|
|
基于高斯过程分类的小样本图像识别
|
Abstract:
当今图片分类课题应用广泛，各种神经网络模型层出不穷。计算机性能和图片样本量对模型的训练和预测结果均有影响。针对于图片分类可能遇到的小样本问题，本文提出使用高斯过程分类模型和HSV图片分解的组合方式，与传统机器学习模型和RGB分解方式进行比较，发现该组合方式的准确率最高，效果最好。
Nowadays, image classification is widely used, and various neural network models emerge in endlessly. The performance of computer and the sample size of pictures have an influence on the training and prediction results of the model. Aiming at the problem of small samples that may be encountered in image classification, this paper proposes a combination method of the Gaussian process classification model and HSV image decomposition. Compared with the traditional machine learning model and RGB decomposition method, it is found that this combination method has the highest accuracy and the best effect.
| [1] | 郑远攀, 李广阳, 李晔. 深度学习在图像识别中的应用研究综述[J]. 计算机工程与应用, 2019, 55(12): 20-36. |
| [2] | He, K., Zhang, X., Ren, S. and Sun, J. (2015) Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37, 1904-1916.
https://doi.org/10.1109/TPAMI.2015.2389824 |
| [3] | 季长清, 高志勇, 秦静, 汪祖民. 基于卷积神经网络的图像分类算法综述[J]. 计算机应用, 2022, 42(4): 1044-1049. |
| [4] | 盖荣丽, 蔡建荣, 王诗宇, 仓艳, 陈娜. 卷积神经网络在图像识别中的应用研究综述[J]. 小型微型计算机系统, 2021, 42(9): 1980-1984. |
| [5] | LeCun, Y., Bottou, L., Bengio, Y. and Haffner, P. (1998) Gradient-Based Learn in Applied to Document Recognition. Proceedings of the IEEE, 86, 2278-2324. https://doi.org/10.1109/5.726791 |
| [6] | Krizhevsky, A., Sutskever, I. and Hinton, G.E. (2012) Imagenet Classification with Deep Convolutional Neural Networks. Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012, Lake Tahoe, 3-6 December 2012, 1097-1105. |
| [7] | Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Anguelov, D., Erhan, D., Vanhoucke, V. and Rabinovich, A. (2015) Going Deeper with Convolutions. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, 7-12 June 2015, 1-9. https://doi.org/10.1109/CVPR.2015.7298594 |
| [8] | Simonyan, K. and Zisserman, A. (2021) Very Deep Convolutional Networks for Large-Scale Image Recognition. 3rd International Conference on Learning Representations, ICLR 2015, San Diego, 7-9 May 2015, 1-14.
https://arxiv.org/pdf/1409.1556.pdf |
| [9] | He, K., Zhang, X., Ren, S. and Sun, J. (2016) Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, 27-30 June 2016, 770-778.
https://doi.org/10.1109/CVPR.2016.90 |
| [10] | Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T. andreetto, M. and Adam, H. (2021) Mobilenets: Efficient Convolutional Neural Networks for Mobile Vision Applications.
https://arxiv.org/pdf/1704.04861.pdf |
| [11] | 刘颖, 雷研博, 范九伦, 王富平, 公衍超, 田奇. 基于小样本学习的图像分类技术综述[J]. 自动化学报, 2021, 47(2): 297-315. |
| [12] | 吕昊远, 俞璐, 周星宇, 邓祥. 半监督深度学习图像分类方法研究综述[J]. 计算机科学与探索, 2021, 15(6): 1038-1048. |
| [13] | 葛轶洲, 刘恒, 王言, 徐百乐, 周青, 申富饶. 小样本困境下的深度学习图像识别综述[J]. 软件学报, 2022, 33(1): 193-210. https://doi.org/10.13328/j.cnki.jos.006342 |
| [14] | 王海霞, 李凯勇. 基于机器学习的图像敏感信息识别方法[J]. 现代电子技术, 2021, 44(19): 66-70. |
| [15] | 安强强, 张峰, 李赵兴, 张雅琼. 基于机器学习的图像分割研究[J]. 自动化与仪器仪表, 2018(6): 29-31. |
| [16] | 田朝辉, 金鑫, 赵耿, 李晓东. 基于深度学习的物体识别验证码破解方法[J]. 计算机仿真, 2018, 35(3): 216-220. |
| [17] | Williams, C.K. and Rasmussen, C.E. (2006) Gaussian Processes for Machine Learning. MIT Press, Cambridge.
https://doi.org/10.7551/mitpress/3206.001.0001 |
| [18] | 叶婧. 基于高斯过程回归的锂电池数据处理[D]: [硕士学位论文]. 北京: 北京交通大学, 2016. |
| [19] | 何亚东. 云南大理州林火预测的高斯过程分类模型研究[D]: [硕士学位论文]. 昆明: 云南大学, 2020. |
| [20] | 石美红, 申亮, 龙世忠, 胡西民. 从RGB到HSV色彩空间转换公式的修正[J]. 纺织高校基础科学学报, 2008(3): 351-356. |
| [21] | 刘国宏, 于竞翔, 任丽君. RGB检测方法研究进展[J]. 分析科学学报, 2020, 36(4): 591-596. |
| [22] | 姜兰池, 沈国强, 张国煊. 基于HSV分块颜色直方图的图像检索算法[J]. 机电工程, 2009, 26(11): 54-57. |
| [23] | 魏宝刚, 李向阳, 鲁东明, 潘云鹤. 彩色图像分割研究进展[J]. 计算机科学, 1999(4): 59-62. |
| [24] | 张国权, 李战明, 李向伟, 魏伟一. HSV空间中彩色图像分割研究[J]. 计算机工程与应用, 2010, 46(26): 179-181. |
