Photographic composition classification and dominant geometric element detection for outdoor scenes

Jun Tae Lee, Han Ul Kim, Chul Lee, Chang-Su Kim

Research output: Contribution to journalArticle

Abstract

Despite the practical importance of photographic composition for improving or assessing the aesthetical quality of photographs, only a few simple composition rules have been considered for its classification. In this work, we propose novel techniques to classify photographic composition rules of outdoor scenes and detect dominant geometric elements, called composition elements, for each composition class. Specifically, we first categorize composition rules of outdoor photographs into nine classes: RoT, center, horizontal, symmetric, diagonal, curved, vertical, triangle, and pattern. Then, we develop a photographic composition classification algorithm using a convolutional neural network (CNN). To train the CNN, we construct a photographic composition database, which is publicly available. Finally, for each composition class, we propose an effective scheme to locate composition elements, i.e., bounding boxes for main subjects, leading lines, axes of symmetry, triangles, and sky regions. Extensive experimental results demonstrate that the proposed algorithm classifies composition classes reliably and detects composition elements accurately.

Original languageEnglish
Pages (from-to)91-105
Number of pages15
JournalJournal of Visual Communication and Image Representation
Volume55
DOIs
Publication statusPublished - 2018 Aug 1

Fingerprint

Chemical analysis
Neural networks

Keywords

  • Composition element detection
  • Geometric element detection
  • Image classification
  • Photographic composition
  • Rule of thirds
  • Sky detection

ASJC Scopus subject areas

  • Signal Processing
  • Media Technology
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Photographic composition classification and dominant geometric element detection for outdoor scenes. / Lee, Jun Tae; Kim, Han Ul; Lee, Chul; Kim, Chang-Su.

In: Journal of Visual Communication and Image Representation, Vol. 55, 01.08.2018, p. 91-105.

Research output: Contribution to journalArticle

@article{b9c7fd81b7834c9a97ed626ec6847850,
title = "Photographic composition classification and dominant geometric element detection for outdoor scenes",
abstract = "Despite the practical importance of photographic composition for improving or assessing the aesthetical quality of photographs, only a few simple composition rules have been considered for its classification. In this work, we propose novel techniques to classify photographic composition rules of outdoor scenes and detect dominant geometric elements, called composition elements, for each composition class. Specifically, we first categorize composition rules of outdoor photographs into nine classes: RoT, center, horizontal, symmetric, diagonal, curved, vertical, triangle, and pattern. Then, we develop a photographic composition classification algorithm using a convolutional neural network (CNN). To train the CNN, we construct a photographic composition database, which is publicly available. Finally, for each composition class, we propose an effective scheme to locate composition elements, i.e., bounding boxes for main subjects, leading lines, axes of symmetry, triangles, and sky regions. Extensive experimental results demonstrate that the proposed algorithm classifies composition classes reliably and detects composition elements accurately.",
keywords = "Composition element detection, Geometric element detection, Image classification, Photographic composition, Rule of thirds, Sky detection",
author = "Lee, {Jun Tae} and Kim, {Han Ul} and Chul Lee and Chang-Su Kim",
year = "2018",
month = "8",
day = "1",
doi = "10.1016/j.jvcir.2018.05.018",
language = "English",
volume = "55",
pages = "91--105",
journal = "Journal of Visual Communication and Image Representation",
issn = "1047-3203",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Photographic composition classification and dominant geometric element detection for outdoor scenes

AU - Lee, Jun Tae

AU - Kim, Han Ul

AU - Lee, Chul

AU - Kim, Chang-Su

PY - 2018/8/1

Y1 - 2018/8/1

N2 - Despite the practical importance of photographic composition for improving or assessing the aesthetical quality of photographs, only a few simple composition rules have been considered for its classification. In this work, we propose novel techniques to classify photographic composition rules of outdoor scenes and detect dominant geometric elements, called composition elements, for each composition class. Specifically, we first categorize composition rules of outdoor photographs into nine classes: RoT, center, horizontal, symmetric, diagonal, curved, vertical, triangle, and pattern. Then, we develop a photographic composition classification algorithm using a convolutional neural network (CNN). To train the CNN, we construct a photographic composition database, which is publicly available. Finally, for each composition class, we propose an effective scheme to locate composition elements, i.e., bounding boxes for main subjects, leading lines, axes of symmetry, triangles, and sky regions. Extensive experimental results demonstrate that the proposed algorithm classifies composition classes reliably and detects composition elements accurately.

AB - Despite the practical importance of photographic composition for improving or assessing the aesthetical quality of photographs, only a few simple composition rules have been considered for its classification. In this work, we propose novel techniques to classify photographic composition rules of outdoor scenes and detect dominant geometric elements, called composition elements, for each composition class. Specifically, we first categorize composition rules of outdoor photographs into nine classes: RoT, center, horizontal, symmetric, diagonal, curved, vertical, triangle, and pattern. Then, we develop a photographic composition classification algorithm using a convolutional neural network (CNN). To train the CNN, we construct a photographic composition database, which is publicly available. Finally, for each composition class, we propose an effective scheme to locate composition elements, i.e., bounding boxes for main subjects, leading lines, axes of symmetry, triangles, and sky regions. Extensive experimental results demonstrate that the proposed algorithm classifies composition classes reliably and detects composition elements accurately.

KW - Composition element detection

KW - Geometric element detection

KW - Image classification

KW - Photographic composition

KW - Rule of thirds

KW - Sky detection

UR - http://www.scopus.com/inward/record.url?scp=85048460149&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048460149&partnerID=8YFLogxK

U2 - 10.1016/j.jvcir.2018.05.018

DO - 10.1016/j.jvcir.2018.05.018

M3 - Article

VL - 55

SP - 91

EP - 105

JO - Journal of Visual Communication and Image Representation

JF - Journal of Visual Communication and Image Representation

SN - 1047-3203

ER -