In recent years, several authors have reported that spectral saliency detection methods provide state-of-the-art performance in predicting human gaze in images (see, e.g., [1 3]). We systematically integrate and evaluate quaternion DCTand FFT-based spectral saliency detection [3,4], weighted quaternion color space components [5], and the use of multiple resolutions [1]. Furthermore, we propose ...

The purpose of this supplementary material is to examine in detail the contributions of our proposed Local Background Enclosure (LBE) feature. A comparison of LBE with the contrast based depth features used in state-of-the-art salient object detection systems is presented. The LBE feature is compared with the raw depth features ACSD [1], DC [3] and a signed version of DC denoted SDC on the RGBD...

The benefits of integrating attention and object recognition are investigated. While attention is frequently modeled as a pre-processor for recognition, we investigate the hypothesis that attention is an intrinsic component of recognition and vice-versa. This hypothesis is tested with a recognition model, the hierarchical discriminant saliency network (HDSN), whose layers are top-down saliency ...

Lane cracks are one of the biggest threats to pavement conditions. The automatic detection lane can not only assist evaluation road quality and quantity but also be used develop best crack repair plan, so as keep level ensure driving safety. Although extracted from images because gray intensity pixels is lower than background intensity, it still a challenge extract continuous complete three-lan...

In this study, the authors investigated how salient visual features capture attention and facilitate detection of emotional facial expressions. In a visual search task, a target emotional face (happy, disgusted, fearful, angry, sad, or surprised) was presented in an array of neutral faces. Faster detection of happy and, to a lesser extent, surprised and disgusted faces was found both under upri...

This paper presents a new interest point detector for color images. It is based on a non linear filtering of the image which preserves edges, and on the use of a color point detector based on the Harris detector. We present how does interest points detectors work to justify the use of this filtering. We compare it with the Harris detector under the criteria of repeatibility, information content...