A new algorithm for target tracking using fuzzy-edge-based feature matching and robust statistic

Behrad, Alireza; Motamedi, Seyed Ahmad; Madani, Kourosh; Esnaashari, Mehdi

doi:10.1109/icip.2002.1038089

Cited by 3 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It does not use image derivatives and noise reduction is not needed [18]. Since this method does not use image derivatives, it has less sensitivity to image noises [19].…”

Section: Related Workmentioning

confidence: 99%

Directional SUSAN image boundary detection of breast thermogram

Mahmoudzadeh

Zekri

Montazeri

et al. 2016

IET Image Processing

View full text Add to dashboard Cite

Thermography of the breast has been shown to be well suited to detect early signs of breast cancer. This study proposes a novel method for boundary detection of breast thermography images using directional SUSAN method. Among breast thermography image processing steps, breast isolation from background and from each other is an essential stage for proper detection of breast cancer. For this purpose, in this study, breast boundary is grouped into three regions depending on the region property. The algorithm of boundary detection is different for each region. Specially, for bottom breast boundary, directional SUSAN edge detector is presented that uses two rectangle masks to create a directional SUSAN gradient image with emphasis on oblique useful edges and omitting undesirable ones. Then cubic parabolic interpolation is implemented to determine a set of edge points on the boundaries. At last, an effective search algorithm is executed to correct some false points in order to extract breast boundaries accurately. The performance of the proposed approach illustrated by applying on the images of three databases. Experimental results show that this method acts effectively and confirm the accurate boundary detection. Moreover, statistical measures are calculated to indicate the remarkable capabilities of the proposed approach.

show abstract

“…It does not use image derivatives and noise reduction is not needed [18]. Since this method does not use image derivatives, it has less sensitivity to image noises [19].…”

Section: Related Workmentioning

confidence: 99%