Computer vision
- 1. Presentation Course Code: CSE 414 Course Name: Simulation and Modelling Presented to: Anup Majumder Lecturer Department of CSE Daffodil International University
- 2. Hello! We are The IT Crowd Jannatul Nayem Himel 163-15-8538 Maksudur Rahman 162-15-7955 Md. Nazmul Hossain Mir 163-15-8386
- 4. What is Computer Vision At an abstract level, the goal of computer vision problems is to use the observed image data to infer something about the world.
- 5. What do you see? .
- 6. “ Just like to hear is not same as to listen, To take pictures is not same as to see.
- 7. A brief history Summer 1966, Seymour Papert and Marvin Minsky at MIT Artificial Intelligence group started a project titled Summer Vision Project. 70s, taking ideas from studies of the cerebellum, hippocampus and cortex for human perception, David Marr, a neuroscientist at MIT, set up the building blocks for the modern Computer Vision and thus is known as the father of the modern Computer Vision.
- 9. Artificial intelligence Artificial intelligence and computer vision share topics such as pattern recognition and learning techniques. Related fields Information engineering Computer vision is often considered to be part of information engineering.
- 10. Related fields Solid-state physics Most computer vision systems rely on image sensors, which detect electromagnetic radiation, which is typically in the form of either visible or infra- red light. The sensors are designed using quantum physics. Neurobiology The field of biological vision studies and models the physiological processes behind visual perception in humans and other animals. Computer vision, on the other hand, studies and describes the processes implemented in software and hardware behind artificial vision systems. Signal processing Because of the specific nature of images there are many methods developed within computer vision which have no counterpart in processing of one-variable signals. Together with the multi- dimensionality of the signal, this defines a subfield in signal processing as a part of computer vision.
- 11. Applications
- 12. Self Driving Vehicles Place your screenshot here
- 13. Facial recognition Place your screenshot here
- 14. Augmented and mixed reality
- 15. Application of Computer Vision Smartphones • QR codes • Computational photography (Android Lens Blur, iPhone Portrait Mode) • Panorama construction (Google Photo Spheres) • Face detection • Expression detection (smile) • Snapchat filters (face tracking) • Google Lens, Night Sight (Pixel) Web • Image search • Google photos • face recognition • object recognition • scene recognition • glocalization from vision • Facebook (image captioning) • Google maps aerial imaging (image stitching) • YouTube (content categorization) VR/AR • Outside-in tracking (HTC VIVE) • Inside out tracking (simultaneous localization and mapping, HoloLens) • Object occlusion (dense depth estimation)
- 16. Application of Computer Vision Medical imaging • CT / MRI reconstruction • Assisted diagnosis • Automatic pathology • Connect omics • AI-guided surgery Media • Visual effects for film • TV (reconstruction) • Virtual sports replay (reconstruction) • Semantics-based auto edits (reconstruction recognition) Insurance • Claims automation • Damage analysis • Property inspection
- 17. Limitations ◍ Failure to detect irrational behavior
- 18. Limitations ◍ Unable to classify messy data
- 19. Evolution
- 20. Manual Deep Learning The evolution of computer vision Machine Learning
- 21. Manual process Create a database Capture new images Annotate images
- 22. Machine Learning ◍ “features” ◍ Statistical learning algorithm ◌ Linear regression ◌ Logistic regression ◌ Decision trees ◌ Support vector machines (SVM) • Detect patterns • Classify images • Detect objects
- 23. Deep Learning ◍ Neural networks ◌ Labelled examples of a specific kind of data ◌ Extract common patterns ◌ Transform it into a mathematical equation ◌ Classify future pieces of information