Automated visual inspection system for the classification of preserved vegetables

This paper describes an automated visual inspection system (AVIS) for quality control of preserved orange segments, widely applicable to production processes of preserved fruits and vegetables. Main constraints concerning these kinds of inspection applications are addressed: the need of online operation together with a strong requirement of economic profitability. The strong commitment of above circumstances has forced the development of a flexible and low cost AVIS architecture. The data volume to be processed has forced up the development of sophisticated control architecture for high-speed machine vision applications. Special effort has been put in the design of the defect detection algorithms to reach two main objectives: accurate feature extraction and online capabilities, both considering robustness and low processing time. These goals have been achieved combining a local analysis together with data interpretation based on syntactical analysis, which has allowed avoiding morphological analysis. An online implementation to inspect up to ten orange segments by second is reported.