Fruit Fly Classification via Convolutional Neural Network

摘要

The recognition of fruit fly is an important part of the quarantine work, for which it is of great significance to establish the fruit fly feature automatic extraction classification system. Depending on the manual design of machine learning algorithm and the feature of the model classification, the existing fruit flies classification system needs to be improved in many ways, such as its complicated process, the excessive requirement for specialty, incapability of automatic feature extraction. Given these problems, the research on automatic feature extraction of classification model has been conducted, the convolutional neural network algorithm has been come up with. This algorithm can automatically extract feature classification training, try to find the solution to the problems of beforehand artificial designing and extracting in the existing fruit fly classification system, is helping to greatly improve the staff's efficiency. Experimental results show that the method can identify the Bactrocera dorsalis, Bactrocera cucurbitae, Bactrocera tau, Bactrocera scutellata, with the overall accuracy of 97.19^{%, and have a good application prospect.}