This repo contains a SDK and a sample project for Microsoft Cognitive Services written in Swift since Microsoft doesn't provide one. If you are looking for the Windows, Android or Phython SDK you can find them here.
The repo contains a client SDK for the following areas (Work in progress):
This module will produce visual features based on the input image's visual content -- image categories, pornographic detection, dominant color, and more.
-
Use the adult and racy features to enable automated restriction of sexual content and protect your users.
-
Utilize categorization to help append tags to images, as well as group images into clusters.
-
Describe images in complete sentences and recognize celebrities that appear in photos.
Given an input image, you will be able to generate a high quality and storage efficient thumbnail.
-
Leverage thumbnail generation to help present images in the best form suited to your needs.
-
Use smart cropping for thumbnails that are different than the aspect ratio of your original image in order to preserve the region of interest.
Optical Character Recognition (OCR) detects text in an image and extracts the recognized characters into a machine-usable character stream.
-
Run on embedded images to generate text and enable searching.
-
Allow users to take photos of text instead of transcribing to save time and effort.
To get started just import the SDK folder into your Project.
In case you want to contribute go ahead and create that pull request :).There's plenty more to do. Feel free to file issues on the repo and I'll try address them as soon as possible.
For questions, feedback, or suggestions about the SDK, feel free to get in touch with me. Here you get help with questions about the Cognitive Services.
- Computer Vision APIs (Preview): Distill actionable information from images
- Emotion APIs (Preview): Personalize experiences with emotion recognition
- Face APIs (Preview): Detect, identify, analyze, organize, and tag faces in photos
- Video APIs (Preview): Analyze, edit, and process videos within your app
- Speaker Recognition APIs (Preview): Give your app the ability to know who's talking
- Speech APIs (Preview): Convert speech to text and back again, and understand its intent
- LUIS, Language Understanding Intelligent Services (Preview): Teach your apps to understand commands from your users
- Linguistic Analysis APIs (Preview): Easily parse complex text with language analysis
- Web Language Model APIs (Preview): Leverage the power of language models trained on web-scale data
- Entity Linking APIS (Preview): Contextually extend knowledge of people, locations, and events
To see the full list of APIs, please visit Microsoft Cognitive Service APIs.
To learn more and sign-up for Microsoft Cognitive Services, visit Microsofts website. You must obtain subscription keys for different services and will need a Microsoft account.
The SDK is licensed under the Apache License 2.0. For more details, see LICENSE.
The SDK uses the Microsoft Cognitive Services, see https://www.microsoft.com/cognitive-services/. Developers using this are expected to follow the “Developer Code of Conduct for Microsoft Cognitive Services” at http://go.microsoft.com/fwlink/?LinkId=698895.
Data submitted may be retained by Microsoft for service improvement purposes, along with the other stipulations noted in the following documents: Cognitive Services TOU, Developer Code of Conduct
This project follows the Cognitive Services TOU