World’s FIRST TRUE Unified Search Engine -
A Single Engine to "Search Everything"
Babbobox Search is probably the world's most advanced search engine and is the only true unified search engine in the world that enables you to "Search Everything" - allowing you to index and search INSIDE your VIDEO, AUDIO, IMAGE and DOCUMENT files.
These include words and terms inside your documents, each word spoken in your organisation's audio and video assets. Babbobox Search can tell you exactly where these words are spoken of the video clip, in which segment, right down to the second, and then bringing you to it.
This is the Power of "Search Everything", it means you can now:
- Search Speech inside your Audio and Video files (in 12 languages)
- Search Text appearing in your Video files (in 26 languages)
- Search Context within Photos/Images (using Artificial Intelligence)
- Search Content/Text inside your Documents (over 100 languages)
The Magic is...
#1. In how we search videos
Searching documents is nothing new as this technology has been around for decades. However, when it comes to videos, current search engines can only search for "Title" and "Metadata". But the real content is INSIDE the videos.
Search Engine to combine Speech Recognition with Video OCR (Optical Character Recognition) into a unified video search platform. This combination makes Babbobox Search one of the world's most powerful video search engine.
#2. how we analyze images
Our engine can return tags based on more than 2000 recognizable objects, living beings, scenery, and actions. In cases where tags may be ambiguous or not common knowledge, our system provides “hints” to clarify the meaning of the tag in context of a known setting. A collection of content tags forms the foundation for an image “description” displayed as human readable language formatted in complete sentences. Tagging is not limited to the main subject, such as a person in the foreground, but also includes the setting (indoor or outdoor), furniture, tools, plants, animals, accessories, gadgets etc. (Note, that at this point English is the only supported language for image description.)
The following diagram shows the 86 categories that our image analyzer can tag and search.
Supported image formats: JPEG, PNG, GIF, BMP.
Image file size: Less than 4MB.
Image dimension: Greater than 50 x 50 pixels
#3. in the languages we search...
For Documents, we can search over 100 languages, for example: English, Simplified Chinese (简体中文), Traditional Chinese (繁體中文), Arabic, Malay, Bahasa Indonesia, Tagalog, Vietnamese, Japanese, Korean, Spanish, French, Portuguese, German, Russian, Dutch, Swedish, Greek, Italian, Hebrew, Latin, Turkish, Mongolian, etc.
For Video Speech Recognition, we can search up to 12 languages, they are: English, Chinese, Spanish, French, German, Italian, Portuguese (Brazilian), Arabic (Egyptian) Japanese, Russian, British English and Mexican Spanish
For Video OCR, we can search up to 26 languages, they are: Arabic, Chinese Simplified, Chinese Traditional, Czech, Danish, Dutch, English, Finnish, French, German, Greek, Hungarian, Italian, Japanese, Korean, Norwegian, Polish, Portuguese, Romanian, Russian, Serbian Cyrillic, Serbian Latin, Slovak, Spanish, Swedish, Turkish.
#4. in the formats that we can index...
The most comprehensive format types in any known Search Engine!
For Document formats: MS Office 2007+ (.docx, .xlsx, .pptx), HTML (.aspx, .asp .jsp, .htm, .html, etc), PDF, TXT, RTF, CSV, OOXML / MS Office 2007+ (.docx, .xlsx, .pptx), ODF (.odt, .ods), XML, ZIP
For Image Analysis, supported image formats: .jpeg, .png, .gif, .bmp.
For Speech Recognition, Video and Audio file formats: .wav, .wma, .wmv, .mp3, .mp4, .m4a, .aac.
For Video OCR, Video file formats: .mp4, .mov, and .wmv
#5. In our enterprise-grade search features
#1 High-speed index based search engine
Searches through millions of words across thousands of documents of multiple types in a fraction of a second.
#2 Phrase matching
Allows portions of a query to be surrounded with quotes causing the contained keywords to be treated as an exact phrase, search results will contain the words in the phrase in precise order.
#3 Smart search result summary & keyword highlighting
The search result summary is an extract of the original text showing as many of the search keywords as possible. Summary can include multiple extracts from various parts of the document when searched words are not close enough.
#4 Stemming/Lemmas - Word form variations are searched and ranked lower
Word variations are (optionally) included in the search - For example, the search term "downwards" yielded results with the same stem "downward" which were ranked lower (optional through an adjustable factor). Similarly a search for "downward" would yield results with "downwards", etc.
#5 Complex expression support; nested groups, partial matching, NOT, OR and AND
Brackets indicate grouping, "-" indicates a NOT operator, OR indicates OR logic, AND indicates AND logic (implicit when not specified). Groups can be nested to any number of levels, and may contain any legal expressions (phrases, NOT, OR, AND). Wildcards * can be used to indicate partial matches.
#6 Unicode and non English language support
Crawls and indexes pages encoded in most encodings (Unicode, UTF-8, ASCII, Cyrillic, Greek etc.) Page encoding is determined by server response or if in the page meta tags. All UI text's are localizable.
#6. in what else we can do (optional)
Video-Search-as-a-Service - where we focus on 6 areas:
- Speech Recognition
- Words or Text (Video OCR)
- Motion Detection
- Facial Detection
- Emotion Detection
- Offensive Content Detection
Translation Search - Search original Speech in another language!
- More than 8 x 50 = 400 language pairs to choose from
We Are Transforming "Search"...
Why do we need a search engine that searches everything? Simple. Because of 2 fundamentals:
- "Search" is a basic human and organisation need.
- Organizations possess all forms of digital assets (documents, images, audio and video)
Therefore, there is a fundamental need to find these digital assets when you need them, for whatever purpose. For research, to increase efficient or productivity. or simply finding something that you do not even know exist.
Not only are we transforming "Search", we are starting our quest in "The Search for Everything"