Download to read offline
More Related Content
Similar to Machine learningfor computervision_ashutoshupadhyay
Machine learningfor computervision_ashutoshupadhyay
- 1. Machine Learning ForComputer Vision 1 Machine Learning for Computer Vision Ashutosh Upadhyay Assistant Professor School of Computer Science and Engineering Galgotias University, India
- 2. Machine Learning ForComputer Vision 2 Presentation Outline What is computer Vision Computer vision vs Human Vision Need of Computer Vision Challenges of Computer Vision Applications of Computer Vision Relation of Machine Learning with computer vision Machine learning algorithms Introduction of implementation using python
- 3. Machine Learning ForComputer Vision 3 What is Computer Vision? Make computers understand images and video Like when human “sees” something and interpret What kind of scene? Where are the people? How many Persons ? How Many Cars? How far is the building? Following Social Distancing or Not? Wearing mask or not?
- 4. Machine Learning ForComputer Vision 4 It is a multidisciplinary field that could broadly be called a subfield of artificial intelligence and machine learning, which may involve the use of specialized methods and make use of general learning algorithms What is Computer Vision?
- 5. Machine Learning ForComputer Vision 5 Computer Vision vs Human Vision
- 6. Machine Learning ForComputer Vision 6 Computer Vision vs Human Vision
- 7. Machine Learning ForComputer Vision 7 Computer Vision vs Human Vision
- 8. Machine Learning ForComputer Vision 8 Need of computer vision To get the most out of image data, we need computers to “see” an image and understand the content. This is a trivial problem for a human A person can describe the content of a photograph they have seen once. A person can summarize a video that they have only seen once. A person can recognize a face that they have only seen once before. We require at least the same capabilities from computers in order to unlock our images and videos.
- 9. Machine Learning ForComputer Vision 9 Challenge of Computer Vision The goal of computer vision is to extract useful information from images. Dynamic shape of object Changes in illumination Orientation of the objects Partial occlusion Shadowing effect
- 10. Machine Learning ForComputer Vision 10 Application of Computer Vision Optical character recognition (OCR) Machine inspection Retail (automated checkouts Amazon Store) Medical imaging Automotive safety Motion capture Surveillance Fingerprint recognition and biometrics
- 11. Machine Learning ForComputer Vision 11 Object Classification Object Identification Object Verification Object Detection Object Landmark Detection Object Segmentation Object Recognition Application of Computer Vision
- 12. Machine Learning ForComputer Vision 12 MACHINE LEARNING Machine learning is programming computers to optimize a performance criterion using example data or past experience. Learning is used when: Human expertise does not exist Humans are unable to explain their expertise
- 13. Machine Learning ForComputer Vision 13 Training Models
- 14. Machine Learning ForComputer Vision 14 Computer Vision Meets Machine Learning Dog Cat Dog Train: Deploy: Training Labels Training Image Features Prediction Image Features Learned model
- 15. Machine Learning ForComputer Vision 15 Image Features ?? Slide credit: L. Lazebnik Colour Edge Histogram Shape LBP HAAR HOG Region etc.
- 16. Machine Learning ForComputer Vision 16 Brief Tour of Some Classifiers K-nearest neighbor SVM Decision Trees Neural networks Naïve Bayes Bayesian network Logistic regression Random Forests Etc.
- 17. Machine Learning ForComputer Vision 17 Deep learning is an artificial intelligence function that imitates the workings of the human brain in processing data and creating patterns for use in decision making. Enables the automatic learning of feature Generally based on artificial neural networks Deep Learning
- 18. Machine Learning ForComputer Vision 18 Deep Learning Everywhere MEDICINE &BIOLOGY Cancer Cell Detection Diabetic Grading Drug Discovery INTERNET & CLOUD Image Classification Speech Recognition Language Translation Language Processing Sentiment Analysis Recommendation
- 19. Machine Learning ForComputer Vision 19 SECURITY & DEFENSE Face Detection Video Surveillance Satellite Imagery AUTONOMOUS MACHINES Pedestrian Detection Lane Tracking Recognize Traffic Sign
- 20. Machine Learning ForComputer Vision 20 Why Python Is Well-suited To Data Science? NumPy Numerical library for python Fast Scipy Common maths, science, engineering routines Matplotlib Hugely flexible plotting library Similar syntax to Matlab Produces publication-quality output
- 21. Machine Learning ForComputer Vision 21 Thank You