Valid data augmentation by patch alpha matting
文献类型：会议论文
| 作者 | Li, Hongyun; Rao, Jianghao; Zhou, Lijun; Zhang, Jianlin |
| 出版日期 | 2019-07-01 |
| 会议日期 | July 19, 2019 - July 21, 2019 |
| 会议地点 | Wuxi, China |
| DOI | 10.1109/SIPROCESS.2019.8868572 |
| 页码 | 361-366 |
| 英文摘要 | In this study, we designed a new data augmentation method by matting for object detection and segmentation tasks. This method first uses a trained model to retrieve easy samples from the training data. After the easy dataset is built, a new patch matting algorithm is used to obtain object's fine border, and then a set of photo montage strategies is used to generate a new dataset. For natural image matting, obtaining accurate borders around very similarly colored foreground and background regions is a hard challenge. This problem is often encountered in reality and causes visual flaws in composite images. To avoid poor composite images, we proposed a new matting method based on color and semantic features on patches to obtain visually acceptable images in such challenging regions and used it in the data augmentation method above. Unlike the traditional data augmentation method, which can only generate similar images, our method can effectively improve the ability of models to distinguish objects from the background. In experiments, we generated 20,000 new images and added them to the original COCO dataset to train a MaskRCNN model. As a result, the performances of our model are superior to the original model on all evaluating indexes of COCO. © 2019 IEEE. |
| 会议录 | 2019 IEEE 4th International Conference on Signal and Image Processing, ICSIP 2019
 |
| 会议录出版者 | Institute of Electrical and Electronics Engineers Inc. |
| 文献子类 | 会议论文 |
| 语种 | 英语 |
| 源URL | [http://ir.ioe.ac.cn/handle/181551/9588]  |
| 专题 | 光电技术研究所_光电探测与信号处理研究室（五室） |
| 作者单位 | Institute of Optics and Electronics, Chinese Academy of Sciences University, Chinese Academy of Sciences, Chengdu, China |
| 推荐引用方式 GB/T 7714 | Li, Hongyun,Rao, Jianghao,Zhou, Lijun,et al. Valid data augmentation by patch alpha matting[C]. 见:. Wuxi, China. July 19, 2019 - July 21, 2019. |
入库方式： OAI收割
来源：光电技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。