Evaluating the visual quality of web pages using a computational aesthetic approach

Abstract

Current Web mining explores useful and valuable information (content) online for users. However, there is scant research on the overall visual aspect of Web pages, even though visual elements such as aesthetics significantly influence user experience. A beautiful and well-laid out Web page greatly facilitates users' accessing and enhances browsing experiences. We use "visual quality (VisQ)" to denote the aesthetics of Web pages. In this paper, a computational aesthetics approach is proposed to learn the evaluation model for the visual quality of Web pages. First, a Web page layout extraction algorithm (V-LBE) is introduced to partition a Web page into major layout blocks. Then, regarding a Web page as a semi-structured image, features (e.g., layout, visual complexity, colorfulness) known to significantly affect the visual quality of a Web page are extracted to construct a feature vector. We present a multi-cost-sensitive learning for visual quality classification and a multi-value regression for visual quality score assignment. Our experiments compare the extracted features and conclude that the Web page's layout visual features (LV) and text visual features (TV) are the primary affecting factors toward Web page's visual quality. The performance of the learned visual quality classifier is close to some persons'. The learned regression function also achieves promising results.

Quantification of interface visual complexity

“…Unlike the studies above, Wu et al [42] identified low-level visual GUI characteristics (e.g., the number and sizes of visual blocks, and density of text characters), which accounted for 46% of variance in webpage visual quality ratings A part of their measures (e.g., the average values of hue, saturation and value of webpage screenshot), though, could represent the preferences of a particular social group rather than interface complexity, which might lower the generalizability of their results. Purchase et al [22] also concentrated on the visual side of complexity and operationalized it with the number of image colors (before and after color reduction), the variability in pixel luminance, the ratio of edge pixels to all pixels, and with the sizes of images saved in PNG, GIF and JPEG formats.…”

“…They could explain 78% of variation in colorfulness ratings. Similarly, Wu et al [42] used the average values and variation in hue, brightness and saturation, and again, colorfulness [11]. They could explain 46% of variation in webpage visual quality ratings.…”

Affective Analysis of Abstract Paintings Using Statistical Analysis and Art Theory

“…The progress of computer vision research has become mature enough to predict emotions Machajdik & Hanbury [2010]; Yanulevskaya et al [2008], aesthetics Marchesotti et al [2011], and interestingness Isola et al [2011] of images, paintings, and even web pages Wu et al [2011]. Yanulevskaya et al [2008] proposed an emotion categorization system based on the assessment of local image statistics followed by supervised learning of emotion categories using Support Vector Machines.…”

Detecting and Removing Visual Distractors for Video Aesthetic Enhancement

“…The users of capture devices also want to improve their results but often do not know how. Thus, researchers in the multimedia community have proposed intelligent methods to evaluate the visual quality of variant media, such as images [3][4] [5], videos [6], paintings [7] and webpages [8] [9]. They both utilize state-of-the-art techniques, such as deep learning [4], to rate aesthetic quality and investigate how the intrinsic features contribute to the final perceptual quality [10] [11].…”