Classification for Fruit Fly Images Using Convolutional Neural Networks

Abstract

The discriminative information of fruit fly images often exists in a very fine region, resulting in hard extracting the desired features from the entire image level. Hence, it is a tough task to obtain the discriminative features in the fine-grained image for the classification of fruit fly images. To address this, here proposed a convolutional neural network of bilinear pooling based on feature fusion for the classification of fruit fly images. Firstly, Gaussian blur is performed on fruit fly images to reduce the detailed level of fruit fly images, which conveniently extracts high-level features. In the fruit fly images processed by Gaussian blur, the convolutional layers in the proposed model (i.e., consisting of CNN A and CNN B) are used for the features extraction from the processed images. Then, these extracted features are fused by using the matrix dot multiplication in the Bilinear layers. According to these fused features, the softmax layer performs the classification of fruit fly images. Experimental results on the 4000 image set containing different fruit fly morphology show that the propose method not only outperforms the state-of-the-art methods in the classification accuracy of fruit fly images, but also the precision, recall and score are above 94.87% on testing set and validation set. We find that image feature fusion has positive effects on promoting the accuracy of image classification. We also demonstrate that using feature connection operation after performing the matrix point multiplication operation is beneficial to feature fusion, instead of using feature connection operation directly. In addition, our findings indicates that convolutional neural networks easily obtain the desired features from the images performed by Gaussian blur.