Submitted to: Applied Optics
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: October 31, 2005
Publication Date: May 20, 2006
Citation: Ding, F., Chen, Y.R., Chao, K., Kim, M.S. 2006. Three-color mixing for classifying agricultural products for safety and quality. Applied Optics. 45(15):3516-3526. Interpretive Summary: Presently, the Instrumentation and Sensing Laboratory (ISL), USDA, is developing a low-cost color-based, optically enhanced device that can assist inspectors or plant processors in small meat and poultry plants to conduct inspection in situ. In a previous paper, we showed two-band color mixing to be directly related to the two-color band ratio criterion. It can be useful for separation of wholesome and unwholesome poultry carcasses. In this paper, we further show that three-color mixing is related to three-color band ratios, which is often used for class discrimination and target detections. We show that the three-color mixing technique provides better discrimination power than the previously presented two-color mixing technique for identification of chicken carcasses conditions and fecal contamination on apples. The novel three-color mixing technique for visual inspection can be implemented on visual devices for a variety of applications, ranging from target detection to food safety inspection. This paper also reports the results of research to select optimal waveband pairs from color difference and chromaticness difference indices, and to design optically enhanced binoculars for chicken inspection based on a three-color mixing technique. The simulation of color appearance is also presented. We showed that three color-mixing binoculars have potential for practical use in a processing plant environment. This will directly impact small-scale poultry processors in terms of improved efficacy of the HACCP program. This information would be useful to FSIS and researchers who are interested in developing low cost vision-based systems for inspecting agricultural products.
Technical Abstract: In this paper, the three-color mixing application for food safety inspection is presented. It was shown that the chromaticness of the visual signal resulting from the three-color mixing achieved through our device is directly related to the three-band ratio of light intensity at three selected wavebands. An optical visual device using three-color mixing to implement the three-band ratio criterion is presented. Inspection through human vision assisted by an optical device that implements the three-band ratio criterion would offer flexibility and significant cost savings as compared to inspection with a multispectral machine vision system that implements the same criterion. Example applications of this optical three-color mixing technique are given for the inspection of chicken carcasses with various diseases and for apples with fecal contamination. With proper selection of the three narrow wavebands, discrimination by chromaticness that has a direct relation with the three-band ratio can work very well. In particular, compared with the previously presented two-color mixing application, the conditions of chicken carcasses were more easily identified using the three-color mixing application. The novel three-color mixing technique for visual inspection can be implemented on visual devices for a variety of applications, ranging from target detection to food safety inspection.