CNN-Based Food Image Segmentation Without Pixel-Wise Annotation

被引：27

作者：

Shimoda, Wataru ^{[1
]}

Yanai, Keiji ^{[1
]}

机构：

[1] Univ Electrocommun, Dept Informat, Chofu, Tokyo 1828585, Japan

来源：

NEW TRENDS IN IMAGE ANALYSIS AND PROCESSING - ICIAP 2015 WORKSHOPS | 2015年 / 9281卷

关键词：

Food segmentation; Convolutional neural network; Deep learning; UEC-FOOD;

D O I：

10.1007/978-3-319-23222-5_55

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We propose a CNN-based food image segmentation which requires no pixel-wise annotation. The proposed method consists of food region proposals by selective search and bounding box clustering, back propagation based saliency map estimation with the CNN model fine-tuned with the UEC-FOOD100 dataset, GrabCut guided by the estimated saliency maps and region integration by non-maximum suppression. In the experiments, the proposed method outperformed RCNN regarding food region detection as well as the PASCAL VOC detection task.

引用

页码：449 / 457

页数：9