Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection

Permanent URI for this collectionhttps://hdl.handle.net/11147/7148

Browse

Filters

2021 - 20232

Settings

Publisher: search.filters.publisher.SpringerSubject: search.filters.subject.Image segmentation

Search Results

Now showing 1 - 2 of 2
  • Article
    Citation - WoS: 5
    Citation - Scopus: 6
    Lung Parenchyma Segmentation From Ct Images With a Fully Automatic Method
    (Springer, 2023) Mousavi Moghaddam, Reza; Aghazadeh, Nasser
    For the last three years, the world has been facing an infectious disease that primarily affects the human breathing organ. The disease has caused many deaths worldwide so far and has imposed high economic costs on all countries. Therefore, attention to computer-aided detection/diagnosis (CAD) systems to help diagnose and treat diseases related to the human respiratory system should be given more attention so that countries’ health systems can treat patients in epidemics. Considering the importance of CAD systems, we proposed a two-step automatic algorithm. In the first step, we obtain the primary boundary of the lobes in CT lung scan images with the help of some conventional image processing tools. In the second stage, we obtained a more precise boundary of the lung lobes by correcting the unusual dimples and valleys (which are sometimes caused by the presence of juxtapleural nodules). This proposed method has low implementation time. Given that a precise boundary of the pulmonary lobes is essential in the more accurate diagnosis of lung-related diseases, an attempt has been made to ensure that the final segmentation of the lung parenchyma has an acceptable score in terms of evaluation criteria so that the proposed algorithm can be used in the diagnosis procedure. © 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
  • Article
    Citation - WoS: 43
    Citation - Scopus: 47
    Semantic Segmentation of Outdoor Panoramic Images
    (Springer, 2021) Orhan, Semih; Baştanlar, Yalın
    Omnidirectional cameras are capable of providing 360. field-of-view in a single shot. This comprehensive view makes them preferable for many computer vision applications. An omnidirectional view is generally represented as a panoramic image with equirectangular projection, which suffers from distortions. Thus, standard camera approaches should be mathematically modified to be used effectively with panoramic images. In this work, we built a semantic segmentation CNN model that handles distortions in panoramic images using equirectangular convolutions. The proposed model, we call it UNet-equiconv, outperforms an equivalent CNN model with standard convolutions. To the best of our knowledge, ours is the first work on the semantic segmentation of real outdoor panoramic images. Experiment results reveal that using a distortion-aware CNN with equirectangular convolution increases the semantic segmentation performance (4% increase in mIoU). We also released a pixel-level annotated outdoor panoramic image dataset which can be used for various computer vision applications such as autonomous driving and visual localization. Source code of the project and the dataset were made available at the project page (https://github.com/semihorhan/semseg-outdoor-pano). © 2021, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.