Show/Hide Menu
Hide/Show Apps
Logout
Türkçe
Türkçe
Search
Search
Login
Login
OpenMETU
OpenMETU
About
About
Open Science Policy
Open Science Policy
Communities & Collections
Communities & Collections
Help
Help
Frequently Asked Questions
Frequently Asked Questions
Guides
Guides
Thesis submission
Thesis submission
MS without thesis term project submission
MS without thesis term project submission
Publication submission with DOI
Publication submission with DOI
Publication submission
Publication submission
Supporting Information
Supporting Information
General Information
General Information
Copyright, Embargo and License
Copyright, Embargo and License
Contact us
Contact us
Who draw this? Caricaturist recognition using convolutional neural networks Bunu kim çizdi? Evrişimsel sinir aǧlari ile karikatürist tanima
Date
2018-05-05
Author
Hicsonmez, Samet
Samet, Nermin
Akbaş, Emre
Duygulu, Pinar
Metadata
Show full item record
This work is licensed under a
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
.
Item Usage Stats
112
views
0
downloads
Cite This
Caricature is the art of expressing an event that will be described in many pages in writing, visually with a small drawing. The details of the drawing, the style, and the objects used in the drawing, which make up the visual structure, are very important in conveying the event or thought. Therefore, different caricaturists express similar events (eg. social or political messages) using different details and objects according to their own style and imagination worlds. Determining which caricature belongs to which caricaturist will help us to organize large collections, determine originality, and make caricature suggestions based on subject/style. In this study, a total of 4212 caricature from 10 different Turkish caricaturists were collected from the Internet and a new caricature data set was created. Using this dataset, both the existing Convolutional Neural Network models and the proposed new network, ComicNet, are trained and their performances are compared. Experiments show that ComicNet is the most successful model with an accuracy of 94.68%.
Subject Keywords
Comic and Caricaturist Recognition
,
ComicNet
,
Convolutional Neural Networks
,
Deep Learning
URI
https://hdl.handle.net/11511/40053
DOI
https://doi.org/10.1109/siu.2018.8404770
Collections
Department of Computer Engineering, Conference / Seminar
Suggestions
OpenMETU
Core
Graffiti and urban space in Istanbul
Sarıyıldız, Hatice Özlem; Sargın, Güven Arif; Department of Media and Cultural Studies (2007)
The aim of this study is to uncover and discuss the spaces appropriated by graffiti writers and to reveal out the possible resistances involved in the act throughout the writers’ motivations, characteristics, spaces they produce and all over process they are entering into together with the specifications of graffiti in Turkey. It demands to unfold the possibilities sheltered in everyday practices looking through graffiti and subsequently revealing out possibilities in graffiti looking through everyday life....
A Study on matched-piece lapping process for production of precision machine elements
Vayghannezhad, Salar; Dölen, Melik; Department of Mechanical Engineering (2014)
The process of lapping has been long regarded as an art. Since the quality of lapping differs from one operator to another, significantly and the results are often time inconsistent. The material removal rate, surface finish and geometry all depends on proper control of lapping parameters (e.g. lapping speed, lapping pressure, lapping material and size and type, workpiece material and hardness, etc.). Furthermore, to attain the desired outcomes, it is imperative to select proper values for lapping process c...
Mimarlıkta Yaratıcı Haritalama: “Yaşanmış Mekân”ı Görünür Kılmak Üzerine
Aral, Hacer Ela (2018-02-01)
İki boyutlu haritaların üç boyuttaki yaşamı ve deneyimleri aktarabilmesi için bürünmesi gereken anlatım zenginliği, “yaratıcı haritalama” kavramı üzerinden ele alınıyor. Yazar, “yaşanmış mekân”ı görselleştiren bu tekniğin sadece bir gösterim yöntemi değil, farklılaşan bir tasarım yaklaşımının aracı ve parçası olduğunu belirtiyor.
The cognitive aspects of model-making in architectural design
Gürsoy, Benay; Özkar, Mine; Department of Architecture (2010)
Considerable research has been done by various scholars to assess the significance of sketching in the early stages of the design process. However, sketching in design studies usually corresponds to drawing and the extensive research on the cognitive aspects of sketching does not always include three-dimensional sketching through physical and digital models produced in the early phases of design process. The aim of the presented research is to identify some characteristics of model-making that make it effec...
Criticism of contemporary art initiatives in arts from feminist standpoint theory: the case of Ankara / Turkey.
Akbıyık, Merv; Ecevit, Mehmet Cihan; Department of Gender and Women's Studies (2020)
The purpose of this thesis is based on to claim that in paradigmatic problematization of art, contemporary art and specificities of subjectivities of contemporary art initiatives which is in contemporary art should be understood on the basis of knowledge and politics. The approach to contemporary art initiatives through Feminist Standpoint Theory will also bring the understanding of contemporary art that is critical to capitalist understanding of contemporary art. The institutionalized capitalist contempora...
Citation Formats
IEEE
ACM
APA
CHICAGO
MLA
BibTeX
S. Hicsonmez, N. Samet, E. Akbaş, and P. Duygulu, “Who draw this? Caricaturist recognition using convolutional neural networks Bunu kim çizdi? Evrişimsel sinir aǧlari ile karikatürist tanima,” 2018, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/40053.