Loading...
Please wait, while we are loading the content...
Similar Documents
DRAW : Deep networks for Recognizing styles of Artists Who illustrate children ’ s books
| Content Provider | Semantic Scholar |
|---|---|
| Author | Inal, Ayşe Seza Sendak, Maurice Mckee, David Delioglu, Mustafa Gliori, Debi Polacco, Patricia Butschkow, Ralf Carle, Eric Curto, Rosa María Hill, Eric R. Deliorman, Serap Cartwright, Stephen Henkes, Kevin Ross, T. P. |
| Copyright Year | 2017 |
| Abstract | is paper is motivated from a young boy’s capability to recognize an illustrator’s style in a totally dierent context. In the book ”We are All Born Free” [1], composed of selected rights from the Universal Declaration of Human Rights interpreted by dierent illustrators, the boywas surprised to see a picture similar to the ones in the ”Winnie the Witch” series drawn by Korky Paul (Figure 1). e style was noticeable in other characters of the same illustrator in dierent books as well. e capability of a child to easily spot the style was shown to be valid for other illustrators such as Axel Scheer and Debi Gliori. e boy’s enthusiasm let us to start the journey to explore the capabilities of machines to recognize the style of illustrators. We collected pages from children’s books to construct a new illustrations dataset consisting of about 6500 pages from 24 artists. We exploited deep networks for categorizing illustrators and with around 94% classication performance our method over-performed Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for prot or commercial advantage and that copies bear this notice and the full citation on the rst page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permied. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specic permission and/or a fee. Request permissions from permissions@acm.org. ICMR ’17, June 6–9, 2017, Bucharest, Romania © 2017 ACM. ACM ISBN 978-1-4503-4701-3/17/06. . .$15.00 DOI: hp://dx.doi.org/10.1145/3078971.3078982 the traditional methods bymore than 10%. Going beyond categorization we explored transferring style. e classication performance on the transferred images has shown the ability of our system to capture the style. Furthermore, we discovered representative illustrations and discriminative stylistic elements. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://users.metu.edu.tr/snermin/papers/icmr2017.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
