Bayesian classification of ripening stages of tomato fruit using acoustic impact and colorimeter sensor data

Authors:
Arturo Baltazar;Jorge Isidro Aranda;Gustavo González-Aguilar
Affiliations:
Centro de Investigación y Estudios Avanzados, CINVESTAV-Saltillo, Robotics and Advanced Manufacturing Program, Ramos Arizpe, Coahuila, Mexico;Universidad Michoacana de San Nicolás de Hidalgo, Facultad de Ciencias Físico-Matemáticas, Morelia, Michoacán, Mexico;Centro de Investigación de Alimentos y Desarrollo, A.C. (CIAD), Tecnología en Alimentos de Origen Vegetal, Hermosillo, Sonora, Mexico
Venue:
Computers and Electronics in Agriculture
Year:
2008

Citing 7
Cited 3

Application of a general learning algorithm to the control of robotic manipulators

International Journal of Robotics Research
Bounds on the Bayes Classification Error Based on Pairwise Risk Functions

IEEE Transactions on Pattern Analysis and Machine Intelligence
Using boundary methods for estimating class separability

Using boundary methods for estimating class separability
Sensor and Data Fusion: A Tool for Information Assessment and Decision Making (SPIE Press Monograph Vol. PM138)

Sensor and Data Fusion: A Tool for Information Assessment and Decision Making (SPIE Press Monograph Vol. PM138)
Estimation of Classification Error

IEEE Transactions on Computers
A Class of Algorithms for Fast Digital Image Registration

IEEE Transactions on Computers
On optimum recognition error and reject tradeoff

IEEE Transactions on Information Theory

The Effect of Repeated Measurements on Bayesian Decision Regions for Class Discrimination of Time-Dependent Biological Systems

MICAI '08 Proceedings of the 7th Mexican International Conference on Artificial Intelligence: Advances in Artificial Intelligence
Spots and color based ripeness evaluation of tobacco leaves for automatic harvesting

Proceedings of the First International Conference on Intelligent Interactive Technologies and Multimedia
Comparison of acoustic sensor systems for quality analysis of asparagus using scanning laser vibrometry for visualization

Computers and Electronics in Agriculture

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this work, the concept of data fusion is applied to nondestructive testing data for classification of fresh intact tomatoes based on their ripening stages. A Bayesian classifier considering a multivariate, three-class problem was incorporated for data fusion. Probability of error was estimated numerically for univariate and multivariate cases based on Bhattacharyya distance. Numerical results showed that multi-sensorial data fusion reduces the classification error considerably. The Bayesian classifier was tested on data of tomato fruits taken by the following nondestructive tests: colorimeter and acoustic impact. Results of Bayesian classifier agree with numerical estimations showing an 11% classification error in the multivariate (multi-sensor) case compared with a 48% obtained by the univariate case (single sensor).