| 摘 要: 本文重点研究宫颈细胞图像分类识别问题，结合宫颈细胞病理学等方面知识，利用基于深度卷积神经 网络ResNet50的迁移学习，对实验数据集进行模型训练和特征提取。实验结果表明，通过基于深度神经网络的迁移学 习，可以获取较优的病变与正常细胞的分类结果。 |
| 关键词: 卷积神经网络；迁移学习；宫颈癌 |
|
中图分类号: TP391.4
文献标识码: A
|
|
| Lesion Cell Classification of Cervical Smear Based on Deep Convolution Neural Network |
|
HU Hui,CAI Jinqing
|
( School of Computer Science and Software, Tianjin University of Technology, Tianjin 300387, China)
|
| Abstract: This article focuses on the study of cervical cell image classification and recognition in combination with the knowledge of cervical pathology from the perspective of the transfer learning of the deep convolution neural network ResNet50 to perform model training and feature extraction.It shows that better classification results of lesion and normal cells can be obtained. |
| Keywords: convolution neural network;transfer learning;cervical cancer |
