.png){kind=icon}
返回
A Combined Method for Multi-class Image Semantic Segmentation
.png){kind=icon}
PRE
AI
DOI：10.1109/TCE.2012.6227465.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Multi-class image semantic segmentation (MCISS) is one of the most crucial steps toward many applications related with consumer electronics fields such as image editing and content-based image retrieval. Existing MCISS approaches often consider only the top-down process and suffer from poor label consistency among neighboring pixels. To overcome this limitation, this paper proposes a combined MCISS method to integrate a state-of-the-art top-down (TD) approach Semantic Texton Forests (STF) and a classical bottom-up (BU) approach JSEG to exploit their relative merits. Experimental results on two challenging datasets show that the proposed method can achieve higher accuracy in comparison with the original STF method, while it does not notably prolong the computational time. In addition, several insights into the evaluation metrics of MCISS are reported.
Keyword:
Multi-Class Image Semantic Segmentation
Combined Segmentation
Evaluation Metrics
期刊
IF:
10.9
论文数:
5.3K
被引数:
6.8K
机构
引用论文
.png){kind=icon}
Geochemistry and zircon U–Pb geochronology of mafic rocks in the Kaiyuan tectonic mélange of northern Liaoning Province, NE China: Constraints on the tectonic evolution of the Paleo‐Asian Ocean中国东北辽宁省北部开元构造m é lange中镁铁质岩的地球化学和锆石u-pb年代学: 古亚洲海洋构造演化的制约因素
PREAI
分享收藏
Sarcomatoid Intrahepatic Cholangiocarcinoma: A Rare Case of Primary Liver Cancer肉瘤样肝内胆管癌：一种罕见的原发性肝癌病例
OAAI
OAAI分享收藏分享收藏
查看更多内容