Video compression enhancement based on speeded Up robust features (SURF)‎ algorithm and scene segmentation

العناوين الأخرى

تحسين ضغط الفيديو بالاعتماد على خوارزمية السيرف و تقسيم المشاهد

مقدم أطروحة جامعية

al-Shuwayki, Jumanah Mufid M.

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

2019

الملخص الإنجليزي

Video is one of the most important sources of information, where it constitutes a high rate of information content that is viewed daily on social media and other sites on the internet.

Compared to other sources of information such as images, texts and audio clips, video combines these three sources into one unit, therefore videos require more storage space than other sources since it contains a large number of images and audio tracks, which contributes to the slow transmission through the Internet.

Therefore, video streaming became a focal research to find methods for reducing the size of the video and accelerate its transmission, which is now known as video compression algorithms.

These methods represent the original data using fewer bits by eliminating repetitive information while ensuring that the quality of the data source is not compromised (objectively and subjectively) so that it can result in minor distortion.

This thesis proposes a new video compression scheme by adopting the concepts of video segmentation to scenes using image matching as master schema elements.

It is a common knowledge that the video consists of a series of successive images also known as frames, so we can first use video segmentation concept to segment the video into a group of images, then divide the collection of these images into a number of scenes by applying image matching using SURF algorithm, after that eventually each scene is compressed separately and the final step is to compress all compressed scenes combined.

The main idea of this thesis is to utilize the scientific fact that the group of similar images produces a higher compression ratio.Results obtained after testing on a series of video clips showed promising results by achieving a slight improvement in the compression ratios compared to four well-known compression algorithms used in video compression.

Results obtained when applying our proposed scheme, a 14.5% increase in comparison to Wavelet Haar algorithm, a 2.26% increase in comparison to the Block Truncation algorithm, a 13.75% increase in comparison to LZW algorithm, and an 8.58% improvement when compared with the popular JPEG compression algorithm.

الموضوع الرئيسي

تكنولوجيا المعلومات وعلم الحاسوب

الموضوعات

عدد الصفحات

75

قائمة المحتويات

Table of contents.

Abstract.

Abstract in Arabic.

Chapter One : Introduction

Chapter Two : Theoretical framework and literature review.

Chapter Three : The proposed scheme.

Chapter Four : Results and analysis.

Chapter Five : Conclusion and future work.

References.

نمط استشهاد جمعية علماء النفس الأمريكية (APA)

al-Shuwayki, Jumanah Mufid M.. (2019). Video compression enhancement based on speeded Up robust features (SURF) algorithm and scene segmentation. (Master's theses Theses and Dissertations Master). Amman Arab University, Jordan
https://search.emarefa.net/detail/BIM-932640

نمط استشهاد الجمعية الأمريكية للغات الحديثة (MLA)

al-Shuwayki, Jumanah Mufid M.. Video compression enhancement based on speeded Up robust features (SURF) algorithm and scene segmentation. (Master's theses Theses and Dissertations Master). Amman Arab University. (2019).
https://search.emarefa.net/detail/BIM-932640

نمط استشهاد الجمعية الطبية الأمريكية (AMA)

al-Shuwayki, Jumanah Mufid M.. (2019). Video compression enhancement based on speeded Up robust features (SURF) algorithm and scene segmentation. (Master's theses Theses and Dissertations Master). Amman Arab University, Jordan
https://search.emarefa.net/detail/BIM-932640

لغة النص

الإنجليزية

نوع البيانات

رسائل جامعية

رقم السجل

BIM-932640