Food Image Recognition Using Covariance of Convolutional Layer Feature Maps
Food Image Recognition Using Covariance of Convolutional Layer Feature Maps
复制标题
DOI：
10.1587/transinf.2015edl8212
复制
发表时间：
2016-06
期刊：
影响因子：
--
通讯作者：
A. Tatsuma;Masaki Aono
中科院分区：
文献类型：
--
作者：
A. Tatsuma;Masaki Aono
最近的研究已经获得了图像识别任务中的上级性能，通过使用，作为一种图像表示，全连接层激活的卷积神经网络（CNN）训练与各种图像。然而，CNN表示不是很适合涉及食物图像识别的细粒度图像识别任务。为了提高CNN表示在食品图像识别中的性能，我们提出了一种新的图像表示，它由卷积层特征映射的协方差组成。在ETHZ Food-101数据集上的实验中，我们的方法达到了58.65%的平均准确率，优于之前的方法，如Bag-of-Visual-Words直方图，改进的Fisher向量和CNNSVM。关键词：食品图像识别，卷积神经网络，协方差描述符，模式识别，深度学习
Recent studies have obtained superior performance in image recognition tasks by using, as an image representation, the fully connected layer activations of Convolutional Neural Networks (CNN) trained with various kinds of images. However, the CNN representation is not very suitable for fine-grained image recognition tasks involving food image recognition. For improving performance of the CNN representation in food image recognition, we propose a novel image representation that is comprised of the covariances of convolutional layer feature maps. In the experiment on the ETHZ Food-101 dataset, our method achieved 58.65% averaged accuracy, which outperforms the previous methods such as the Bag-of-Visual-Words Histogram, the Improved Fisher Vector, and CNNSVM. key words: food image recognition, convolutional neural networks, covariance descriptor, pattern recognition, deep learning