Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Machine vision and near infrared spectroscopy technology were employed to detect the external and internal quality of dried apricots nondestructively. Weight and defect were detected as two indexes for external quality of dried apricots based on machine vision. A new filling algorithm was developed for segmentation of dried apricots in four images captured for each dried apricot at four different angles. Areas of each dried apricots in four images were calculated respectively. Evaluation model based on co-relationship between dried apricots actual weight and area in images was developed via multiple linear regressions. The correlation coefficient was 0.9283 for calibration set and 0.9191 for predication set. For total 160 samples, detection accuracy of weight of dried apricots was 89.8%. A regional growth algorithm was developed to extract surface defects of dried apricots. The detection accuracy reached 85%. With respect to detection of sugar content of dried apricots using near infrared spectroscopy, the back interval partial least squares (biPLS) model got the best prediction result. The optimal biPLS model was obtained with 22 divided intervals and the optimal combinations of intervals [17 2 3 9 20 13 7 18 15 11 6] with its principal factor number being 10. The correlation coefficient was 0.8983 for calibration set and 0.8814 for prediction set. Dried apricots were graded using the fusion information obtained from machine vision and near infrared technology. It maybe a useful method to detect the internal and external quality of dried apricots and other similar dried fruits based on fusion information.