Detection and Classification of Watermelon Seeds Exterior Quality Based on LS-SVM Using Machine Vision

Xiai Chen; Shuang Ke; Ling Wang

doi:10.4028/www.scientific.net/AMM.278-280.727

Paper Titles

Analog Circuits Test by Using Principal Component Analysis
p.709

Applications of Doppler Radar Sensors on Railroad Crossing Safety Alerting System
p.714

Design of Monitoring and Controlling System for Aquaculture Based on Wireless-Embedded Technology
p.719

Design of Sensor Bearing Based on the Hall Elements
p.723

Detection and Classification of Watermelon Seeds Exterior Quality Based on LS-SVM Using Machine Vision
p.727

Dye Concentration Calculations Using Derivative Ratio Method in an Online and In Situ Optical Fibre Dyeing Sensing System
p.731

Dynamic and Static Characteristics Analysis Study of Hot-Wire Probe in Constant Temperature Model
p.735

Effects of Surface Crack on Eddy Current Sensor Signal in Maglev System
p.743

FPGA+USB-Based Real-Time Data Processing System for Defects Inspection by CCD Scanning
p.749

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 278-280Detection and Classification of Watermelon Seeds...

Detection and Classification of Watermelon Seeds Exterior Quality Based on LS-SVM Using Machine Vision

Abstract:

A machine vision system was developed to investigate the detection of watermelon seeds exterior quality. The main characteristics of watermelon seeds appearance including area, perimeter, roughness and minimum enclosing rectangle were calculated by image analysis. Least square support vector machine optimized by genetic algorithm was applied for the classification of watermelon seeds exterior quality, and the broken seeds, normal seeds and high-quality seeds were distinguished finally. The surface irregularities defects of watermelon seeds were detected by machine vision grid laser. The experimental results show that the watermelon seeds exterior quality could be well detected and classified by machine vision based on least squares support vector machine.