Webpage is becoming a more and more important visual input to us. While there are few studies on saliency in webpage, we in this work make a focused study on how humans deploy their attention when viewing webpages and for the first time propose a computational model that is designed to predict webpage saliency. A dataset is built with 149 webpages and eye tracking data from 11 subjects who free-view the webpages. Inspired by the viewing patterns on webpages, multi-scale feature maps that contain object blob representation and text representation are integrated with explicit face maps and positional bias. We propose to use multiple kernel learning (MKL) to achieve a robust integration of various feature maps. Experimental results show that the proposed model outperforms its counterparts in predicting webpage saliency.
In this paper, ultrasound imaging is utilized to detect the anatomical structure of the lumbar spine based on which an image processing algorithm will search for key features to identify the optimal needle insertion site. The key challenge lies in the nature of ultrasound images which are obscure and have low spatial resolution, induced by contamination from random speckle noises. In order to improve the interpretability of ultrasound images, a modified version of local normalization using the Difference of Gaussian algorithm is first used for pre-processing to filter the speckle noise and extract the main anatomical structure in the raw images obtained. Meanwhile, local means induced by non-uniform wave reflection rate is also successfully removed by the proposed pre-processing algorithm, thus a potential element that may degrade the image recognition accuracy is excluded. In the second stage, a template matching algorithm, augmented with a position correlation function, automatically identifies the key features of interest and thus the insertion site. The approach has been tested on more than 200 ultrasound images with a 100% success rate. The proposed system allows the anesthetist to use the approach efficiently without the burden of interpreting real time ultrasound images.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.