Virtual portraitist

An intelligent tool for taking well-posed selfies

Chuan Shen Hu, Yi Tsung Hsieh, Hsiao Wei Lin, Mei-Chen Yeh

Research output: Contribution to journalArticle

Abstract

Smart photography carries the promise of quality improvement and functionality extension in making aesthetically appealing pictures. In this article, we focus on self-portrait photographs and introduce newmethods that guide a user in how to best pose while taking a selfie. While most of the current solutions use a post processing procedure to beautify a picture, the developed tool enables a novel function of recommending a good look before the photo is captured. Given an input face image, the tool automatically estimates the pose-based aesthetic score, finds the most attractive angle of the face, and suggests how the pose should be adjusted. The recommendation results are determined adaptively to the appearance and initial pose of the input face. We apply a data mining approach to find distinctive, frequent itemsets and association rules from online profile pictures, upon which the aesthetic estimation and pose recommendation methods are developed. A simulated and a real image set are used for experimental evaluation. The results show the proposed aesthetic estimation method can effectively select user-favorable photos. Moreover, the recommendation performance for the vertical adjustment is moderately related to the degree of conformity among the professional photographers' recommendations. This study echoes the trend of instant photo sharing, in which a user takes a picture and then immediately shares it on a social network without engaging in tedious editing.

Original languageEnglish
Article number10
JournalACM Transactions on Multimedia Computing, Communications and Applications
Volume15
Issue number1s
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

Association rules
Photography
Data mining
Processing

Keywords

  • Computational aesthetics
  • Pose recommendation
  • Selfie
  • Smart photography

ASJC Scopus subject areas

  • Hardware and Architecture
  • Computer Networks and Communications

Cite this

Virtual portraitist : An intelligent tool for taking well-posed selfies. / Hu, Chuan Shen; Hsieh, Yi Tsung; Lin, Hsiao Wei; Yeh, Mei-Chen.

In: ACM Transactions on Multimedia Computing, Communications and Applications, Vol. 15, No. 1s, 10, 01.01.2019.

Research output: Contribution to journalArticle

@article{e1330803f3ed4f60abc2e4b90271d245,
title = "Virtual portraitist: An intelligent tool for taking well-posed selfies",
abstract = "Smart photography carries the promise of quality improvement and functionality extension in making aesthetically appealing pictures. In this article, we focus on self-portrait photographs and introduce newmethods that guide a user in how to best pose while taking a selfie. While most of the current solutions use a post processing procedure to beautify a picture, the developed tool enables a novel function of recommending a good look before the photo is captured. Given an input face image, the tool automatically estimates the pose-based aesthetic score, finds the most attractive angle of the face, and suggests how the pose should be adjusted. The recommendation results are determined adaptively to the appearance and initial pose of the input face. We apply a data mining approach to find distinctive, frequent itemsets and association rules from online profile pictures, upon which the aesthetic estimation and pose recommendation methods are developed. A simulated and a real image set are used for experimental evaluation. The results show the proposed aesthetic estimation method can effectively select user-favorable photos. Moreover, the recommendation performance for the vertical adjustment is moderately related to the degree of conformity among the professional photographers' recommendations. This study echoes the trend of instant photo sharing, in which a user takes a picture and then immediately shares it on a social network without engaging in tedious editing.",
keywords = "Computational aesthetics, Pose recommendation, Selfie, Smart photography",
author = "Hu, {Chuan Shen} and Hsieh, {Yi Tsung} and Lin, {Hsiao Wei} and Mei-Chen Yeh",
year = "2019",
month = "1",
day = "1",
doi = "10.1145/3288760",
language = "English",
volume = "15",
journal = "ACM Transactions on Multimedia Computing, Communications and Applications",
issn = "1551-6857",
publisher = "Association for Computing Machinery (ACM)",
number = "1s",

}

TY - JOUR

T1 - Virtual portraitist

T2 - An intelligent tool for taking well-posed selfies

AU - Hu, Chuan Shen

AU - Hsieh, Yi Tsung

AU - Lin, Hsiao Wei

AU - Yeh, Mei-Chen

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Smart photography carries the promise of quality improvement and functionality extension in making aesthetically appealing pictures. In this article, we focus on self-portrait photographs and introduce newmethods that guide a user in how to best pose while taking a selfie. While most of the current solutions use a post processing procedure to beautify a picture, the developed tool enables a novel function of recommending a good look before the photo is captured. Given an input face image, the tool automatically estimates the pose-based aesthetic score, finds the most attractive angle of the face, and suggests how the pose should be adjusted. The recommendation results are determined adaptively to the appearance and initial pose of the input face. We apply a data mining approach to find distinctive, frequent itemsets and association rules from online profile pictures, upon which the aesthetic estimation and pose recommendation methods are developed. A simulated and a real image set are used for experimental evaluation. The results show the proposed aesthetic estimation method can effectively select user-favorable photos. Moreover, the recommendation performance for the vertical adjustment is moderately related to the degree of conformity among the professional photographers' recommendations. This study echoes the trend of instant photo sharing, in which a user takes a picture and then immediately shares it on a social network without engaging in tedious editing.

AB - Smart photography carries the promise of quality improvement and functionality extension in making aesthetically appealing pictures. In this article, we focus on self-portrait photographs and introduce newmethods that guide a user in how to best pose while taking a selfie. While most of the current solutions use a post processing procedure to beautify a picture, the developed tool enables a novel function of recommending a good look before the photo is captured. Given an input face image, the tool automatically estimates the pose-based aesthetic score, finds the most attractive angle of the face, and suggests how the pose should be adjusted. The recommendation results are determined adaptively to the appearance and initial pose of the input face. We apply a data mining approach to find distinctive, frequent itemsets and association rules from online profile pictures, upon which the aesthetic estimation and pose recommendation methods are developed. A simulated and a real image set are used for experimental evaluation. The results show the proposed aesthetic estimation method can effectively select user-favorable photos. Moreover, the recommendation performance for the vertical adjustment is moderately related to the degree of conformity among the professional photographers' recommendations. This study echoes the trend of instant photo sharing, in which a user takes a picture and then immediately shares it on a social network without engaging in tedious editing.

KW - Computational aesthetics

KW - Pose recommendation

KW - Selfie

KW - Smart photography

UR - http://www.scopus.com/inward/record.url?scp=85061174524&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061174524&partnerID=8YFLogxK

U2 - 10.1145/3288760

DO - 10.1145/3288760

M3 - Article

VL - 15

JO - ACM Transactions on Multimedia Computing, Communications and Applications

JF - ACM Transactions on Multimedia Computing, Communications and Applications

SN - 1551-6857

IS - 1s

M1 - 10

ER -