Saliency detection is useful for many computer vision tasks including content-based image retrieval, segmentation, and object detection. However, methods on saliency detection are usually greatly affected by factors like features and segmentation results. We propose a novel selective segmentation-based saliency detection model to decrease the side effects caused by these factors. After extracti...

Automatic image segmentation is emerging field in image processing research domain. In a visual scene, the objects which are different from their surroundings get more visual importance and get high gaze attention of the viewer. Saliency detection predicts significantly important regions in a scene, which should be considered for further processing according to specific applications. There are ...

The success of current deep saliency detection methods heavily depends on the availability of large-scale supervision in the form of per-pixel labeling. Such supervision, while labor-intensive and not always possible, tends to hinder the generalization ability of the learned models. By contrast, traditional handcrafted features based unsupervised saliency detection methods, even though have bee...

We present a new segment-based method for saliency detection based on multi-size superpixels that combines local and global saliency cues. We extract superpixels at several scales and represent each superpixel with a normal distribution in CIE-Lab space estimated from its associated pixels. Global saliency is computed by grouping similar superpixels to estimate the spatial distribution of color...

We discuss two experiments that deal with saliency in videos. In the first experiment, we combine motion detection algorithms with a context-aware saliency detection algorithm to add motion as a feature in video saliency. In the second experiment, we apply principles from spatial saliency in static images to pick out salient frames in a video.

In order to solve the problem of defect detection and contour accurate segmentation periodic texture fabric images, a method based on saliency region similarity location is proposed. Firstly, image be detected was processed by color space conversion, Gaussian filtering, contrast enhancement, frequency-tuned (FT) salient algorithm used estimate map enhanced image. The divided into blocks same si...

360° images are informative – it contains omnidirectional visual information around the camera. However, areas that cover a image is much larger than human’s field of view, therefore important in different view directions easily overlooked. To tackle this issue, we propose method for predicting optimal set Region Interest (RoI) from single using saliency as clue. deal with ...

Saliency detection is an active topic in multimedia field. Several algorithms have been proposed in this field. Most previous works on saliency detection focus on 2D images. However, for some complex situations which contain multiple objects or complex background, they are not robust and their performances are not satisfied. Recently, 3D visual information supplies a powerful cue for saliency d...

In this paper, we propose a new approach to detect salient traffic signs, which is based on visual saliency and auto-generated strokes for image segmentation. The proposed algorithm deals with two tasks on detecting traffic signs: auto-location and auto extraction. Firstly, inspired by recent work of visual saliency detection, we obtain the location of traffic signs in a natural image by multi-...