Reflection spectral imaging technology and its application in detection of foreign materials

Imaging detection techniques currently used cannot effectively detect similar foreign materials for their same appearance as the background. To resolve the problem of detection of similar foreign materials in the complex background, a reflection spectrum imaging method based on optimal selecting wavelength was proposed in this paper. According to the method, an optimal selecting wavelength function based on synthesis gray discrimination between foreign materials and background was constructed, and the optimal wavelength differed foreign materials from background in region of near ultraviolet-visible-near infrared was selected. Then the reflection spectrum imaging system based on optimal wavelength illumination was constructed. In the actual application of detection of foreign materials in cotton, the foreign material features were acquired using optimal wavelength imaging system and the targets were extracted effectively using binary processing. The experiment result suggested that detection ration was 0.94 under the condition of illumination coefficient 0.74, and it was a novel and feasible method to detect similar foreign materials from background.