Fruit Recognition Using Color and Morphological Features Fusion

Abstract

It is still difficult to recognize the kind of fruit which are of different colors, shapes, and textures. This paper proposes a features fusion method to recognize five different classes of fruits that are the images from the fruit360 dataset. We are processed with four stages: preprocessing, boundary extraction, feature extractions, and classification. Pre-processing is performed to remove the noise by using the median filter, and boundary extraction are operated with the morphological operation. In feature extraction, we have extracted two types of features: color, and morphological features of the image. Color features are extracted from the RGB color channel, and morphological features are extracted from the image that detected the boundary of fruit by using morphological operations. These two types of features are combined in a single feature descriptor.

Estimating and evaluating the rice cluster distribution uniformity with UAV-based images

“…According to the feature classification algorithm, classification methods are divided into two categories: probability density-based methods 14 and discriminant function-based methods 15 . A large number of studies has been carried out on the recognition of plants or organs by predecessors, which have been widely applied to agricultural intelligence, such as the classification, recognition and positioning of fruits such as apples and strawberries 16 – 19 .and determination of the tiller and panicle numbers of rice, wheat, maize and other crops 20 – 24 . Therefore, aerial images and target recognition are feasible techniques to accurately identify and locate rice clumps.…”