A Comparison of methods for trademark retrieval in a large trademark dataset

Download

index.pdf

Date

2015

Author

Tuerxun, Wusiman

Metadata

Show full item record

Item Usage Stats

209
views

121
downloads

By the end of the first decades of the 21 th century, the applications for trademarks worldwide have approached an astounding number of 5 million. In Turkey alone, this number has reached the 1 million mark, and is expected by all means to keep increasing. The accelerating competition of trademark influence and uniqueness has intensified trademark piracies and infringements, and therefore resulted in a substantial burden for the patent offices, not to mention direct economic losses. To overcome this ever-increasing problem of trademark registration without compromising from service quality, and to minimize unnecessary disputes of legal ownership, organizations like patent offices gradually turn to automatized registration, employing Trademark Retrieval Systems (TRS) equipped with image processing and computer vision tools. The last two decades have seen the successful implementation of well-known content-based image processing (CBIR) techniques in several TRS systems. However, these results are falling behind as the rapid increase in trademark registration escalates the trademark retrieval problem to the next level. Developing next-generation TRS systems with well-examined and analyzed new image retrieval and object detection techniques is necessary. Yet, the lack of public large-scale trademark datasets has obstructed the progress of this research field. In this thesis, to fill this gap, we offer a large scale and challenging dataset with 1 million trademarks as a benchmark. Then, as an initial attempt to trademark retrieval research on large scale datasets, we implement and analyze a variety of global image descriptors (\eg, color, shape, texture), as well as local image descriptors (\eg, SIFT, SURF, HOG, ORG), on this dataset (called the METU trademark dataset).

Subject Keywords

Trademarks., Business names., Branding (Marketing)., Database searching., Information retrieval., Content-based image retrieval.

URI

http://etd.lib.metu.edu.tr/upload/12618595/index.pdf
https://hdl.handle.net/11511/24527

Collections

Graduate School of Natural and Applied Sciences, Thesis

Suggestions

OpenMETU
Core

Comparison of Students' Success In an International Technology Certificate Program Delialioğlu, Ömer; Çakır, Hasan (Hacettepe University, 2008) There has been a rapid increase in the number of technology certificate programs offered around the world in the last decade. While designing, developing, and implementing these programs little or no consideration is given to geographical, cultural and developmental differences between different regions of the world. This study investigates the students' success in the Cisco Certified Network Associate (CCNA) program - a unique model combining technology-supported learning with local instruction world-wide....
A migration management framework proposal for cobol/cics based mainframes Kaplan, Halil; Doğru, Ali Hikmet; Department of Computer Engineering (2010) Today, mainframes contain a considerable portion of business applications worldwide. It is estimated that the current inventory of production COBOL running on mainframes is 150 to 200 billion lines of code. Despite the efforts to change within the mainframe environment, these mainframes, nowadays, face major problems for host organizations due to a combined set of financial, business related, technical and organizational problems. Moreover, the factors like diminishing resources (COBOL programmers), lack of...
A comparative evaluation of XML repositories Ünal, Özgül; Doğaç, Asuman; Department of Information Systems (2002) Recently XML has established itself as the standard for representing data in scientific and business applications. Starting out as a standard data exchange format over the web, it has become instrumental in all kinds of applications. Almost all standardization efforts on the web today are based on XML. As a consequence, the amount of XML data being stored and processed is large and will be increasing at a very rapid rate. This has caused XML data management to become a focus of research efforts in the datab...
An interactive approach for Bi-attribute multi-item auctions Karakaya, Gülşah (2016-10-01) The advances in the technological infrastructure and in the Internet led electronic auctions to become popular. With online sites, people buy/sell inexpensive products/services through auctions. In this paper, we develop an interactive approach that provides aid to both the buyer and the bidders in a bi-attribute, multi-item auction environment. Our approach is applicable for both reverse and forward auctions. We test our approach for underlying linear preference functions of the buyer. We also adapt it as ...
FABLABS AND THEIR CONTRIBUTION TO SUSTAINABILITY IN THE CONTEXT OF SOCIO-TECHNICAL SYSTEMS Coşkun, Beyza; Aydınoğlu, Arsev Umur; Department of Science and Technology Policy Studies (2021-9) Since their first establishment at the beginning of the millennium, the number of fablabs has increased significantly worldwide. Fablabs serve many purposes, such as facilitating repairs, relocating production locally, educating on science and technology, or carrying out R&D in an open and disruptive manner. The innovation carried out in fablabs creates niche markets that are alternatives to the existing unsustainable, locked-in systems. This research explores the current state and future potential of perso...

Citation Formats

W. Tuerxun, “A Comparison of methods for trademark retrieval in a large trademark dataset,” M.S. - Master of Science, Middle East Technical University, 2015.