Automation of the brazil-nuts classification process using dynamic level set

The usual method for classification processes of brazil-nut is manual and present some drawbacks like slowness, subjectivity, and inconsistency. In this paper, the main objective is to automate the classification process by analysing digital images with multiple brazil-nuts. These images have been segmented using the Level Set method without reinitialization with a new stopping criteria based on the area of objects, which have been proposed in order to reach better results. The goal is to optimize the manual classification process that has been done until now by generating higher productivity. The efficiency achieved by the proposal is 97.63% for whole brazil-nuts and 84.09% for broken brazil-nuts for image taken at a distance of 40 cm and 99.55% and 98.44% for whole and broken brazil-nuts respectively for image taken at a distance of 30 cm, properly classified.