Show simple item record

dc.contributor.advisorNasution, Mahyuddin K. M
dc.contributor.advisorSitompul, Opim Salim
dc.contributor.authorTanjung, Mahardika Abdi Prawira
dc.date.accessioned2021-09-14T02:25:01Z
dc.date.available2021-09-14T02:25:01Z
dc.date.issued2017
dc.identifier.urihttp://repositori.usu.ac.id/handle/123456789/43203
dc.description.abstractThe human eye can directly distinguish objects from images. Such as animals, plants or inanimate objects that have been directly recognized by humans. However, the computer does not have the capability of such a human eye that can instantly recognize objects in the image. Because computers only recognize binary numbers 0 and 1. Bag of visual words is a method to present the image based on local features, where an image can be taken its characteristics, so as to distinguish the objects in the image. In the process, bag of visual words has the stages of determining the characteristics of the interest points. In this study, the determination of the interest point is modified using the speed-up robust feature with histogram of oriented gradients. Performance of these modifications generate consistent accuracy by using 5-scale detection of interest points.en_US
dc.description.abstractMata manusia dapat secara langsung membedakan objek-objek pada citra. Seperti hewan, tumbuhan ataupun benda-benda mati yang telah dikenali secara langsung oleh manusia. Namun, komputer tidak memiliki kemampuan seperti mata manusia yang dapat langsung mengenali objek pada citra tersebut. Karena komputer hanya mengenali bilangan biner yaitu 0 dan 1. Bag of visual words merupakan suatu metode untuk mempresentasikan citra berdasarkan fitur lokal, dimana sebuah citra dapat diambil karakteristiknya, sehingga dapat membedakan objek-objek pada citra. Dalam prosesnya, Bag of visual words memiliki tahapan penentuan karakteristik yaitu interest point. Dalam penelitian ini, penentuan interest point dimodifikasi menggunakan speed-up robust feature dengan histogram of oriented gradients. Kinerja modifikasi tersebut menghasilkan akurasi yang konsisten dengan menggunakan 5 skala pendeteksian interest point.en_US
dc.language.isoiden_US
dc.publisherUniversitas Sumatera Utaraen_US
dc.subjectCitraen_US
dc.subjectBag of Visual Wordsen_US
dc.subjectInterest Pointen_US
dc.titleModifikasi Speed-Up Robust Feature (SURF) dengan Histogram of Oriented Gradient (HOG) pada Klasifikasi Citra Bluren_US
dc.typeThesisen_US
dc.identifier.nimNIM147038071
dc.description.pages69 Halamanen_US
dc.description.typeTesis Magisteren_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record