Fruit recognition method and device based on deep learning

Abstract

The invention provides a fruit recognition method and device based on deep learning. The method comprises the steps of selecting a target fruit image library, extracting the features of all training images in the image library, inputting obtained feature vectors of all training images into a deep learning model and training the deep learning model, and identifying images inputted by a user by using the trained deep learning model, judging whether target fruits are included and identifying the specific locations of all the target fruits in the images. Compared with the prior art, the modification and training are carried out based on a traditional deep learning model and fruit images are identified, the recognition of obtained fruit image data has higher accuracy, information such as position information is included, and thus a better recognition effect is obtained.

Description

technical field [0001] The invention relates to the field of image recognition, in particular to a method and device for fruit recognition based on deep learning. Background technique [0002] The concept of deep learning originates from the research of artificial neural networks. Deep learning is a method based on representational learning of data in machine learning. Its observations (such as a certain image) can be represented in various ways, such as each pixel A vector of intensity values, or more abstractly represented as a series of regions of a particular shape, etc. The advantage of deep learning is to use unsupervised or semi-supervised feature learning and hierarchical feature extraction efficient algorithms to replace manual feature acquisition. [0003] Picking fruit in traditional agriculture requires a lot of manpower and material resources, and the use of machine automation picking technology will first face how to identify the precise location of the fruit ...

AI Technical Summary

Problems solved by technology

[0003] Picking fruit in traditional agriculture requires a lot of manpower and material resources, but the use of machine automation picking technology will first face the problem of how to identify the precise location of the fruit in the natural environment

Images