An optimized scale-invariant feature transform (SIFT)‎ using chamfer distance in image matching

العناوين الأخرى

تحسين خوارزمية مقياس المعادلة الثابت (SIFT)‎ باستخدام مقياس شامفر في مطابقة الصور

مقدم أطروحة جامعية

al-Sharbaji, Tamara Abd al-Qadir

مشرف أطروحة جامعية

al-Kabnah, Khalid Abd al-Hafiz

الجامعة

جامعة عمان العربية

الكلية

كلية العلوم الحاسوبية و المعلوماتية

القسم الأكاديمي

قسم علم الحاسوب

دولة الجامعة

الأردن

الدرجة العلمية

ماجستير

تاريخ الدرجة العلمية

2018

الملخص الإنجليزي

Computer vision is one of the most important elements used in the field of computer science so that it serves several fields, including the matching of images.

Matching multiple images is a main step in computer vision.

This can be reached by tracking the main points common to these images, and can determine the match between them.

Image matching among multiple images is a core and vital step in the field of computer vision.

This can be achieved by tracking correspondence over key points in an image and then matching among them can be identified.

ScaleInvariant Feature Transform (SIFT) is an image matching algorithm used to match objects of two images by extracting the feature points of target objects in each image.

SIFT suffers from long processing time due to embedded calculations which reduces the overall speed of the technique.

This research aims to enhance SIFT processing time by using Chamfer Distance Algorithm to find the distance between image descriptors instead of using Euclidian Distance Algorithm used in SIFT.

Chamfer Distance Algorithm requires less computational time than Euclidian Distance Algorithm because it selects the shortest path between any two points when the distance is computed.

To validate and evaluate the enhanced algorithm, A data set with (412) images including: (100) images with different degrees of rotation, (100) images with different intensity levels, (112) images with different measurement levels and (100) distorted images to different degrees were used; these images were applied according to four different criteria including (the number of key point in the original image, the number of key point in the testing image, the matching rate, the processing time).

The simulation results showed that the enhanced SIFT outperforms the ORB and the original SIFT in term of the processing time, and it reduces the overall processing time of the classical SIFT by (41%).

التخصصات الرئيسية

تكنولوجيا المعلومات وعلم الحاسوب

الموضوعات

• الخوارزميات
• جودة الصورة

عدد الصفحات

149

قائمة المحتويات

• APA
• MLA
• AMA

لغة النص

الإنجليزية

نوع البيانات

رسائل جامعية

رقم السجل

BIM-932937