Printer Friendly

Determine product quality reliably.

Research underway in Europe aims to improve and advance artificial vision technology to solve two problems: classifying fresh products and determining quality in a rapid and reliable way. Current conventional quality-determining methods on the market, either manual or partially automated, are slow and expensive. In addition, their reliability is incompatible with the speed of changing consumer demands for freshness and high quality.

When the ISO 9002 standards are extensively applied, the present quality classifying systems will have to be substituted by others that are faster, more efficient and economical. Although the research undertaken in this project will focus on developing a quality-determining tool that can be used on many foods, this study specifically will focus on two products: olives destined for table consumption and potatoes.

Olives have to be sorted based on their size and external defects, and on an homogeneous color. At present, olives are classified after harvesting, after fermentation and prior to filling and packing. However, this classification must be done manually, which is extremely expensive, and the technique only allows the characterization of a small, not representative, part of the production.

In addition, the sorting and manual selection is based on the subjectivity of the worker, whose criteria do not remain invariable after long hours of work in a monotonous task, under stressful working conditions.

The main objective of scientists is to build a system that can automatically classify a product and which is capable of analyzing 2500 kg of olives per hour and 10,000 kg of potatoes per hour. The researchers plan to develop an artificial vision system for quality inspection of olives and potatoes. The work includes the illumination design and configuration of the cameras, the development of the software to obtain information from the images and the development of software for product selection.

Scientists intend to implement algorithms over a specific platform so that the images can be processed in real time. There will also be a user's graphic interface. Development of a process line that can handle the products at high speed also is planned. Researchers will have to develop techniques for separating the product at high speed, and for synchronizing the produce rejection mechanism, camera, computer and belt conveyor.

Further information. Ricardo Diaz Pujol, Department of Instrumentation and Automation, Instituto Tecnologico Agroalimentario (AINIA), Parque Tecnologico de Valencia, Benjamin Franklin, 5-11 46980-Paterna, Valencia, Spain; phone: +34 961 366 090; fax: +34 961 318 008; URL:
COPYRIGHT 2001 Food Technology Intelligence, Inc.
No portion of this article can be reproduced without the express written permission from the copyright holder.
Copyright 2001, Gale Group. All rights reserved. Gale Group is a Thomson Corporation Company.

Article Details
Printer friendly Cite/link Email Feedback
Publication:Emerging Food R&D Report
Date:Aug 1, 2001
Previous Article:Neural network optimizes fermentations.
Next Article:Plan to evaluate healthful soybean oil.

Related Articles
SEC commissioner proposes new multilayer reporting model.
A new database helps identify and characterize.
Apply DNA fingerprinting to food products.
Depaneling requires a closer look: press-type depaneling can be an accurate and gentle singulation method.
Estimating and Bidding for Builders and Remodelers.
Middle ear prosthesis.
Middle ear prosthesis.
Overcoming the hurdles of VoIP call recording.

Terms of use | Privacy policy | Copyright © 2019 Farlex, Inc. | Feedback | For webmasters