Full Text:   <157>

CLC number: 

On-line Access: 2020-01-18

Received: 2019-07-22

Revision Accepted: 2019-12-08

Crosschecked: 0000-00-00

Cited: 0

Clicked: 199

Citations:  Bibtex RefMan EndNote GB/T7714

-   Go to

Article info.
Open peer comments

Frontiers of Information Technology & Electronic Engineering  1998 Vol.-1 No.-1 P.

10.1631/FITEE.1900367


Automatic synthesis of advertising images according to a specified style


Author(s):  Wei-tao YOU, Hao JIANG, Zhi-yuan YANG, Chang-yuan YANG, Ling-yun SUN1

Affiliation(s):  Key Laboratory of Design Intelligence and Digital Creativity of Zhejiang Province, Hangzhou 310027, China; more

Corresponding email(s):   weitao_you@zju.edu.cn, jiang_hao@zju.edu.cn, youngs@zju.edu.cn, changyuan.yangcy@alibaba-inc.com

Key Words:  Image dataset, Data-driven method, Automatic ad synthesis


Wei-tao YOU, Hao JIANG, Zhi-yuan YANG, Chang-yuan YANG, Ling-yun SUN1. Automatic synthesis of advertising images according to a specified style[J]. Frontiers of Information Technology & Electronic Engineering, 1998, -1(-1): .

@article{title="Automatic synthesis of advertising images according to a specified style",
author="Wei-tao YOU, Hao JIANG, Zhi-yuan YANG, Chang-yuan YANG, Ling-yun SUN1",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="-1",
number="-1",
pages="",
year="1998",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.1900367"
}

%0 Journal Article
%T Automatic synthesis of advertising images according to a specified style
%A Wei-tao YOU
%A Hao JIANG
%A Zhi-yuan YANG
%A Chang-yuan YANG
%A Ling-yun SUN1
%J Frontiers of Information Technology & Electronic Engineering
%V -1
%N -1
%P
%@ 2095-9184
%D 1998
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.1900367

TY - JOUR
T1 - Automatic synthesis of advertising images according to a specified style
A1 - Wei-tao YOU
A1 - Hao JIANG
A1 - Zhi-yuan YANG
A1 - Chang-yuan YANG
A1 - Ling-yun SUN1
J0 - Frontiers of Information Technology & Electronic Engineering
VL - -1
IS - -1
SP -
EP -
%@ 2095-9184
Y1 - 1998
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.1900367


Abstract: 
Images are widely used by companies to advertise their products and promote awareness of their brands. The automatic synthesis of advertising images is challenging because the advertising message must be clearly conveyed while also complying with the style required for the product, brand, or target audience. In this study, we propose a data-driven method to capture individual design attributes and the relationships between elements in advertising images with the aim of automatically synthesizing the input of elements into an advertising image according to a specified style. To achieve this multi-format ad design, we created a dataset that contained 13,280 advertising images with rich annotations that encompassed the outlines and colors of the elements, in addition to the classes and goals of the ads. Using our probabilistic models, users guided the style of synthesized ads via additional constraints (e.g., context-based keywords). We applied our method to a variety of design tasks, and the results were evaluated in several perceptual studies, which showed that our method improved users’ satisfaction by 4.3% compared to designs generated by nonprofessional students, and 21.1% and 31.2% more users preferred the coloring results of our designs to those generated by other two models.

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Please provide your name, email address and a comment





Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - Journal of Zhejiang University-SCIENCE