Predicting Human Perception of Scene Complexity

Cameron Kyle-Davidson; Adrian Gheorghe Bors; Karla Evans

doi:10.1109/ICIP46576.2022.9897953

Predicting Human Perception of Scene Complexity

Cameron Kyle-Davidson, Adrian Gheorghe Bors, Karla Evans

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

It is apparent that humans are intrinsically capable of determining the degree of complexity present in an image; but it is unclear which regions in that image lead humans towards evaluating an image as complex or simple. Here, we develop a novel deep learning model for predicting human perception of the complexity of natural scene images in order to address these problems. For a given image, our approach, ComplexityNet, can generate both single-score complexity ratings and two-dimensional per-pixel complexity maps. These complexity maps indicate the regions of scenes that humans find to be complex, or simple. Drawing on work in the cognitive sciences we integrate metrics for scene clutter and scene symmetry , and conclude that the proposed metrics do indeed boost neural network performance when predicting complexity.

Original language	English
Title of host publication	IEEE International Conference on Image Processing (ICIP)
Place of Publication	Bordeaux, France
Publisher	IEEE
Pages	1281-1285
DOIs	https://doi.org/10.1109/ICIP46576.2022.9897953
Publication status	Published - 18 Oct 2022

Bibliographical note

© IEEE 2022. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details

Access to Document

10.1109/ICIP46576.2022.9897953

Predicting Human Perception of Scene Complexity
© IEEE 2022. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details
Accepted author manuscript, 8.29 MB

Cite this

@inproceedings{ad5b4a2098ef44f2994eabe1892b0472,

title = "Predicting Human Perception of Scene Complexity",

abstract = "It is apparent that humans are intrinsically capable of determining the degree of complexity present in an image; but it is unclear which regions in that image lead humans towards evaluating an image as complex or simple. Here, we develop a novel deep learning model for predicting human perception of the complexity of natural scene images in order to address these problems. For a given image, our approach, ComplexityNet, can generate both single-score complexity ratings and two-dimensional per-pixel complexity maps. These complexity maps indicate the regions of scenes that humans find to be complex, or simple. Drawing on work in the cognitive sciences we integrate metrics for scene clutter and scene symmetry , and conclude that the proposed metrics do indeed boost neural network performance when predicting complexity.",

author = "Cameron Kyle-Davidson and Bors, {Adrian Gheorghe} and Karla Evans",

note = "{\textcopyright} IEEE 2022. This is an author-produced version of the published paper. Uploaded in accordance with the publisher{\textquoteright}s self-archiving policy. Further copying may not be permitted; contact the publisher for details",

year = "2022",

month = oct,

day = "18",

doi = "10.1109/ICIP46576.2022.9897953",

language = "English",

pages = "1281--1285",

booktitle = "IEEE International Conference on Image Processing (ICIP)",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - Predicting Human Perception of Scene Complexity

AU - Kyle-Davidson, Cameron

AU - Bors, Adrian Gheorghe

AU - Evans, Karla

N1 - © IEEE 2022. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details

PY - 2022/10/18

Y1 - 2022/10/18

N2 - It is apparent that humans are intrinsically capable of determining the degree of complexity present in an image; but it is unclear which regions in that image lead humans towards evaluating an image as complex or simple. Here, we develop a novel deep learning model for predicting human perception of the complexity of natural scene images in order to address these problems. For a given image, our approach, ComplexityNet, can generate both single-score complexity ratings and two-dimensional per-pixel complexity maps. These complexity maps indicate the regions of scenes that humans find to be complex, or simple. Drawing on work in the cognitive sciences we integrate metrics for scene clutter and scene symmetry , and conclude that the proposed metrics do indeed boost neural network performance when predicting complexity.

AB - It is apparent that humans are intrinsically capable of determining the degree of complexity present in an image; but it is unclear which regions in that image lead humans towards evaluating an image as complex or simple. Here, we develop a novel deep learning model for predicting human perception of the complexity of natural scene images in order to address these problems. For a given image, our approach, ComplexityNet, can generate both single-score complexity ratings and two-dimensional per-pixel complexity maps. These complexity maps indicate the regions of scenes that humans find to be complex, or simple. Drawing on work in the cognitive sciences we integrate metrics for scene clutter and scene symmetry , and conclude that the proposed metrics do indeed boost neural network performance when predicting complexity.

U2 - 10.1109/ICIP46576.2022.9897953

DO - 10.1109/ICIP46576.2022.9897953

M3 - Conference contribution

SP - 1281

EP - 1285

BT - IEEE International Conference on Image Processing (ICIP)

PB - IEEE

CY - Bordeaux, France

ER -