Mature blueberry fruit identification method based on deep learning neural network

Abstract

The invention discloses a mature blueberry fruit identification method based on a deep learning neural network, which adopts a method of combining a ResNet50 residual neural network and a YOLOv2 detection network for training, and specifically comprises the following steps: preprocessing a collected blueberry fruit picture set, and expanding a data set by using data augmentation; dividing the augmented data set into a training set, a test set and a verification set in proportion; marking image features; carrying out image feature extraction by adopting a ResNet50 residual network; taking the extracted features as an entry function, and inputting the entry function into a YOLOv2 detection network for target detection; the identification accuracy of the mature blueberry fruits in the test set is 95%, and the mature blueberry fruits in the test set are correctly identified. According to the method, the advantages of the ResNet50 residual neural network and the YOlOv2 detection network are ingeniously combined, the ResNet50 residual neural network effectively solves the problems of gradient explosion and gradient disappearance caused by layer number deepening, the YOLOv2 detection network is accurate in prediction and high in speed, and the training precision and the recognition reaction speed of the neural network are enhanced through combination of the ResNet50 residual neural network and the YOLOv2 detection network.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a method for identifying ripe blueberry fruits based on a deep learning neural network. Background technique [0002] At this stage, the acquisition of blueberry ripening information mainly relies on manual observation. Observers conduct field measurements on blueberries according to the definitions and descriptions in the Agricultural Meteorological Observation Specification, which is not only inefficient, but also requires a lot of manpower and material resources, which cannot meet real-time and rapid monitoring. need. Nowadays, intelligent recognition technology is more and more used in the field of agriculture. Contemporary computers have super computing power. They input image data into neural networks and learn through abstract data to train neural networks that can recognize and classify specific crops to improve production. efficiency. SUMMARY OF THE INVENTION ...

AI Technical Summary

Problems solved by technology

[0002] At this stage, the acquisition of blueberry ripening information mainly relies on manual observation. The observers conduct field measurements on blueberries according to the definition and description in the agricultural meteorological observation norms. need

Images