No description available.

Real-time inspection based on machine vision technologies is being widely used in quality control and cost reduction in a variety of application domains. The high demands on the inspection performance and low cost requirements make the algorithm design a challenging task that requires new and innovative methodologies in image processing and fusion. In this research, an integrated approach that combines novel image processing and fusion techniques is proposed for the efficient design of accurate and real-time machine vision-based inspection algorithms with an application to the food processing problem. Firstly, a general methodology is introduced for effective detection of defects and foreign objects that possess certain spectral and shape features. The factors that affect performance metrics are analyzed, and a recursive segmentation and classification scheme is proposed in order to improve the segmentation accuracy. The developed methodology is applied to real-time fan bone detection in deboned poultry meat with a detection rate of 93% and a false alarm rate of 7% from a lab-scale testing on 280 samples. Secondly, a novel snake-based algorithm is developed for the segmentation of vector-valued images. The snakes are driven by the weighted sum of the optimal forces derived from corresponding energy functionals in each image, where the weights are determined based on a novel metric that measures both local contrasts and noise powers in individual sensor images. This algorithm is effective in improving the segmentation accuracy when imagery from multiple sensors is available to the inspection system. The effectiveness of the developed algorithm is verified using (i) synthesized images (ii) real medical and aerial images and (iii) color and x-ray chicken breast images. The results further confirmed that the algorithm yields higher segmentation accuracy than monosensory methods and is able to accommodate a certain amount of registration error. This feature-level image fusion technique can be combined with pixel- and decision- level techniques to improve the overall inspection system performance.

Manufacturing industries are facing major challenges in terms of improving product quality and increasing throughput while sustaining production costs to acceptable levels. Product-oriented processes, both legacy and new, are poorly monitored and controlled on the basis of distributed loop controllers that are aiming to maintain critical process variables within acceptable bounds. Thus, poor quality product results when such processes are subjected to large disturbances - operational failures, environmental changes, and changes in loading conditions. In this research, product quality modeling and control based on a vision inspection methodology is proposed to improve product quality and increase productivity. The main contributions of this research are twofold. First, this research introduces a product quality modeling methodology that combines both physical-based modeling and data-driven modeling. The quality model is the link between information coming from the inspection of product features and the specification of process control strategies. It is essential to control and optimize the process. Physical-based modeling is used to model the product temperature profile, and data-driven modeling is used to train the mapping from the product temperature profile to each quality metric. The break down of the sub models increase the flexibility of model development and reduce the effort to change the model when the quality metrics change. The second contribution is the development of a novel approach to control product quality based on vision inspection, which is developed as part of a hybrid, hierarchical architecture. The high-level control module involves scheduling of multiple plant processes, diagnostics of the failure condition in the process, and the supervision of the whole process. The mid-level control module, which is the focus of the work presented here, takes advantage of baking product quality indicators and oven parameter measurements to optimize zone temperature and conveyor speed set points so that the best product quality is achieved even in the presence of disturbances. The low-level control module consists of basic control loops. Each of them controls parameters of each operation in the process separately. They are generally simple and easy to implement.