Discovering triangles in portraits for supporting photographic creation

Siqiong He, Zihan Zhou, Farshid Farhat, James Wang

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Incorporating the concept of triangles in photos is an effective composition technique used by professional photographers for making pictures more interesting or dynamic. Information on the locations of the embedded triangles is valuable for comparing the composition of portrait photos, which can be further leveraged by a retrieval system or used by the photographers. This paper presents a system to automatically detect embedded triangles in portrait photos. The problem is challenging because the triangles used in portraits are often not clearly defined by straight lines. The system first extracts a set of filtered line segments as candidate triangle sides, and then utilizes a modified random sample consensus algorithm to fit triangles onto the set of line segments. We propose two metrics, Continuity Ratio and Total Ratio, to evaluate the fitted triangles; those with high fitting scores are taken as detected triangles. Experimental results have demonstrated high accuracy in locating preeminent triangles in portraits without dependence on the camera or lens parameters. To demonstrate the benefits of our method to digital photography, we have developed two novel applications that aim to help users compose high-quality photos. In the first application, we develop a human position and pose recommendation system by retrieving and presenting compositionally similar photos taken by competent photographers. The second application is a novel sketch-based triangle retrieval system which searches for photos containing a specific triangular configuration. User studies have been conducted to validate the effectiveness of these approaches.

Original languageEnglish (US)
Article number8010436
Pages (from-to)496-508
Number of pages13
JournalIEEE Transactions on Multimedia
Volume20
Issue number2
DOIs
StatePublished - Jan 1 2018

Fingerprint

Recommender systems
Photography
Chemical analysis
Lenses
Cameras

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Media Technology
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

@article{a71a29ad7a7b4898a0e0a77ce9887854,
title = "Discovering triangles in portraits for supporting photographic creation",
abstract = "Incorporating the concept of triangles in photos is an effective composition technique used by professional photographers for making pictures more interesting or dynamic. Information on the locations of the embedded triangles is valuable for comparing the composition of portrait photos, which can be further leveraged by a retrieval system or used by the photographers. This paper presents a system to automatically detect embedded triangles in portrait photos. The problem is challenging because the triangles used in portraits are often not clearly defined by straight lines. The system first extracts a set of filtered line segments as candidate triangle sides, and then utilizes a modified random sample consensus algorithm to fit triangles onto the set of line segments. We propose two metrics, Continuity Ratio and Total Ratio, to evaluate the fitted triangles; those with high fitting scores are taken as detected triangles. Experimental results have demonstrated high accuracy in locating preeminent triangles in portraits without dependence on the camera or lens parameters. To demonstrate the benefits of our method to digital photography, we have developed two novel applications that aim to help users compose high-quality photos. In the first application, we develop a human position and pose recommendation system by retrieving and presenting compositionally similar photos taken by competent photographers. The second application is a novel sketch-based triangle retrieval system which searches for photos containing a specific triangular configuration. User studies have been conducted to validate the effectiveness of these approaches.",
author = "Siqiong He and Zihan Zhou and Farshid Farhat and James Wang",
year = "2018",
month = "1",
day = "1",
doi = "10.1109/TMM.2017.2740026",
language = "English (US)",
volume = "20",
pages = "496--508",
journal = "IEEE Transactions on Multimedia",
issn = "1520-9210",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

Discovering triangles in portraits for supporting photographic creation. / He, Siqiong; Zhou, Zihan; Farhat, Farshid; Wang, James.

In: IEEE Transactions on Multimedia, Vol. 20, No. 2, 8010436, 01.01.2018, p. 496-508.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Discovering triangles in portraits for supporting photographic creation

AU - He, Siqiong

AU - Zhou, Zihan

AU - Farhat, Farshid

AU - Wang, James

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Incorporating the concept of triangles in photos is an effective composition technique used by professional photographers for making pictures more interesting or dynamic. Information on the locations of the embedded triangles is valuable for comparing the composition of portrait photos, which can be further leveraged by a retrieval system or used by the photographers. This paper presents a system to automatically detect embedded triangles in portrait photos. The problem is challenging because the triangles used in portraits are often not clearly defined by straight lines. The system first extracts a set of filtered line segments as candidate triangle sides, and then utilizes a modified random sample consensus algorithm to fit triangles onto the set of line segments. We propose two metrics, Continuity Ratio and Total Ratio, to evaluate the fitted triangles; those with high fitting scores are taken as detected triangles. Experimental results have demonstrated high accuracy in locating preeminent triangles in portraits without dependence on the camera or lens parameters. To demonstrate the benefits of our method to digital photography, we have developed two novel applications that aim to help users compose high-quality photos. In the first application, we develop a human position and pose recommendation system by retrieving and presenting compositionally similar photos taken by competent photographers. The second application is a novel sketch-based triangle retrieval system which searches for photos containing a specific triangular configuration. User studies have been conducted to validate the effectiveness of these approaches.

AB - Incorporating the concept of triangles in photos is an effective composition technique used by professional photographers for making pictures more interesting or dynamic. Information on the locations of the embedded triangles is valuable for comparing the composition of portrait photos, which can be further leveraged by a retrieval system or used by the photographers. This paper presents a system to automatically detect embedded triangles in portrait photos. The problem is challenging because the triangles used in portraits are often not clearly defined by straight lines. The system first extracts a set of filtered line segments as candidate triangle sides, and then utilizes a modified random sample consensus algorithm to fit triangles onto the set of line segments. We propose two metrics, Continuity Ratio and Total Ratio, to evaluate the fitted triangles; those with high fitting scores are taken as detected triangles. Experimental results have demonstrated high accuracy in locating preeminent triangles in portraits without dependence on the camera or lens parameters. To demonstrate the benefits of our method to digital photography, we have developed two novel applications that aim to help users compose high-quality photos. In the first application, we develop a human position and pose recommendation system by retrieving and presenting compositionally similar photos taken by competent photographers. The second application is a novel sketch-based triangle retrieval system which searches for photos containing a specific triangular configuration. User studies have been conducted to validate the effectiveness of these approaches.

UR - http://www.scopus.com/inward/record.url?scp=85028451238&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028451238&partnerID=8YFLogxK

U2 - 10.1109/TMM.2017.2740026

DO - 10.1109/TMM.2017.2740026

M3 - Article

AN - SCOPUS:85028451238

VL - 20

SP - 496

EP - 508

JO - IEEE Transactions on Multimedia

JF - IEEE Transactions on Multimedia

SN - 1520-9210

IS - 2

M1 - 8010436

ER -