Accurate Image Cutout Using Automatically Generated Trimaps
Accurate Image Cutout Using Automatically Generated Trimaps
复制标题
DOI：
10.1109/iiaiaai55812.2022.00074
复制
发表时间：
2022-07
期刊：
影响因子：
--
通讯作者：
Yuki Matsuura;Takahiro Hayashi
中科院分区：
文献类型：
--
作者：
Yuki Matsuura;Takahiro Hayashi
图像切口已被广泛用于各种图像处理应用程序。图像切口技术可以分为半自动和自动方法。半自动方法需要用户互动，以精确切割目标对象。自动方法采用机器学习方法，这些方法不需要任何用户交互。在本文中，我们提出了一种新的切割方法，该方法结合了两种类型的方法，用于在没有任何用户交互的情况下获得精确的切口结果。提出的方法首先使用机器学习方法大致提取对象区域。接下来，使用提取的结果代替用户输入进行半自动方法，提出的方法获得了精确的切口结果。从使用可可数据集和AIM-500数据集的实验中，我们确认所提出的方法可以精确提取对象区域而无需任何用户交互。
Image cutout has been widely used in various image processing applications. Image cutout techniques can be divided into semi-automatic and automatic methods. Semi-automatic methods require user interaction for precise cutout of target objects. Automatic methods adopt machine-learning approaches which do not require any user interaction. In this paper, we proposed a new cutout method which combines the two types of methods for obtaining precise cutout results without any user interaction. The proposed method, first, roughly extracts an object region using a machine-learning approach. Next, using the extracted result instead of user input for a semi-automatic method, the proposed method obtains a precise cutout result. From experiments using COCO dataset and AIM-500 dataset, we confirmed that the proposed method can precisely extract object regions without any user interaction.