arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1708.01986stat.MLcs.CV
收藏

通过深度学习识别3种苔藓,使用“切碎图片”方法

Identifying 3 moss species by deep learning, using the "chopped picture" method

Kyoto University(京都大学)

Takeshi Ise, Mari Minagawa, Masanori Onishi

摘要:

一般来说,对象识别往往不能很好地工作在模糊的,无定形的对象,如植被。在这项研究中,我们开发了一种简单而有效的方法来识别模糊的对象,并将该方法应用于几种苔藓。结果表明,该模型对测试图像进行了正确分类,准确率超过90%。使用这种方法将有助于计算机视觉研究的进展。

英文摘要:

In general, object identification tends not to work well on ambiguous, amorphous objects such as vegetation. In this study, we developed a simple but effective approach to identify ambiguous objects and applied the method to several moss species. As a result, the model correctly classified test images with accuracy more than 90%. Using this approach will help progress in computer vision studies.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑