AI in image recognition
Download as PPTX, PDF2 likes352 views
The document discusses image recognition capabilities of Google Vision and Amazon Rekognition and how they can be used in a mobile app called Fastra. Google Vision can understand image content, detect objects, faces, logos and texts. It can also search image content online, detect inappropriate content, facial expressions and landmarks. Amazon Rekognition also allows video analysis, facial analysis, celebrity recognition and text detection in images. Some ideas mentioned are automatic tagging, emotion-based suggestions, landmark-based categories, filters, celebrity recognition and linking to trends for the Fastra app.
AI in image recognition
- 1. AI Capabilities in Image Recognition Technology and Ideas we can use in our app
- 2. Agenda Overview Introduction to Google Vision Capabilities of Google Vision How it can benefit Fastra app A look at Amazon Rekognition Ideas?
- 3. Overview What is AI? What is the role of AI in Image processing?
- 4. Google Vision “Now, users can naturally find GIFs based on popular movie lines, music lyrics and catchphrases. This has resulted in click-through rates increasing up to 32%.” - Nick Hasty, Director, GIPHY
- 5. What it can do 01 Understand the content of an image. It's a boat! It's a tiger! It's a bird! 02 Can detect monuments, objects, faces. 03 Can detect company logos, texts, offensive content.
- 6. What it can do 04 Using capabilities of Google, can search the image content from web and detect the source and links. 05 Can detect copyright material, celebrities, news events etc. 06 Can detect facial expression and other things related to face recognition.
- 7. Detecting Faces It can find human faces in photos, videos or live streams. Can also detect facial landmarks like nose, eyes and mouth.
- 8. Detecting objects It can easily detect broad sets of objects in your images, from flowers, animals, or transportation to thousands of other object categories commonly found within images.
- 12. Detecting inappropriate content Powered by Google SafeSearch, easily moderate content from your crowd sourced images. Vision API enables you to detect different types of inappropriate content from adult to violent content.
- 15. Power of Google Search Vision API uses the power of Google Image Search to find topical entities like celebrities, logos, or news events. Combine this with Visually Similar Search to find similar images on the web.
- 19. Reads Text Optical Character Recognition (OCR) enables you to detect text within your images, along with automatic language identification. Vision API supports a broad set of languages.
- 22. Emotion Detection Detects every kind of emotion on faces.
- 25. Logos and Landmark Detection Detects various objects, landmarks, monuments or logos.
- 35. Google Vision SDKs ● Mobile SDKs - iOS and Android ● Backend SDKs
- 36. What we can do in Fastra ● Automatic tag creation ● Suggestion to user on the basis of emotion detected in Selfies ● Different Slefie/Fun Categories on the basis of background landmark ● Filters ● Celebrity recognition ● Linking to current affairs/trends ● Text Detection in Fun ● Filter out objectionable images
- 37. Amazon Rekognition Amazon Rekognition Video also allows you to easily and quickly review hours of video footage to search for persons of interest, track their movement, and detect their activities.
- 38. Amazon Rekognition - Capabilities ● Image moderation ● Facial analysis ● Celebrity Recognition ● Face comparison ● Text In Image ● Video analysis
- 40. Ideas?