An image acquisition and processing algorithm for inspection of tire treads has been developed. The tire treads are flat strips of black rubber material used as the main component in retreading automobile tires. These treads have a complex molded design on one side (DESIGN SIDE) and a fiat surface on the other side (see Figure 1). The inspection of the Design Side of the tread is one of the key operations in the tread fabrication process impacting quality and consistency of the final product. Increasing production rates and rigorous quality control demands put forth a requirement for the automation of the inspection operation. The main objective of the automated inspection system is to provide on-line, 100% inspection of the product for specified types of potential defects. Additional system benefit will include full access to the real-time process-control data, which can be used as process feedback parameters and allow implementation of advanced process-control techniques. This paper will discuss development of the main optical inspection algorithms utilized in the system design. The algorithms described in this paper were tested in the laboratory prototype of the inspection system and will be implemented in the final production system.

A machine vision system was developed by BIRL, Northwestern University's industrial research laboratory, in response to the need for continuous on-line monitoring of tire tread fabrication line. A versatile design philosophy was used to provide verification and identification functions for a wide variety of treads and to utilize essentially "off-the-shelf' hardware components. This paper discusses technical aspects of this successful application, from the original design to the final implementation. Specific emphases are given to the hardware and software implementation of the system's image acquisition and processing. Aspects regarding the imaging of highly absorptive material (black rubber) and rapidly moving targets are also discussed. Problems encountered during the development and integration of the system are described, and solutions are presented.