Forests are the lungs of our planet. Conserving the plants may require the development of an automated system that will identify plants using leaf features such as shape, color, and texture. In this paper, a leaf shape descriptor based on sinuosity coefficients is proposed. The sinuosity coefficients are defined using the sinuosity measure, which is a measure expressing the degree of meandering of a curve. The initial empirical experiments performed on the LeafSnap dataset on the usage of four sinuosity coefficients to characterize the leaf images using the Radial Basis Function Neural Network (RBF) and Multilayer Perceptron (MLP) classifiers achieved accurate classification rates of 88% and 65%, respectively. The proposed feature extraction technique is further enhanced through the addition of leaf geometrical features, and the accurate classification rates of 93% and 82% were achieved using RBF and MLP, respectively. The overall results achieved showed that the proposed feature extraction technique based on the sinuosity coefficients of leaves, complemented with geometrical features improve the accuracy rate of plant classification using leaf recognition.

No abstract

No abstract

No abstract

Shape extraction and analysis is one of the most important task in image processing. The accuracy of the shape features extraction process increases the object recognition rate. Minimum Bounding Rectangle (MBR) is a tool that contributes to the increase of the accuracy of the shape features extraction, particularly it can be used to determine the real aspect ratio. This paper focuses on the improvement of the existing method. This is focused around the determination of the MBR's edges points, using a series of approximations. The proposed method gives more accurate MBR in all the tested situations. In order to demonstrate the accuracy of the proposed method, an experiment is setup based on the comparison of the manually drawn MBR and the ones generated by each of the methods. Results achieved showed that the proposed method outperforms existing method as it consistently produced results closest to the manually drawn MBR.