Saliency modeling via outlier detection

Abstract

Based on the fact that human attention is more likely to be attracted by different objects or statistical outliers of a scene, a bottom-up saliency detection model is proposed. Our model regards the saliency patterns of an image as the outliers in a dataset. For an input image, first, each image element is described as a feature vector. The whole image is considered as a dataset and an image element is classified as a saliency pattern if its corresponding feature vector is an outlier among the dataset. Then, a binary label map can be built to indicate the salient and the nonsalient elements in the image. According to the Boolean map theory, we compute multiple binary maps as a set of Boolean maps which indicate the outliers in multilevels. Finally, we linearly fused them into the final saliency map. This saliency model is used to predict the human eye fixation, and has been tested on the most widely used three benchmark datasets and compared with eight state-of-the-art saliency models. In our experiments, we adopt the shuffled the area under curve metric to evaluate the accuracy of our model. The experimental results show that our model outperforms the state-of-the-art models on all three datasets. © 2014 SPIE and IS&T [

Optimization of Salient Object Segmentation by using the influence of color in Digital Image

“…From the various developments salient object detection, the influence of light intensity still cannot be solved, and there are various salient object detection results, which area of the object is clipped, or not displayed because it are not included as salient area [2], so it needs to be improved, so that cuts area of the object can be produced with more natural. Some of these errors can be shown in Fig [8], Chen [6] and Zhu [26] and also some other methods.…”

“…There are many applications that use visual interest or salient objects that have been developed at this time, such as, automatic image cropping [24], adaptive image display on small devices [7], image / video compression, advertising design [16], and images collection browsing [23]. Various approaches to detect salient area of various objects have been done, including structural salient object detection [25], A Model of Saliency-Based Visual Attention for Rapid Scene Analysis [17], Saliency Based on Information Maximization [4], Graph-based visual saliency [12], A spectral residual approach saliency detection [15], multi-task saliency pursuit method [20], Frequency-tuned salient region detection [1], Highlighting sparse salient regions [14], adaptive clustering saliency [5], outlier detection saliency [6], the soft image abstraction salient detection [9], and several optimizations such as Robust Background Detection Optimization [26], and global contrast based optimization [8].…”

“…Nowadays, many segmentation techniques available, but none of them were able to meet the natural shape of the object, so it remains a challenge for researchers [22]. Human attention is more likely to be interested in different objects or striking in image processing called the salient object [6]. Research concerning the interests of eyes to the salient object, has been studied by researchers in physiology, psychology, nervous system, and computer vision for a long time as described in Section II.…”

Saliency Detection from Subitizing Processing

“…Zhu [33], on the other hand, proposed a visual attention architecture called DenseASPP, to extract information. Chen [34] proposed a spatial attenuation context network, which recursively translated and aggregated the context features in different layers. Tu [35] introduced an edge-guided block to embed boundary information in saliency maps.…”

Sparsity-guided saliency detection for remote sensing images

“…In order to achieve automatic, rapid, and accurate remote sensing target detection, saliency detection was introduced to the remote sensing field in the last decade. [1][2][3][4][5][6] This method imitates human visual attention to identify the attention-grabbing regions that may contain candidate objects.…”