Hand-dorsa vein recognition with structure growing guided CNN
Hand-dorsa vein recognition with structure growing guided CNN
复制标题
DOI：
10.1016/j.ijleo.2017.09.064
复制
发表时间：
2017-11
期刊：
影响因子：
3.1
通讯作者：
Jun Wang;Guoqing Wang
中科院分区：
文献类型：
--
作者：
Jun Wang;Guoqing Wang
传统的手工特征模型无法同时克服旋转、缩放、平移和光照变化的影响。另一方面，预处理步骤不可避免地通过去噪和对比度增强来破坏现有的特征分布，这在传统的识别框架中是必要的，并且经常带来高的错误拒绝率。CNN可以识别具有极端可变性的模式，并且对失真和简单的几何变换具有鲁棒性，用于解决静脉识别任务。对原始CNN进行了三次修改。首先将正则化的RBF网络引入到CNN中，实现最后一层的识别任务。其次，自生长策略被设置为跨全局模型训练特征学习层。此外，设计了新添加层中的参数学习算法和新发布模型中的再学习算法，以获得最终的RCNN-3模型，用于生成区分性特征表示和最先进的分类结果。在实验室建立的手背静脉数据库上进行了严格的实验，训练识别率达到91.25%，测试识别率达到89.43%，同时与手工特征和CNN模型进行了对比实验，充分证明了该模型对手背静脉识别问题的有效性。证明了在传统的静脉识别任务中引入特征学习模型的必要性。
Traditional hand-crafted feature models are incapable of overcoming the rotation, scaling, translation and lighting variation influence simultaneously. On the other hand, the pre-processing step, which inevitably destroys the existing feature distribution by denoising and contrast enhancement, is necessary in the traditional recognition framework and often brings in high false rejection rate. CNN, which can recognize patterns with extreme variability, and with robustness to distortions and simple geometric transformations, is adopted to tackle the vein recognition task. Three modifications are made to the original CNN. Firstly, the regularized RBF network is imported to the CNN to realize the recognition task in the last layer. Secondly, self-growth strategy is set to train the feature learning layers across the global model. What’s more, the parameters learning algorithm in the newly-added layer and relearning in the newly published model is designed to obtain the final RCNN-3 model for the generation of discriminative feature representation and state-of-the-art classification results. Rigorous experimental results with the lab-made hand-dorsa vein database by achieving recognition rate of 91.25% in training and 89.43% in testing, and also the comparative experiments with both hand-crafted feature and CNN models fully demonstrates the effectiveness of the proposed model for hand-dorsa vein recognition problem, as well as proves the necessity of importing feature learning model to traditional vein recognition task.