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 $$10{\times }$$ 10 × faster than the RC and GMR models and having similar or better precision performances.

中文翻译：

---

灰度和彩色图像的实时显着性检测

无需先验假设的无监督显着图像生成在计算机视觉中具有许多应用。我们提出了三种独特的实时显着性生成算法，可为灰度和彩色图像提供最先进的性能。我们最快的方法平均每帧运行时间不到 50 毫秒。我们的算法引入了一种新颖的方向特征加权直方图，以补充单色图像流形排名的图像强度。我们还提供了一种使用主成分分析的非归一化最优亲和矩阵 (OAM) 的降维方法；这种新技术允许更快地计算和稳定 OAM 反演过程。我们使用三个标准和自定义数据集（包括 ECSSD、DUT-OMRON 和 MSRA10K 共 32 个）将我们的方法与 18 种传统和最新技术进行比较，536 幅图像用于颜色和灰度变化。结果表明，我们的方法比 RC 和 GMR 模型快 10 多美元{\times }$$ 10 倍，并且具有相似或更好的精度性能。