激光与光电子学进展, 2021, 58 (6): 0610019, 网络出版: 2021-03-11   

基于改进残差网络的中式菜品识别模型 下载: 532次

Chinese Food Recognition Model Based on Improved Residual Network
作者单位
南京信息工程大学自动化学院, 江苏 南京 210044
摘要
针对传统神经网络无法对相似度较高的中式菜品进行有效分类的问题,提出了一种基于改进残差网络的中式菜品识别 RNA-TL (ResNet with Attention and Triplet Loss) 模型。该算法先融合多尺度特征以提取深层次图像的语义信息,然后增加一层注意力机制层,给予图像重要部分更多的关注,最后利用三元组损失(Triplet Loss, TL)计算类间相似度并将结果输入到支持向量机(Support Vector Machine, SVM)中进行分类。实验表明,相较于其他主流算法模型,RNA-TL模型在中式菜品公共数据集上以及课题组采集的数据集上的识别准确率表现出更优越的性能。
Abstract
In view of the fact that traditional neural networks cannot effectively classify Chinese food with high similarity, a Chinese food recognition model of RNA-TL (ResNet with attention and triplet loss) based on an improved residual network is proposed. The algorithm first fuses the multi-scale features to extract the semantic information of deep-level images, and then adds an attention mechanism layer to give more attention to the important parts of the images. Finally, the similarity among classes is calculated by using triplet-loss, whose result is input into support vector machine (SVM) for classification. The experimental results indicate that the proposed RNA-TL model possesses more superior performances in recognition accuracy on the public dataset of Chinese food and the dataset collected by our project team, compared with the other mainstream algorithm models.

邓志良, 李磊. 基于改进残差网络的中式菜品识别模型[J]. 激光与光电子学进展, 2021, 58(6): 0610019. Deng Zhiliang, Li Lei. Chinese Food Recognition Model Based on Improved Residual Network[J]. Laser & Optoelectronics Progress, 2021, 58(6): 0610019.

本文已被 2 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!