The Viper group deals with the processing and management of multimedia. In particular, we focus onmultimedia information retrieval and mining. Our current research interests include:
- Multimedia information Retrieval: Image and video (including audio)
- Multimedia information mining with our novative concept of Collection Guiding and also our efforts for large multimedia collection management
- Multimedia processing as a need to design efficient features.
WHY MMIR IS NEEDED NOWADAYS?
BECAUSE With the explosive growth of digital media data, there is a huge demand for new tools and systems that enables average users to more efficiently and more effectively search, access, process, manage, author and share these digital media contents.
MMIR OVERVIEW:
MMIR OVERVIEW:
- CONTENT-BASED IMAGE RETRIEVAL (CBIR)
Content-based image retrieval (CBIR), also known as query by image content (QBIC) and content-based visual information retrieval (CBVIR) is the application of computer vision techniques to the image retrieval problem, that is, the problem of searching for digital images in large databases. for a recent scientific overview of the CBIR field)
"Content-based" means that the search will analyze the actual contents of the image rather than the metadata such as keywords, tags, and/or descriptions associated with the image. The term 'content' in this context might refer to colors, shapes, textures, or any other information that can be derived from the image itself. CBIR is desirable because most web based image search engines rely purely on metadata and this produces a lot of garbage in the results. Also having humans manually enter keywords for images in a large database can be inefficient, expensive and may not capture every keyword that describes the image. Thus a system that can filter images based on their content would provide better indexing and return more accurate results.
- Image Search Systems that search images by image content
<-> Keyword-based Image Retrieval
(ex. Google Image Search)
Applications of CBIR
�� Consumer Digital Photo Albums
�� Digital Cameras
�� Ex. WWMX by Microsoft Research
�� Medical Images
�� Digital Museum
�� Trademarks Search
�� MPEG-7 Content Descriptors
How does CBIR work ?
�� Extract Features from Images
�� Let the user do Query
�� Query by Sketch
�� Query by Keywords
�� Query by Example
�� Refine the result by Relevance Feedback
�� Give feedback to the previous result
Query techniques
- query by examples
- semantic retrrieval
Content comparison using image distance measures
- Color
- Texture
- Shape
![]() |
![]() |
MANY CBIR SYSTEM HAVE BEEN BUILT |
- CONTENT-BASED VIDEO RETRIEVAL (CBVR)
Content-Based Video Retrieval: A Database Perspective concentrates on the semantic gapproblem, i.e., the problem of inferring semantics from raw video data, as the main problem of content based video retrieval.
The proposed architecture for a content-based video
retrieval system is as shown above . The process of
database population is shown with dashed lines, whilequerying is shown with solid lines. The raw videodata is stored in the file system, while the storageserver is used to store video content meta data andindexes. In the process of the database population, thefeatures, objects, and events that are specified bysystem administrator, are extracted. Indexes and metadata are put in the storage server and videos in the filesystem. Most queries are resolved directly in thestorage server, but if the query comprises somethingthat has not been already extracted the extractors dothat dynamically.
- CONTENT-BASED AUDIO RETRIEVAL (CBAR)
to search sounds by their features in the waveform, statistics, OR transform domains. examples such as Speech, Music, Environment Audio, Silence.
APPLICATION:
- Entertainment
��Film making - searching sound effects
��TV/radio studio - editing programs
��Karaoke, music stores, or online shopping
- query by humming the melody
- 2. Audio/video archive management
��Segmenting and indexing of raw recordings
��Searching and browsing audio/video clips
3. Surveillance
��Monitoring criminal or emergent events
��Film rating