Edge detection of aerial images using artificial bee colony algorithm
Yükleniyor...
Dosyalar
Tarih
2022-06-30
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Kırgızistan Türkiye Manas Üniversitesi
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
Edge detection techniques are the one of the best popular and significant implementation areas of the image processing. Moreover, image processing is very widely used in so many fields. Therefore, lots of methods are used in the development and the developed studies provide a variety of solutions to problems of computer vision systems. In many studies, metaheuristic algorithms have been used for obtaining better results. In this paper, aerial images are used for edge information extraction by using Artificial Bee Colony (ABC) Optimization Algorithm. Procedures were performed on gray scale aerial images which are taken from RADIUS/DARPA-IU Fort Hood database. Initially bee colony size was specified according to sizes of images. Then a threshold value was set for each image, which related with images’ standard deviation of gray scale values. After the bees were distributed, fitness values and probability values were computed according to gray scale value. While appropriate pixels were specified, the other ones were being abandoned and labeled as banned pixels therefore bees never located on these pixels again. So the edges were found without the need to examine all pixels in the image. Our improved method’s results are compared with other results found in the literature according to detection error and similarity calculations’. All the experimental results show that ABC can be used for obtaining edge information from images.
Açıklama
Anahtar Kelimeler
Image processing, Edge detection, Artificial bee colony optimization, Aerial images
Kaynak
MANAS Journal of Engineering
WoS Q Değeri
Scopus Q Değeri
Cilt
10
Sayı
1
Künye
Yelmenoğlu, E. D. & Akhan Baykan, N. (2022). Edge detection of aerial images using artificial bee colony algorithm. MANAS Journal of Engineering, 10(1), 73-80. doi:10.51354/mjen.1053446
