The applying I intend to make requires computer vision technology, so I looked for it and
discovered in regards to the Vision framework, so I briefly summarized it.
The Vision Framework is a framework that was announced together with coreML at WWDC in 2017.
- face detection
- Ability to trace facial landmarks
- Like iPhoneβs LiveText, the flexibility to seek out text in a photograph
- General image registration, tracking function
Computer vision algorithms might be applied to a picture or video to perform various functions similar to the above.
openCV can be one in every of the very talked-about computer vision frameworks.
- It supports several languages, but unfortunately swift isn’t supported.
Nevertheless, for the reason that vision framework was developed by Apple, it supports swift.
Also, itβs my guess, but because it was developed by Apple, isnβt it more compatible with swift? π€ - OpenCV is an external framework, so it must be installed individually, however the Vision framework is
import Vision
finished with only one code.
Pipelines are made up of subparts
request
handler
VNImageRequestHandler
: Used when working with still imagesVNSequenceRequestHandler
: Note the sequence. Used when working on image sequences (videos)
result
VNRequest
A request made with a subclass of is passed to the handler.- handler might be of
VNImageRequestHandler
typeVNSequenceRequestHandler
- The processed result
VNObservation
is returned as a subclass of .
For instance, if a sort VNRequest
that may be a subclass of is received as a request, a sort that may be a subclass of is returned as a return.VNDetectFaceRectanglesRequestVNObservationVNFaceObservation
For an additional example, it’s a format VNDetectContoursRequest
where is received as a request and VNContoursObservation
is returned as a return.