Recognition Insect Images at the Order Level Based on Elliptic Metric Learning

Abstract

HighlightsInsect order recognition.Space transformation combined with elliptic metric.Feature fusion with the Relief-F for the sliding window feature and HOG feature.The recognition accuracy of insect images at the order level is 95.8%.Abstract. The accurate recognition of insects is crucial for the protection and management of crops, vegetables, and fruit trees. This study proposes a recognition algorithm for insect images at the order level based on elliptic metric learning to improve the accuracy of the recognition. The nonlinear transformation that reflects the space structure or semantic information of insect image features is determined via elliptic metric learning. Then, the model for the potential relationship among insect image features is built. This model reduces the distance between same-order features but increases the distance between different-order features, improving the discriminative performance of classifiers. In elliptic metric learning, the regular term of the Frobenius norm is added to the triple constraint function to avoid overfitting and improve generalization ability. Moreover, to weaken the effects of image scale, rotation, and other changes on the recognition result, the sliding window method is used to extract the HSV color feature and the scale-invariant local ternary pattern texture feature of insect images. The feature vector is formed by gathering the maximum value of the features in the same horizontal sliding window. The features of the histogram of oriented gradients are also extracted from the images. Then, the optimized features are gained using the Relief-F algorithm. The results of the experiment on insect images at nine order levels show that the proposed method can significantly improve the recognition accuracy of insect images at the order level. Keywords: Elliptic metric, Insect images at the order level, Object recognition, Triple constraint, Regular term.