Abstract
A wide variety of methods have been developed to approach the problem of salient ob ject detection. The performance of these meth- ods is often image-dependent. This paper aims to develop a method that is able to select for an input image the best salient ob ject detection result from many results produced by different methods. This is a challenging task as different salient ob ject detection results need to be compared without any ground truth. This paper addresses this challenge by design- ing a range of features to measure the quality of salient ob ject detection results. These features are then used in various machine learning algo- rithms to rank different salient ob ject detection results. Our experiments show that our method is promising for ranking salient ob ject detection results and our method is also able to pick the best salient ob ject detec- tion result such that the overall salient ob ject detection performance is better than each individual method.