%0 Journal Article
%T WraNet：一种基于二维离散小波变换的轻量害虫识别网络<br>WraNet: An Efficient Pest Recognition Network Based on 2D Discrete Wavelet Transform
%A 李晖
%A 吴茜茵
%A 胡欣仪
%A 唐栩燃
%A 罗伟
%A 赵雪如
%A 谭廷俊
%A 赵泽华
%A 李超然
%J Journal of Image and Signal Processing
%P 33-46
%@ 2325-6745
%D 2024
%I Hans Publishing
%R 10.12677/JISP.2024.131004
%X 近年来，人工智能技术在害虫识别领域得到广泛应用。目前深度网络害虫识别方法仍存在计算量大、对复杂背景下的害虫识别效果差等问题。为了解决计算量大的问题，本文提出了一种新型轻量网络——WraNet。该网络利用二维离散变换模块对图像进行特征混合，并学习图像的强先验知识，例如尺度不变性、平移不变性和边缘稀疏性。这使得单层二维离散小波变换层达到多层深度神经网络的效果，从而减少了计算量和模型参数的大小。本文还提出了一种新的算法——WraNet-m，该算法通过软投票集成了WraNet、ResNet50和FPN网络模型，以进一步提升识别效果。WraNet-m算法在IP102和D0害虫数据集上的准确率分别达到了72.44%和99.52%，证明了集成方法的有效性和鲁棒性。<br />
In recent years, with the promotion of agricultural informatization, artificial intelligence techniques have been widely applied in the field of pest recognition. However, current deep neural net-work-based pest recognition methods still face challenges such as high computational complexity and poor performance in complex background scenarios. To address the issue of high computation-al complexity, we propose a novel network called WraNet. This network employs a two-dimensional discrete transform module for token mixing and learns strong prior knowledge of the image, such as scale-invariance, shift-invariance, and sparseness of edges. It is worth noting that we also propose a new algorithm, WraNet-m, which combines WraNet, ResNet50, and FPN models through soft voting for further performance improvement. The WraNet-m algorithm achieves accuracies of 72.44% on the IP102 pest dataset and 99.52% on the D0 pest dataset, approaching state-of-the-art results on both datasets, thus demonstrating the effectiveness and robustness of the ensemble method.
%K 害虫识别，二维离散小波变换，计算机视觉，深度学习<br>Pest Recognition
%K 2D Discrete Wavelet Transform
%K Computer Vision
%K Deep Learning
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=79516