Chang Xu, Ye He, Albert Parra, Edward Delp, Nitin Khanna, Carol Boushey
School of Electrical and Computer Engineering Purdue University West Lafayette, Indiana.
Department of Electronics and Communication Engineering Graphic Era University Dehradun, India.
CEA13 (2013). 2013 Oct;2013:75-80. doi: 10.1145/2506023.2506037.
In this paper, we propose an extension to our previous work on food portion size estimation using a single image and a multi-view volume estimation method. The single-view technique estimates food volume by using prior information (segmentation and food labels) generated from food identification methods we described earlier. For multi-view volume estimation, we use"Shape from Silhouettes"to estimate the food portion size. The experimental results of our volume estimation methods demonstrate our results with respect to accuracy and reliability.
在本文中,我们对之前关于使用单张图像进行食物份量估计的工作以及一种多视图体积估计方法进行了扩展。单视图技术通过使用我们之前描述的食物识别方法生成的先验信息(分割和食物标签)来估计食物体积。对于多视图体积估计,我们使用“从轮廓获取形状”来估计食物份量大小。我们体积估计方法的实验结果在准确性和可靠性方面展示了我们的成果。