Submitted to: Sensing and Instrumentation for Food Quality and Safety
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 3/11/2012
Publication Date: 3/27/2012
Citation: Yoon, S.C., Lawrence, K.C., Jones, D.R., Heitschmidt, G.W., Park, B. 2012. Motion compensated image processing and optimal parameters for egg crack detection using modified pressure. Sensing and Instrumentation for Food Quality and Safety. 5:172-184.
Interpretive Summary: Detection of cracks in the egg shell is important to provide safer egg products for the consumers because cracked eggs increase the risk of bacterial contamination. The researchers at the Agricultural Research Service of the USDA previously developed an imaging system using modified pressure in response to need for a more accurate method for USDA human graders to detect hairline cracks (also called microcracks) in the egg shell. USDA human graders have difficulty in detecting hairline cracks by hand candling over a light source which is the standard egg grading method of USDA human graders. The fatigue from extended hours in a dark room with a concentrated light source can reduce the grader’s ability to consistently assess eggs. Although the detection accuracy of the developed USDA imaging system reached over 99%, the system sometimes miss-classified intact eggs as cracked eggs because of displacement (motion) errors between two images at atmospheric pressure and under negative pressure (vacuum) and also suffered from a performance degradation due to the improper selection of parameter values for the detection algorithm. In this study, the motion errors were fixed by motion estimation and compensation. In a test with 3000 eggs, the new image processing algorithm using motion estimation and compensation reduced the false positive readings down to zero. The new image processing algorithm did not affect the crack detection performance. The receiver operating characteristic (ROC) curve was also used to evaluate and compare the performance of the crack-detection algorithm under varying parameters and to find the optimal parameter values. The true positive and false positive rates at the optimal conditions were 98.91% and 0.14%, respectively. Hence, the imaging system showed the potential to increase the grading accuracy of USDA graders.
Technical Abstract: Shell eggs with microcracks are often undetected during egg grading processes. In the past, a modified pressure imaging system was developed to detect eggs with microcracks without adversely affecting the quality of normal intact eggs. The basic idea of the modified pressure imaging system was to apply a short burst of vacuum within a transparent chamber in order to cause a momentary and forced opening in the egg shell with a crack and thus to utilize the changes in image intensities during this process. The intensity changes from dark to bright in the shell surface were recorded by a high-resolution digital camera and processed by an image ratio technique. However, the performance of the imaging system was compromised by both false readings due to motion of intact eggs relative to the camera and an improper selection of parameter values for the detection algorithm. First, a machine vision technique based on motion estimation of individual eggs was developed to compensate any motion errors present on images and thus reduce false crack-detection readings. The simulation results of the developed motion estimation and compensation technique with 3,000 eggs showed no false errors. Second, the receiver operating characteristic (ROC) curve was used to evaluate and compare the performance of the crack-detection algorithm under varying parameters (ratio and detection-tolerance thresholds) and to find the optimal parameter values. The area under the ROC curve (AUC) was used to compare the performance under varying parameter values. The minimum distance and Youden index criteria were used to find the optimal values from the ROC curve. The minimum distance criterion found the optimal parameters at 1.11 and 20 (or 1.1 and 25) for the ratio and detection-tolerance thresholds, respectively. The true positive and false positive rates at the optimal conditions were 98.91% and 0.14%, respectively.