Q: What is COMputer Vision (Image AI)?

Computer vision is a field of artificial intelligence (AI) that enables computers and systems to derive meaningful information from digital images, videos. In Aispace, we apply this to images or photos in your storage to pull from a rich ontology of more than 10,000 concepts and objects to generate value from your visual assets.

Q: Why use computer vision?

We use Speech AI for these key benefits:

  • Extracts data or information about the image

  • Automatically tag images

  • Enables image search

It is extremely useful if your environment is media-rich!

Q: What information (or data) can we extract?

We can generate information in these six categories:

  1. Captions - Generate a description of an entire image. Includes names of famous people and landmarks

  2. Categories - detect and identify domain-specific content

  3. Tags - Identify and tag visual features, from a set of thousands of recognizable objects, living things, scenery, and actions

  4. Faces - Provide information about each detected face (gender and age)

  5. Image Properties - Properties of an image

  6. Dominant Colours - Analyze colour usage. Useful for “moods”

Q: Can we search our images?

Yes! That’s the purpose of this service. So you can now search for image library using data generated from Computer Vision (Image AI) using our world’s first Unified Search Engine

Q: How many languages does computer vision support?

Currently, we can generate image data in English only.

Q: are there any image requirements?

Yes. There are some requirements. They are:

  • Format: image should be in JPEG, PNG, GIF, or BMP format

  • Size: file size of the image must be less than 4 megabytes (MB)

  • Dimension: image must be greater than 50 x 50 pixels

Q: Whose faces can COmputer vision recognize?

The Computer Vision API has a library of a few hundred thousand celebrities or famous people images (and growing!). However accuracy also depends on quality of images.

Q: How many landmarks can COmputer vision recognize?

The Computer Vision API has a library of over thousand of landmarks worldwide (and growing!). However, accuracy also depends on quality of images.

Q: How is this service consumed in Aispace?

If you have sufficient Computer Vision (Image AI) quota, all images that are uploaded will be analyzed automatically and deducted from your quota. If there are insufficient quota, please contact your organization’s administer to allocate or purchase more.

Q: Is this service secured?

Yes! Your privacy is of utmost importance to us. Yes. Once Computer Vision AI finish processing the media files, they are deleted immediately. We do not keep your media files or the data generated or use them for any other purpose. Nobody inside or outside Aispace has access to your files.

Q: How long does it take to analyse my photos?

Fast. It is almost instant. However, if you upload a large volume of images at once, Aispace will queue these images for processing.

Q: What are the Computer vision packages?

You can buy according to your needs. Packages come in 5,000, 10,000 or 25,000 images.

Q: Can I train this Computer Vision AI with our own data?

This function is currently not available as Aispace is a shared service. However, if you require a custom vision for your own purposes, we do have this capability on a project basis, Please contact us to find out more.