Startseite Naturwissenschaften Identification of Peanut Pods with Three or More Kernels by Machine Vision and Neural Network
Artikel
Lizenziert
Nicht lizenziert Erfordert eine Authentifizierung

Identification of Peanut Pods with Three or More Kernels by Machine Vision and Neural Network

  • Jason Wang , Wade W. Yang EMAIL logo , Lloyd T. Walker und Taha Rababah
Veröffentlicht/Copyright: 23. Januar 2014
Veröffentlichen auch Sie bei De Gruyter Brill

Abstract

Separation of unshelled peanuts containing three or more kernels and then niche marketing them can potentially increase the value of unshelled peanuts and thus the profit of peanut producers or processors. Effective identification of peanut pods with three or more kernels is a critical step prior to separation. In this study, a machine vision system was teamed up with neural network technique to discriminate unshelled peanuts into two groups: one with three or more kernels and the other with two or less kernels. A set of physical features including the number of bumps, projected area, length and perimeter, etc., were extracted from the images taken and used to train an artificial neural network for discriminating the peanuts. It was found that among all the selected features, the length, the major axis length and perimeter have the best correlation with the number of kernels (correlation coefficient r = 0.87–0.88); the area and convex area have good correlation (r = 0.85); the eccentricity, number of bumps, and the compactness have relatively lower correction (r = 0.77–0.80); the solidity and the minor axis length have the least correlation to the number of kernels (r = −0.415–0.26). The best discrimination accuracy obtained for peanut pods with three or more kernels was 92.5% for the conditions used in this study.

References

PoxtonMG, GoldsworthyGT. The remote estimation of weight and growth in turbot using image analysis. In: Proceedings of Conference: Aquaculture ’86, Automation and Data Processing in Aquaculture, 1986:T12.112.8.Suche in Google Scholar

SchofieldCP, MarchantJA. Measuring the size and shape of pigs using image analysis. Paper No. 96G-035, AgEng 96 Conference, Madrid, 1996.Suche in Google Scholar

PearsonT. Machine vision system for automated detection of stained pistachio nuts. Lebensm Wiss Technol1996;29:2039.10.1006/fstl.1996.0030Suche in Google Scholar

RidgwayC, DaviesER, ChambersJ, MasonDR, BatemanM. Rapid machine vision method for the detection of insects and other particulate biocontaminants of bulk grain in transit. Biosyst Eng2002;83:2130.Suche in Google Scholar

PanditRB, TangJ, LiuF, PittsM. Development of a novel approach to determine heating pattern using computer vision and chemical marker (M-2) yield. J Food Eng2007;78:5228.10.1016/j.jfoodeng.2005.10.039Suche in Google Scholar

YangW, WinterP, SokhansanjS, WoodH, CrererB. Discrimination of hard-to-pop popcorn kernels by machine vision and neural networks. Biosyst Eng2005;91:18.10.1016/j.biosystemseng.2005.02.002Suche in Google Scholar

QiaoJ, WangN, NgadiMO, KazemiS. Predicting mechanical properties of fried chicken nuggets using image processing and neural network techniques. J Food Eng2007;79:106570.10.1016/j.jfoodeng.2006.03.026Suche in Google Scholar

BrosnanT, SunD-W. Improving quality inspection of food products by computer vision – a review. J Food Eng2004;61:316.10.1016/S0260-8774(03)00183-3Suche in Google Scholar

DowellFE. Automatic control of a peanut grade sample inspection system. Food Control1992;3:1058.10.1016/0956-7135(92)90041-8Suche in Google Scholar

WangY, YangW, WinterP, WalkerLT. Non-contact sensing of hog weights by machine vision. Appl Eng Agric2005;22:57782.10.13031/2013.21225Suche in Google Scholar

Published Online: 2014-1-23

©2014 by Walter de Gruyter Berlin / Boston

Artikel in diesem Heft

  1. Frontmatter
  2. Mass Transfer Coefficients and Correlation of Supercritical Carbon Dioxide Extraction of Sarawak Black Pepper
  3. Higher Order Predictive Functional Control Versus Dynamical Matrix Control for a Milk Pasteurisation Process: Transfer Function Versus Finite Step Response Internal Models
  4. Fluidized Bed Drying of Sprouted Wheat(Triticum aestivum)
  5. Investigation of Hydrodynamics, Kinetics, Energetic and Exergetic Aspects of Fluidized Bed Drying of Rough Rice
  6. Flux Behavior and Quality of Effluent from a Poultry Processing Plant Treated by Membrane Bioreactor
  7. Experimental Analysis and Numerical Modeling of Microwave Reheating of Cylindrically Shaped Instant Rice
  8. Microwave, Air and Combined Microwave-Air Drying of Grape Leaves (Vitis vinifera L.) and the Determination of Some Quality Parameters
  9. Modelling the Influence of Time and Temperature on Respiration Rate of Fresh Fig and Diced Papaya
  10. Identification of Peanut Pods with Three or More Kernels by Machine Vision and Neural Network
  11. Effect of Drying Pre-treatments on the Yield and Bioactive Content of Oil Extracted from Gac Aril
  12. Effect of Pulsed Electric Field on Microstructure of Some Amino Acid Group of Soy Protein Isolates
  13. A Novel Modified Starch/Carboxymethyl Cellulose/Montmorillonite Bionanocomposite Film: Structural and Physical Properties
  14. Effects of Spray Drying Conditions on the Stability and Antioxidant Properties of Spray-Dried Soluble Maté
  15. Effect of Frying Time and Temperature on the Functional Properties of Carrot Pomace, Pulse Powder and Rice Flour–Based Extrudates
  16. Effects of Moisture Content and Impact Energy on the Cracking Characteristics of Walnuts
  17. Spray Drying of Karkade (Hibiscus sabdariffa L.) Calyces and Evaluation of the Product
  18. Optimization of Closed-Cycle Fluidized Bed Drying of Sesame Seeds Using Response Surface Methodology and Genetic Algorithms
  19. Assessment of Heat Transfer and Mass Change During Fruits and Vegetables Impingement Pre-Cooling
  20. High Temperature Short Time Air Puffed Ready-To-Eat (RTE) Tapioca–Peanut Snack: Process Parameters Optimization
Heruntergeladen am 30.12.2025 von https://www.degruyterbrill.com/document/doi/10.1515/ijfe-2012-0009/pdf
Button zum nach oben scrollen