Yazar "Baştan, Muhammet" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • Küçük Resim Yok
    Öğe
    Camera aided navigation for the visually impaired
    (Institute of Electrical and Electronics Engineers Inc., 2016) Isik, Kadir; Taskin, Erol; Unal, M. Fatih; Yilmaz, Ozgur; Baştan, Muhammet
    One of the most challenging problems a visually impaired person experiences is outdoor navigation. We present an Android application to be used by the visually impaired for GPS and compass based navigation, and a camera based visual navigation for accurate guidance which uses visual matching on previously saved visual landmarks. The system has an ergonomic and intuitive touch based user interface suitable for visually impaired. © 2017 Elsevier B.V., All rights reserved.
  • Küçük Resim Yok
    Öğe
    Mobile image search using multi-query images
    (Institute of Electrical and Electronics Engineers Inc., 2015) Çalışır, Fatih; Baştan, Muhammet; Güdükbay, Uğur; Ulusoy, Özgür
    Recent advances in mobile device technology have turned the mobile phones into powerfull devices with high resolution cameras and fast processing capabilities. Having more user interaction potential compared to regular PCs, mobile devices with cameras can enable richer content-based object image queries: the user can capture multiple images of the query object from different viewing angles and at different scales, thereby providing much more information about the object to improve the retrieval accuracy. The goal of this paper is to improve the mobile image retrieval performance using multiple query images. To this end, we use the well-known bag-of-visual-words approach to represent the images, and employ early and late fusion strategies to utilize the information in multiple query images. With extensive experiments on an object image dataset with a single object per image, we show that multi-image queries result in higher average precision performance than single image queries. © 2021 Elsevier B.V., All rights reserved.
  • Küçük Resim Yok
    Öğe
    Mobile Reader: Turkish scene text reader for the visually impaired
    (Institute of Electrical and Electronics Engineers Inc., 2016) Kandemir, Hilal; Canturk, Busra; Baştan, Muhammet
    Reading text is one of the crucial needs of the visually impaired people. In this work, we developed a mobile system (Mobile Reader) that can read aloud Turkish scene and book text. Images acquired from the camera are processed in realtime to detect text regions, recognize the text and synthesize speech in Turkish. A fast gradient-based text detection algorithm is employed to enable real-time operation, and character recognition is achieved via the open source Tesseract OCR engine. The performance of the system (running time and accuracy) is measured on a scene text image dataset on a mobile device. © 2017 Elsevier B.V., All rights reserved.
  • Küçük Resim Yok
    Öğe
    Turkish OCR on mobile and scanned document images
    (Institute of Electrical and Electronics Engineers Inc., 2015) Karasu, Kurtuluş; Baştan, Muhammet
    Optical character recognition (OCR) systems have been widely used to convert documents into digital form. There are lots of both commercial and open source OCR systems available, but a benchmark on Turkish OCR is nonexistent. In this work, we first prepared two publicly available datasets for Turkish OCR, consisting of scanned document images and mobile camera captured document images. Then, we evaluated the Turkish OCR performance of three popular open source OCR systems (Tesseract, CuneiForm, GOCR) on the datasets. Tesseract outperformed the other two on both datasets. © 2021 Elsevier B.V., All rights reserved.