期刊文献+

基于FL-ResNet50的皮肤镜图像分类方法 被引量:2

Dermoscopic Image Classification Method Based on FL-ResNet50
原文传递
导出
摘要 提出一种采用深度卷积神经网络模型对七类病变皮肤镜图像进行分类的方法。使用数据增强方法扩增训练集,提出一种基于ResNet50模型和多分类Focal Loss函数的多分类模型(FL-ResNet50模型),实现皮肤镜图像的多分类。实验结果表明,FL-ResNet50模型的微平均F1值为0.88,优于传统的ResNet50模型。所提方法实现了对七类皮肤镜图像的分类,将图像预处理、特征提取及预测模型学习形成一个完整连续的系统模型,提高了分类性能和效率,具有重要的应用价值。 In this paper,a classification method for seven types of dermoscopic images based on deep convolution neural network model is proposed.The training set is amplified using the data augmentation method.For the multiclassification of dermoscopic images,the multiclassification model(FL-ResNet50 model)based on ResNet50 model and multiclassification Focal Loss function is proposed.The experimental results show that the micromean F1 value of FL-ResNet50 model is 0.88,which is better than the results obtained using the traditional ResNet50 model.The proposed method realizes seven types of dermoscopic image classification and forms a complete and continuous system model by image preprocessing,feature extraction,and prediction model learning.The FL-ResNet50 model improves upon the classification performance and efficiency of the previous models and has important application value.
作者 罗清 周维 马梓钧 许海霞 Luo Qing;Zhou Wei;Ma Zijun;Xu Haixia(School of Information and Eingineeving,Xiangtan University,Xiangtan,Hunan 411105,China)
出处 《激光与光电子学进展》 CSCD 北大核心 2020年第18期224-232,共9页 Laser & Optoelectronics Progress
基金 国家自然科学基金青年科学基金(61602397) 湖南省物联网学会新华三基金(2018wlw001) 湘潭大学大学生创新性实验计划(201917)。
关键词 图像处理 卷积神经网络 皮肤镜图像 图像分类 样本不平衡 数据增强 损失函数 image processing convolutional neural network dermoscopy image image classification sampleimbalance data augmentation loss function
  • 相关文献

参考文献7

二级参考文献77

  • 1石平,雷增杰,蓝宗富,朱世杰.如何快速有效地获取网上病理学图像资源[J].西北医学教育,2007,15(2):219-221. 被引量:4
  • 2Lowe D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60 (2) 91 110.
  • 3Dalai N, Triggs B. Histograms of oriented gradients for human detection[C]//Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society Conference on. San Diego, USA: IEEE, 2005, 1 886-893.
  • 4Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786) : 504-507.
  • 5Hubel D H, Wiesel T N. Receptive fields, binocular interaction and functional architecture in the catrs visual cortex[J]. The Journal of Physiology, 1962, 160(1): 106-154.
  • 6Fukushima K, Miyake S. Neocognitron: A new algorithm for pattern recognition tolerant of deformations and shifts in posi- tion[J]. Pattern Recognition, 1982, 15(6): 455-469.
  • 7Ruck D W, Rogers S K, Kabrisky M. Feature selection using a multilayer perceptron[J]. Journal of Neural Network Com- puting, 1990, 2(2): 40-48.
  • 8Rumelhart D E, Hinton G E, Williams R J. Learning representations by back-propagating errors[J]. Nature, 1986,3231 533 538.
  • 9LeCun Y, Denker J S, Henderson D, et al. Handwritten digit recognition with a back-propagation network[C]//Advances in Neural Information Processing Systems. Colorado, USA Is. n. ], 1990: 396-404.
  • 10LeCun Y, Cortes C. MNIST handwritten digit database[EB/OL], http//yann, lecun, com/exdb/mnist, 2010.

共引文献787

同被引文献13

引证文献2

二级引证文献4

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部