Mango ripeness classification system using hybrid technique

Current Harumanismango farming technique in Malaysia still mostlydepends on the farmers' own expertise to monitor the crops from the attack ofpests and insects. This approach is susceptible to human errors, and thosewho do not possess this skill may not be able to detect the disease at the righttime. As leaf diseases seriously affect the crop's growth and the quality of theyield, this study aims to develop a recognition system that detects thepresence of disease in the mango leaf using image processing technique.First, the image is acquired through a smartphone camera; once it has beenpre-processed, it is then segmented in which the RGB image is converted toan HSI image, then the features are extracted. Lastly, the classification ofdisease is done to determine thetype of leaf disease. The proposed systemeffectively detects and classify the disease with an accuracy of 68.89%. Thefindings of this project will contribute to farmers and society's benefit, andresearchers can use the approach to address similar issues in future works.

Section: Related Workmentioning

confidence: 99%

Harumanis mango leaf disease recognition system using image processing technique

Gining

Fauzi

Yusoff

et al. 2021

“…Image processing techniques can be applied to agricultural products to reduce both machine cost and human error. Previous applications have included plant quality classification [2], [3], plant disease detection [4]- [6], and monitoring of plant growth [7], [8].…”

Section: Introductionmentioning

confidence: 99%

Image-based lime size grading using the comparison ratio of the pixel radius and the actual size of lime fruit

Chimlek

Jitanan²

2021

Lime is a commercially important fruit in Thailand whose sale price depends on the fruit’s size; hence, farmers must grade limes by size before distribution. However, as lime grading machines are very expensive and each province has different size grading limits, grading is often performed manually, which is time-consuming and error-prone. Agricultural production systems for automatic selection and grading use image processing techniques for extracting key features. Therefore, this study proposes techniques to extract features of limes and to develop analytical methods for grading them. This method can reduce time and cost, and increase accuracy and flexibility for selecting different lime sizes according to each province’s size criteria. To verify our method, we classified limes according to criteria from four Thailand provinces as sample data in an experiment. The focal image feature was the radius or diameter of the lime and the grading conditions were defined by the maximum comparison ratio of the fruit’s radius in pixels to the measured radius of the actual lime in centimeters. The average grading accuracy was 99.59%, which outperformed that of mechanical grading. The processing time was 1.70 seconds per individual fruit.

“…The neural network can be trained to identify specific characteristic shades as the proposed system which uses Root Mean Square derivation to detect the rust in the plants. The hybrid techniques execl better in the performance of the system [9]. Most of the machine learning system suffers from multiclass problem.…”

Section: Introductionmentioning

confidence: 99%

Detection and classification of various pest attacks and infection on plants using recursive backpropagation neural network with GA based particle swarm optimization algorithm

Gangadharan

Kumari

Dhanasekaran

et al. 2020

<span>Machine learning methodologies are commonly used in the field of precession farming. It prospects greatly in the plant safety measure like disease detection and classification of pest attacks. It highly influences the crop production and management. The venture of our system is to produce healthy plantation. The proposed system involves Enhanced Fractal Texture Feature Analysis and Machine Learning methodology for classification. Hence more than ever there is a need for such a tool that combines image processing methodologies and the Neural network concepts and that is supported by huge cloud of structured data which makes the diagnosis part much easier and convenient. The proposed system recognizes and classifies the plant taxonomy and the infection also it measures the percentage of infection. The neural network concept followed in our proposed system is focused on Artificial Neural Network which uses Recursive Back Propagation Neural network to speed up the training process and the weights on ANN is optimized using Genetic Algorithm based Particle Swarm Optimization technique. We have used MATLAB to implement the concept and obtained better accuracy in disease detection and proved to be an efficient method.</span>