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.

Abstract. Tree seedling adulteration is a serious problem in the forest management. Cinnamomum osmophloeum (Lauraceae) has high economic value due to its cinnamaldehyde compound. However, two other species, C. burmannii and C. insularimontanum, having similar leaf morphologies do not produce cinnamaldehyde. Adulteration of C. burmannii with C. osmophloeum has been reported in Taiwan. Yet, it is challenging to discriminate the three species by experts due to their high degree of similarity. This brings economic loss to forest farmers owing to value discrepancy between the species. This study proposed to identify the three Cinnamomum species using leaf images and machine learning. Leaf images of the species were acquired using flat-bed scanners. Venation features of the leaves were quantified using Gabor filters. The features were then used to classify the species as the inputs to support vector machine (SVM) classifiers. Experimental results showed that the SVM classifiers achieved an accuracy of 92.1%.