CNN–SVM: a classification method for fruit fly image with the complex background

Abstract

On the basis of the problem that the image background is simple and the traditional shooting equipment of fruit flies is too high, this study improved the convolutional neural network model. First, the authors changed Softmax classifier to support vector machine (SVM). Moreover, then used convolution layers for extracting features of fruit fly images. Finally, they fed features into SVM for training. Experiments show that the model has been classifying the Bactrocera dorsalis Hendel, Bactrocera cucurbitae, Bactrocera tau and Bactrocera scutellata with accuracy over 92.04%, accordingly making the effective classification of the complex background fruit fly images possible. Moreover, it also provides a good practical application prospect.

Keywords

• feature extraction
• pest control
• learning (artificial intelligence)
• agricultural products
• support vector machines
• image classification
• convolutional neural nets
• bactrocera tau
• bactrocera scutellata
• complex background fruit
• cnn–svm
• classification method
• fruit fly image
• image background
• traditional shooting equipment
• fruit flies
• convolutional neural network model
• softmax classifier
• convolution layers
• bactrocera dorsalis hendel
• bactrocera cucurbitae