MODELLING VISUAL COMPLEXITY USING GEOMETRIC PRIMITIVES

2020

Psychological studies explore visual complexity as perceived by humans. Image complexity is studied extensively in the mathematical, computational sciences. The two disciplines often define visual complexity differently and are thus disjointed. This is manifested in differences between subjective human-perceived complexity, and computer vision algorithms’ performance in visual tasks. Our study investigates this discrepancy in the context of cognitive tests that employ visual stimuli to assess a subject’s primal cognitive functions. A database of cognitive tests including visual recognition tasks and the performance of 403 subjects in terms of response times was used. Computer vision and information theory features were extracted from the images in these tasks. Inspired by cognitive psychology studies, the features were categorized into whole-image and object-specific features. A random forest classifier was used to map the computed features into three complexity labels in the tasks,...

2004

Abstract Scenes are composed of numerous objects, textures and colors which are arranged in a variety of spatial layouts. This presents the question of how visual complexity is represented by a cognitive system. In this paper, we aim to study the representation of visual complexity for real-world scene images. Is visual complexity a perceptual property simple enough so that it can be compressed along a unique perceptual dimension? Or is visual complexity better represented by a multi-dimensional space?

PLOS ONE, 2016

The aim of this work is to predict the complexity perception of real world images. We propose a new complexity measure where different image features, based on spatial, frequency and color properties are linearly combined. In order to find the optimal set of weighting coefficients we have applied a Particle Swarm Optimization. The optimal linear combination is the one that best fits the subjective data obtained in an experiment where observers evaluate the complexity of real world scenes on a web-based interface. To test the proposed complexity measure we have performed a second experiment on a different database of real world scenes, where the linear combination previously obtained is correlated with the new subjective data. Our complexity measure outperforms not only each single visual feature but also two visual clutter measures frequently used in the literature to predict image complexity. To analyze the usefulness of our proposal, we have also considered two different sets of stimuli composed of real texture images. Tuning the parameters of our measure for this kind of stimuli, we have obtained a linear combination that still outperforms the single measures. In conclusion our measure, properly tuned, can predict complexity perception of different kind of images.

This paper reports the results of experiments conducted to determine whether a mathematical/computational model reflects the perception of complexity of background image scenes. Background scenes, such as landscapes, are composed of non-discrete image data. They contain repetitive patterns and colour schemes and therefore the images have to be described using pattern analysis techniques. A brief outline is given regarding the difference in composition of the foreground and background in images. Complexity measures and theories are then explored and results of a pilot test and experiment reported which correlate human perceptual data with a pattern measure which was devised by . This measure had previously only been tested on binary data and not on more realistic image data. The results show a very strong, positive correlation (r=0.899, p<0.01) which seems to suggest that the human perception of complexity of non-determinate image data is modelled well by the pattern measure. The paper concludes by outlining potential implications of the work and uses of the model.

Royal Society Open Science

Perceptual load is a well-established determinant of attentional engagement in a task. So far, perceptual load has typically been manipulated by increasing either the number of task-relevant items or the perceptual processing demand (e.g. conjunction versus feature tasks). The tasks used often involved rather simple visual displays (e.g. letters or single objects). How can perceptual load be operationalized for richer, real-world images? A promising proxy is the visual complexity of an image. However, current predictive models for visual complexity have limited applicability to diverse real-world images. Here we modelled visual complexity using a deep convolutional neural network (CNN) trained to learn perceived ratings of visual complexity. We presented 53 observers with 4000 images from the PASCAL VOC dataset, obtaining 75 020 2-alternative forced choice paired comparisons across observers. Image visual complexity scores were obtained using the TrueSkill algorithm. A CNN with weig...

British Journal of Psychology, 2011

Computers &amp; Graphics, 2011

We present an approach to compute the perceived complexity of a given 3D shape using the similarity between its views. Previous studies on 3D shape complexity relied on geometric and/or topological properties of the shape and are not appropriate for incorporating results from human shape perception which claim that humans perceive 3D shapes as organizations of 2D views. Therefore, we base our approach to computing 3D shape complexity on the (dis)similarity matrix of the shape's 2D views. To illustrate the application of our approach, we note that simple shapes lead to similar views whereas complex ones result in different, dissimilar views. This reflected in the View Similarity Graph (VSG) of a shape as tight clusters of points if the shape is simple and increasingly dispersed points as it gets more complex. To get a visual intuition of the VSG, we project it to 2D using Multi-Dimensional Scaling (MDS) and introduce measures to compute shape complexity through point dispersion in the resulting MDS plot. Experiments show that results obtained using our measures alleviate some of the drawbacks present in previous approaches.

2013

This study aims to explore visual complexity in streetscape composition using RMS contrast information and Fractal Analysis. The dataset was composed of 74 streetscape images, taken in Algeria and Japan in daytime and nighttime. The evaluation and analysis covered two phases: (1) Subjective quantification of perceived complexity using ranking method. (2) Visual complexity measurement based on RMS contrast statistics and fractal characteristics of the streetscape images. The results showed a positive correlation between the subjective ranking of complexity in streetscape images and the proposed measure of visual complexity "α" as well as with the fractal dimension D b .

Designers strive for enjoyable user experience (UX) and put a significant effort into making graphical user interfaces (GUI) both usable and beautiful. Our goal is to minimize their effort: with this purpose in mind, we have been studying automatic metrics of GUI qualities. These metrics could enable designers to iterate their designs more quickly. We started from the psychological findings that people tend to prefer simpler things. We then assumed visual complexity determinants also determine visual aesthetics and outlined eight of them as belonging to three dimensions: information amount (visual clutter and color variability), information organization (symmetry, grid, ease-of-grouping and prototypicality), and information discriminability (contour density and figure-ground contrast). We investigated five determinants (visual clutter, symmetry, contour density, figure-ground contrast and color variability) and proposed six associated automatic metrics. These metrics take screenshots of GUI as input and can thus be applied to any type of GUI. We validated the metrics through a user study: we gathered the ratings of immediate impressions of GUI visual complexity and aesthetics, and correlated them with the output of the metrics. The output explained up to 51% of aesthetics ratings and 50% of complexity ratings. This promising result could be further extended towards the creation of tLight, our automatic GUI evaluation tool.

Humans are sensitive to complexity and