CIVILICA We Respect the Science
(ناشر تخصصی کنفرانسهای کشور / شماره مجوز انتشارات از وزارت فرهنگ و ارشاد اسلامی: ۸۹۷۱)

Edge Detection with ResNet

عنوان مقاله: Edge Detection with ResNet
شناسه ملی مقاله: CMTS03_003
منتشر شده در سومین کنفرانس بین المللی فناوری های نوین در علوم در سال 1402
مشخصات نویسندگان مقاله:

Z. Dorrani - Department of Electrical Engineering, Payame Noor University (PNU), Tehran, Iran
H Farsi - Department of Electrical and Computer Engineering, University of Birjand, Birjand, Iran
S Mohamadzadeh - Department of Electrical and Computer Engineering, University of Birjand, Birjand, Iran

خلاصه مقاله:
Edge detection in computer vision is essential for higher-level vision tasks such as shape matching, visual salience, image segmentation, and object recognition. The methods based on deep learning are among the methods that have been proposed to increase accuracy, which is highly popular. In this paper, a method for edge detection with one of the deep architectures that have high accuracy is proposed. The results show that the F-measure for the proposed method with ResNet architecture has improved compared to other compared methods.

کلمات کلیدی:
convolutional deep learning, edge detection, ResNet.

صفحه اختصاصی مقاله و دریافت فایل کامل: https://civilica.com/doc/1753781/