the normal requirement. However, the manual rice classification using naked eyes are not very accurate and only professionals are able to do it. Machine learning is found to be a suitable technique for rice classification in producing an accurate result and faster solution. Thus, a study on the classification of rice grain using an image processing technique is presented. The rice grain image went through the pre-processing process which includes the grayscale and binary conversion, and segmentation before the feature extraction process. Four attributes of shape descriptor which are area, perimeter, major axis length, and minor axis length and three attributes of color descriptor which are hue, saturation and value were extracted from each rice grain image. In another note, a Multi-class Support Vector Machine (SVM) is used to classify the three types of rice grain which are basmathi, ponni and brown rice. The performance of the proposed study is evaluated to 90 testing images which returned 92.22% of classification accuracy. The study is expected to assist the Agrotechnology industry in automatic classification of rice grain in the future.</span>
Fruit recognition is useful for automatic fruit harvesting. Fruit recognition application can reduce or minimize human intervention during fruit harvesting operation. However, in computer vision, fruit recognition is very challenging because of similar shapes, colors and textures among various fruits. Illuminations changes due to weather condition also leads to a challenging task for fruit recognition. Thus, this paper tends to investigate the performance of basic Convolutional Neural Network (CNN), Alexnet and Googlenet in recognizing nine different types of fruits from a publicly available dataset. The experimental results indicate that all these techniques produce excellent recognition accuracy, but basic CNN achieves the fastest recognition result compared with Alexnet and Googlenet.
This research investigates the application of texture features for leaf recognition for herbal plant identification. Malaysia is rich with herbal plants but not many people can identify them and know about their uses. Preservation of the knowledge of these herb plants is important since it enables the general public to gain useful knowledge which they can apply whenever necessary. Leaf image is chosen for plant recognition since it is available and visible all the time. Unlike flowers that are not always available or roots that are not visible and not easy to obtain, leaf is the most abundant type of data available in botanical reference collections. A comparative study has been conducted among three popular texture features that are Histogram of Oriented Gradients (HOG), Local Binary Pattern (LBP) and Speeded-Up Robust Features (SURF) with multiclass Support Vector Machine (SVM) classifier. A new leaf dataset has been constructed from ten different herb plants. Experimental results using the new constructed dataset and Flavia, an existing dataset, indicate that HOG and LBP produce similar leaf recognition performance and they are better than SURF.
This research investigates the ripeness grading identification of the palm oil FFB using color features that are color histogram, color moment and color correlogram during the optimum stage of its ripeness since it improves the FFB oil quality and quantity.Harvesting wrong bunches decreases the oil extraction rate of the palm.
<span lang="EN-US">Maize is one of the world's leading food supplies. Therefore, the crop's production must continue to reproduce to fulfill the market demand. Maize is an active feeder, therefore, it need to be adequately supplied with nutrients. The healthy plants will be in deep green color to indicate it consist of adequate nutrient. Current practice to identify the nutrient deficiency on maize leaf is throught a laboratory test. It is time consuming and required agriculture knowledge. Therefore, an image processing approach has been done to improve the laboratory test and eliminate a human error in identification process. The purpose of this research is to help agriculturist, farmers and researchers to identify the type of maize nutrient deficiency to determine an action to be taken. This research using image processing techniques to determine the type of nutrient deficiency that occurs on the plant leaf. A combination of Gray-Level Co-Occurrence Matrix (GLCM), hu-histogram and color histogram has been used as a parameter for further classification process. Random forest technique was used as classifiers manage to achive 78.35% of accuracy. It shows random forest is a suitable classifier for nutrient deficiency detection in maize leaves. More machine learning algorithm will be tested to increase current accuracy.</span>
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.