期刊
VISUAL COMPUTER
卷 37, 期 6, 页码 1277-1296出版社
SPRINGER
DOI: 10.1007/s00371-020-01865-x
关键词
Image saliency; Image segmentation; Image features
The study introduces three unique real-time saliency generation algorithms which provide state-of-the-art performance for greyscale and colour images. These algorithms are more than 10 times faster than traditional models, with similar or better precision performance.
Unsupervised salient image generation without the aid of prior assumptions has many applications in computer vision. We present three unique real-time saliency generation algorithms that provide state-of-the-art performance for greyscale and colour images. Our fastest method run under 50 ms per frame on average. Our algorithm introduces a novel weighted histogram of orientation feature to supplement image intensity for monochromatic image manifold ranking. We also provide a method of dimensional reduction for the non-normalized optimal affinity matrix (OAM) using principal components analysis; this novel technique allows faster computation and stabilization of the OAM inversion process. We compare our methods with 18 traditional and recent techniques using three standard and custom datasets including ECSSD, DUT-OMRON and MSRA10K totalling 32,536 images for colour and greyscale variations. The results show our method to be more than 10 x faster than the RC and GMR models and having similar or better precision performances.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据