VIDEO SEARCHING BY AUTOMATIC ANNOTATION
GROUP NUMBER : 16 - 113
INSIDEPROJECT PROPOSAL
Group Members ,
 IT 13122942 Wickramasinghe K.U
 IT 11150558 Ashangani S.K
 IT 13115494 De Silva D.W.N
 IT 13112424 Gamwara V.M
INTRODUCTION
 INSIDE
What is video
 Sequence of images to form a moving picture
Our Mission
 Friendly, simple video searching using automatic annotation to
provide an accurate result
RESEARCH PROBLEM
Available search engines only provide
Keyword searching, Audio searching, Image
searching.
Most videos are weakly labeled or have
misleading names.
Less applications with automatic video
annotation.
SOLUTION
“INSIDE” a smart semantic video searching
application with automatic annotation which
support easy, quick user friendly querying and
return an accurate list of videos for the
requesting query.
LITERATURE REVIEW
 Image subtraction and histogram comparison, traditional
video shot boundary detection techniques – video slicing
( reference : Video summarization by video structure analysis and graph optimization Shi
Lu,Department of Computer Science and Engineering)
 Object detection techniques: Appearance Based
Methods, Geometry-Based Methods (reference: OBJECT
RECOGNITION METHODS BASED ON TRANSFORMATION COVARIANT FEATURES Jiri Matas
and Stepan Obdrzalek)
 Key word searching vs Semantic searching (reference :
https://www.searchenginejournal.com/seo-101-semantic-search-care/119760/)
OBJECTIVES
Allow semantic video searching by analyzing the
structure and detecting content objects.
Classify videos automatically without user interaction.
User friendly
Accurate
METHODOLOGY WITH TOOLS AND
TECHNIQUES
Video structure analysis – Shot boundary detection
and video slicing
Deep Learning - Tensorflow
Data set preparation
Textual searching - Semantic searching
SYSTEM OVERVIEW
FUNCTIONS OF MEMBERS
Member Components Task
De Silva D.W.N Video structure analysis Identify shot boundaries.
Fragment video into shots.
Fragment shot into frames.
Ashangani S.K Deep Learning Neural Network configurations
Gamwara V.M Data set preparation Creation manipulation of large
data set to train the Neural
Network
Wickramasinghe K.U Textual searching Take search query as an input
and identify a relationship
among the words, return the
output
BENEFITS FOR USER
Accurate, Efficient search results.
Can be used at any time any where.
Can annotate video automatically.
COMMERCIAL VALUE
 Can be used as a tool and implement in search engines
 Can be used to categorize videos without user interaction
 Ability to rate videos according to their category (harmful)
Thank You

Inside proposal 16 113 - version 01

  • 1.
    VIDEO SEARCHING BYAUTOMATIC ANNOTATION GROUP NUMBER : 16 - 113 INSIDEPROJECT PROPOSAL
  • 2.
    Group Members , IT 13122942 Wickramasinghe K.U  IT 11150558 Ashangani S.K  IT 13115494 De Silva D.W.N  IT 13112424 Gamwara V.M
  • 3.
    INTRODUCTION  INSIDE What isvideo  Sequence of images to form a moving picture Our Mission  Friendly, simple video searching using automatic annotation to provide an accurate result
  • 4.
    RESEARCH PROBLEM Available searchengines only provide Keyword searching, Audio searching, Image searching. Most videos are weakly labeled or have misleading names. Less applications with automatic video annotation.
  • 5.
    SOLUTION “INSIDE” a smartsemantic video searching application with automatic annotation which support easy, quick user friendly querying and return an accurate list of videos for the requesting query.
  • 6.
    LITERATURE REVIEW  Imagesubtraction and histogram comparison, traditional video shot boundary detection techniques – video slicing ( reference : Video summarization by video structure analysis and graph optimization Shi Lu,Department of Computer Science and Engineering)  Object detection techniques: Appearance Based Methods, Geometry-Based Methods (reference: OBJECT RECOGNITION METHODS BASED ON TRANSFORMATION COVARIANT FEATURES Jiri Matas and Stepan Obdrzalek)  Key word searching vs Semantic searching (reference : https://www.searchenginejournal.com/seo-101-semantic-search-care/119760/)
  • 7.
    OBJECTIVES Allow semantic videosearching by analyzing the structure and detecting content objects. Classify videos automatically without user interaction. User friendly Accurate
  • 8.
    METHODOLOGY WITH TOOLSAND TECHNIQUES Video structure analysis – Shot boundary detection and video slicing Deep Learning - Tensorflow Data set preparation Textual searching - Semantic searching
  • 9.
  • 10.
    FUNCTIONS OF MEMBERS MemberComponents Task De Silva D.W.N Video structure analysis Identify shot boundaries. Fragment video into shots. Fragment shot into frames. Ashangani S.K Deep Learning Neural Network configurations Gamwara V.M Data set preparation Creation manipulation of large data set to train the Neural Network Wickramasinghe K.U Textual searching Take search query as an input and identify a relationship among the words, return the output
  • 11.
    BENEFITS FOR USER Accurate,Efficient search results. Can be used at any time any where. Can annotate video automatically.
  • 12.
    COMMERCIAL VALUE  Canbe used as a tool and implement in search engines  Can be used to categorize videos without user interaction  Ability to rate videos according to their category (harmful)
  • 13.