| A set of X-ray inspection system consisting of X-ray tube, linear diode array, conveyor, and computer for food safety insurance was constructed. Also, software for X-ray inspection system was developed. Function of software system included basic image processing tool and automatic recognition for foreign bodies in x-ray image for food.This research was mainly composed of the following section:1. The radiography course of line-scan detector was analyzed. Then factor of imaging such as reducing noise, choosing suitable voltage and current for imaging was studied to improve image quality.2. A regression model was developed to estimate blank image intensity at higher voltages and currents. Adjusted R2 value was higher than 0.99 for nonlinear fit regression.3. Mathematic morphology was applied to analyze and process image pixels of food with foreign bodies. A method of adaptive grayscale morphology filtering was studied to apply to on-line foreign bodies inspection. The method of adaptive morphology filtering was tried applying to food x-ray images. Several foreign bodies, including metal, bone, wood, and glass, were used as inclusions in on-line sausage inspection. The automatic recognition of foreign bodies methodology was developed by image segmentation and target object extraction. The result of the method was satisfactory for on-line inspection, and on-line inspection speed will be improved significantly by the methodology. The methodology can also be applied to foreign bodies detection for other foods. The X-ray foreign bodies system for food can detect foreign bodies with high density such as metal, glass in even food.4. The X-ray foreign bodies detection system for food can automatically identified foreign bodies using adaptive filtering methods. |