Target Recognition Algorithm Based on Hybrid Convolutional Neural Network Feature Enhancement
ZHAO Wenyan1, ZHONG Cheng1, TIAN Dianxiong1, LU Zeyu1, LI Yong2
1. Tangshan Power Supply Company of State Grid Jibei Electric Power Co, Tangshan 263000, China; 2. Shanghai Zhougu Power Technology Co, Ltd, Shanghai 200000, China
Abstract：To overcome the problem of insufficient feature extraction capabilities of traditional target recognition algorithms in complex scenarios, a new target recognition algorithm based on a hybrid convolutional neural network is proposed. The core of the algorithm lies in combining the learning capability of non-Euclidean domains with traditional convolutional neural networks to enhance the depth and breadth of feature representation. The algorithm in this paper can extract and strengthen the key feature information in target recognition, and significantly improve the accuracy and robustness of recognition.
[1] 沈学利, 关刘美, 翟宇琦. 基于卷积神经网络的颜色修正水下图像增强方法[J]. 计算机技术与发展, 2024, 34(8): 42-48. SHEN X L, GUAN L M, ZHAI Y Q. Color correction underwater image enhancement method based on convolutional neural network[J]. Computer Technology and Development, 2024, 34(8): 42-48. [2] 李莉, 彭娜, 王巍. 基于轻量级卷积神经网络的遥感图像检测模型[J]. 计算机工程与设计, 2023, 44(5): 1511-1518. LI L, PENG N, WANG W. Remote sensing image detection model based on lightweight convolutional neural network[J]. Computer Engineering and Design, 2023, 44(5): 1511-1518. [3] 谭琬滢, 左珊珊, 邱佩琳, 等. 基于深度卷积神经网络的手写数字识别研究[J]. 智能计算机与应用, 2024, 14(8): 138-142. TAN W Y, ZUO S S, QIU P L, et al. Research on handwritten digit recognition based on deep convolutional neural network[J]. Intelligent Computers and Applications, 2024, 14(8): 138-142. [4] 朱克佳. 基于深度学习的目标检测研究[J]. 现代信息科技, 2024, 8(13): 76-83. ZHU K J. Research on object detection based on deep learning[J]. Modern Information Technology, 2024, 8(13): 76-83. [5] BRONSTEIN M M, BRUNA J, LECUN Y, et al. Geometric deep learning: going beyond euclidean data[J]. IEEE Signal Processing Magazine, 2017, 34(4): 18-42. [6] MASCI J, BOSCAINI D, BRONSTEIN M, et al. Geodesic convolutional neural networks on riemannian manifolds[C]//Proceedings of the IEEE International Conference on Computer Vision Workshops. Santiago, Chile: IEEE, 2015: 37-45. [7] BOSCAINI D, MASCI J, RODOLÀ E, et al. Learning shape correspondence with anisotropic convolutional neural networks[C]//Advances in Neural Information Processing Systems. Barcelona, Spain: MIT Press, 2016: 29. [8] ATWOOD J, TOWSLEY D. Diffusion-convolutional neural networks[C]//Advances in Neural Information Processing Systems. Barcelona, Spain: MIT Press, 2016: 29. [9] 李文静, 白静, 彭斌, 等. 图卷积神经网络及其在图像识别领域的应用综述[J]. 计算机工程与应用, 2023, 59(22): 15-35. LI W J, BAI J, PENG B, et al. A review of graph convolutional neural networks and their applications in image recognition[J]. Computer Engineering and Applications, 2023, 59(22): 15-35. [10] WU F, SOUZA A, ZHANG T, et al. Simplifying graph convolutional networks[C]//International Conference on Machine Learning. Long Beach, United States: ACM, 2019: 6861-6871. [11] 王启明, 胥津铭, 苏建, 等. 基于改进ALexNet模型的路面状况识别方法研究[J]. 公路交通科技, 2023, 40(3): 209-218. WANG Q M, XU J M, SU J, et al. Research on road condition recognition method based on improved ALexNet model[J]. Highway Traffic Technology, 2023, 40(3): 209-218. [12] SAHOO P K, PANDA M K, PANIGRAHI U, et al. Animproved VGG-19 network induced enhanced feature pooling for precise moving object detection in complex video scenes[J]. IEEE Access, 2024, 12: 45847-45864. [13] HASSAN E, HOSSAIN M S, SABER A, et al. A quantum convolutional network and ResNet (50)-based classification architecture for the MNIST medical dataset[J]. Biomedical Signal Processing and Control, 2024, 87: 105560. [14] 张艺博, 赵加坤, 陈攀, 等. 基于改进Mask RCNN的遥感图像小目标检测算法研究[J]. 计算机与数字工程, 2024, 52(3): 880-885. ZHANG Y B, ZHAO J K, CHEN P, et al. Research on small target detection algorithm in remote sensing images based on improved Mask RCNN[J]. Computer and Digital Engineering, 2024, 52(3): 880-885. [15] 孙顺远, 杨镇. 基于改进Faster RCNN的目标检测算法[J]. 计算机与数字工程, 2022, 50(12): 2654-2659. SUN S Y, YANG Z. Object detection algorithm based on improved Faster RCNN[J]. Computer and Digital Engineering, 2022, 50(12): 2654-2659. [16] 米增, 连哲. 面向通用目标检测的YOLO方法研究综述[J]. 计算机工程与应用, 2024, 60(21): 38-54. MI Z, LIAN Z. A review of YOLO methods for general object detection[J]. Computer Engineering and Applications, 2024, 60(21): 38-54. [17] BRESSON X, LAURENT T, VON BRECHT J. Enhanced Lasso recovery on graph[C]//2015 23rd European Signal Processing Conference. Nice, France: IEEE, 2015: 1501-1505. [18] SHAHID N, PERRAUDIN N, KALOFOLIAS V, et al. Fast robust PCA on graphs[J]. IEEE Journal of Selected Topics in Signal Processing, 2016, 10(4): 740-756. [19] 孙伟, 陈平华. 基于知识图谱上下文的图注意矩阵补全[J]. 计算机工程与应用, 2022, 58(11): 171-177. SUN W, CHEN P H. Graph attention matrix completion based on knowledge graph context[J]. Computer Engineering and Applications, 2022, 58(11): 171-177. [20] SCARSELLI F, GORI M, TSOI A C, et al. The graph neural network model[J]. IEEE Transactions on Neural Networks, 2008, 20(1): 61-80. [21] 张其, 陈旭, 王叔洋, 等. 动态图神经网络链接预测综述[J]. 计算机工程与应用, 2024, 60(20): 49-67. ZHANG Q, CHEN X, WANG S Y, et al. A review of dynamic graph neural network link prediction[J]. Computer Engineering and Applications, 2024, 60(20): 49-67. [22] 肖国庆, 李雪琪, 陈玥丹, 等. 大规模图神经网络研究综述[J]. 计算机学报, 2024, 47(1): 148-171. XIAO G Q, LI X Q, CHEN Y D, et al. A review of research on large-scale graph neural networks[J]. Journal of Computer Science, 2024, 47(1): 148-171. [23] DEFFERRARD M, BRESSON X, VANDERGHEYNST P. Convolutional neural networks on graphs with fast localized spectral filtering[C]//Advances in Neural Information Processing Systems. Barcelona, Spain: MIT Press, 2016: 29. [24] KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[C]//International Conference on Learning Representations. Toulon, France: OpenReview, 2017. [25] GROVER A, LESKOVEC J. node2vec: Scalable feature learning for networks[C]//Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining. San Francisco, USA: ACM, 2016: 855-864. [26] VELIČKOVIĆ P, CUCURULL G, CASANOVA A, et al. Graph attention networks[C]//International Conference on Learning Representations. Vancouver, Canada: OpenReview, 2018. [27] 侯磊, 刘金环, 于旭, 等. 图神经网络研究综述[J]. 计算机科学, 2024, 51(6): 282-298. HOU L, LIU J H, YU X, et al. A review of research on graph neural networks[J]. Computer Science, 2024, 51(6): 282-298. [28] CAO W, YAN Z, HE Z, et al. A comprehensive survey on geometric deep learning[J]. IEEE Access, 2020, 8: 35929-35949. [29] 刘金利, 张培玲. 改进LeNet-5网络在图像分类中的应用[J]. 计算机工程与应用, 2019, 55(15): 32-37, 95. LIU J L, ZHANG P L. Application of improved LeNet-5 network in image classification[J]. Computer Engineering and Applications, 2019, 55(15): 32-37, 95. [30] YANG Z, COHEN W, SALAKHUDINOV R. Revisiting semi-supervised learning with graph embeddings[C]//International Conference on Machine Learning. New York, USA: ACM, 2016: 40-48. [31] YANG K, WANG X, ZHENG Y. Atext categorization method using graph convolutional network based on sparse representation[C]//2019 Chinese Control Conference. Guangzhou, China: IEEE, 2019: 8756-8759. [32] JOHNSON R, ZHANG T. Semi-supervised convolutional neural networks for text categorization via region embedding[C]//Advances in Neural Information Processing Systems. Montreal, Canada: MIT Press, 2015, 28. [33] ISCEN A, TOLIAS G, AVRITHIS Y, et al. Label propagation for deep semi-supervised learning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE, 2019: 5070-5079. [34] BERAHMAND K, NASIRI E, ROSTAMI M, et al. A modified DeepWalk method for link prediction in attributed social network[J]. Computing, 2021, 103: 2227-2249. [35] CONG G, LIM S H. Versatile feature learning with graph convolutions and graph structures[C]//2021 International Conference on Data Mining Workshops. Auckland, New Zealand: IEEE, 2021: 669-677. [36] XU J, LI K, LI Z, et al.Fuzzy graph convolutional network for hyperspectral image classification[J]. Engineering Applications of Artificial Intelligence, 2024, 127: 107280.
