SlideShare a Scribd company logo
1 of 20
Computer Vision
–
Old Problems and New Solutions
Gopi Krishna Nuti
Vice President, MUST Research
vp@must.co.in, ngopikrishna@gmail.com
Computer Vision
–
The (age) old
problems
• What should a robot do in “Scene
understanding”?
• Identify colours, brightness etc
• Identify objects a.k.a Image Segmentation
• Different things
• Multiple occurrences of the same thing
• Stuff other than things
• Distance of things and stuff
• Relative and absolute
Colour and
Brightness
Colour spaces
• Grayscale, RGB, CMY,
• Transparency/Opacity
using a fourth
attribute
Limitations
• Does not represent all
colours in nature
• colour perception
highly susceptible to
lighting changes.
New Solutions
• Colour spaces have
been expanded greatly.
• With micro and
macro level
differences, ~250
colour spaces are in
vogue
• HSV, HSL/HSI,
YUV, YPbPr, YCbCr
etc
Old Problem
–
Image
Segmentation
Panoptic Segmentation – Not a technique. A metric
Old Problem
–
Image
Segmentation
• Image is an matrix of numbers.
• How to identify the edges of each object
• How to recognize the object correctly
• Differentiate between “things” (foreground)
and “stuff ” (background)
Image
Segmentation
–
Old Solutions
Solution Family Algorithm Drawbacks
Thresholding
• Otsu thresholding
• Adaptive local thresholding
• Mean
• Gaussian
For reasonably simple scenarios only
Edges and Corners
• Canny edges, Sobel Hough, Laplace
algorithms
• Harris Corner detection
• Convolution of kernels
Unsuitable for noisy/blurry images
Region Growing
Watershed
• Relatively strong at detecting
overlapping/touching objects
Super Pixels
• SLCI Algorithm
• Susceptible to noise
• Steep increase in algorithmic
complexit
Clustering
• K-means
• Fuzzy C-Means (FCM)
• Expectation Maximization (EM)
• Relies on low level features like colour etc.
• Poor performance on complicated images
Clustering • Image Pyramid
• Carefully controlled environments only
• Cannot handle non-affine transformation like
rotation, reflection etc.
• Occlusions are a big no-no
• Compute intensive
Image
Segmentation
–
Convolutional
Neural
Networks
• Specialized kind of neural networks
• Process data in known grid-like spatial structures
• Comprised of large number of layers like convolution,
pooling and Fully connected layers
• Usually, very very deep. i.e. lots of layers and lots of weight
parameters
• Non linear Activation Functions are mandatory for learning
complex features
http://cs231n.github.io/convolutional-networks/#overview
Evolution of
CNN
Classifiers
2014
• Regions
with CNN
Features
2015
• Fast R-CNN
• Faster R-CNN
• Inception V3
2016
• YOLO
• SSD
• UberNet
2017
• Mask R-
CNN
• Pixel wise
Instance
Segmentation
Some Salient
points
Regions with CNN FeaturesR-CNN
• Uses Selective Search
• Significantly reduced the search space to ~2000 region proposal
• Very Slow and very complicated
Designed to solve the problems with R-CNNFast R-CNN
• Region Of Interest is treated as a pooling layer
• Jointly trains feature extractor, classifier and bounding box regression into a single model
• Almost 25 time faster than R-CNN
Replace Selective search with region proposal networkFaster R-CNN
• 10 times faster than Fast R-CNN
You Only Look OnceYOLO
• Detection is considered as a regression problem
• Extremely fast but less accurate. Struggles with small objects that appear in groups
Single Shot Multi box detectorSSD
• Faster than YOLO and more accurate as well.
Extension of Faster R-CNNMask R-CNN
• Predicts the object masks as well as bounding box
• Impressive results
Old Problem
-
Depth
Perception
Normal vision and depth
perception expectation
Relative depth
Optical illusion based on depth Picture of a picture. All pixels
have same depth
Old Solutions
-
Depth
Perception
• Stereo cameras spaced at a fixed distance apart capture the
same image.
• Remember trigonometry? 
• Algorithm Families
• Triangulation
• Interferometry
• Time of Flight
• Many Limitations
• Cost
• Complexity
• Controlled environments only
New Solutions
-
Depth
Perception
• Furious research in progress
• Single camera moving between two fixed positions
• Monocular Depth perception
• Some interesting proposals
• Train NN with depth information and semantically segmented
image
• Use the models for predicting depth in new images
Old Problem –
Programmer’s Dilemma
Old Problem
-
Programmers Dilemma
• Which image format should I use?
• Which image file format should I code for? Do I have to
learn reading and writing image files?
• Matlab is expensive 
New Solution
-
OpenCV, Python,
PILLOW etc
• OpenCV
• Democratized image processing
• A large number of functionalities provided as APIs
• Impressive Python bindings and native support for C, Java
• Python
• PILLOW and many other libraries for reading images
• Vectorization and Numpy Arrays
New Solutions
–
New Problems
Neural
Networks
• Data hungry. Lots and lots of training data.
• Resource hungry and compute intensive.
• Overfitting, Underfitting, Stochasticity
• Black box
Some solutions
• Transfer Learning to reduce training time
• Hyper parameter tuning
• Hardware based solutions for improving performance
• On-going research for explainability
• On-going research for reducing the training data
requirement 3rd generation neural networks
Demos

More Related Content

What's hot

Towards a Reactive Game Engine
Towards a Reactive Game EngineTowards a Reactive Game Engine
Towards a Reactive Game EngineNUS-ISS
 
Data! Data! Data! I Can't Make Bricks Without Clay!
Data! Data! Data! I Can't Make Bricks Without Clay!Data! Data! Data! I Can't Make Bricks Without Clay!
Data! Data! Data! I Can't Make Bricks Without Clay!Turi, Inc.
 
Jeff Dean at AI Frontiers: Trends and Developments in Deep Learning Research
Jeff Dean at AI Frontiers: Trends and Developments in Deep Learning ResearchJeff Dean at AI Frontiers: Trends and Developments in Deep Learning Research
Jeff Dean at AI Frontiers: Trends and Developments in Deep Learning ResearchAI Frontiers
 
Machine learning basics
Machine learning basics Machine learning basics
Machine learning basics Akanksha Bali
 
Deep learning Introduction and Basics
Deep learning  Introduction and BasicsDeep learning  Introduction and Basics
Deep learning Introduction and BasicsNitin Mishra
 
“From Inference to Action: AI Beyond Pattern Recognition,” a Keynote Presenta...
“From Inference to Action: AI Beyond Pattern Recognition,” a Keynote Presenta...“From Inference to Action: AI Beyond Pattern Recognition,” a Keynote Presenta...
“From Inference to Action: AI Beyond Pattern Recognition,” a Keynote Presenta...Edge AI and Vision Alliance
 
Deep Learning With Python Tutorial | Edureka
Deep Learning With Python Tutorial | EdurekaDeep Learning With Python Tutorial | Edureka
Deep Learning With Python Tutorial | EdurekaEdureka!
 
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine LearningShimi Bandiel
 
Introduction to machine learningunsupervised learning
Introduction to machine learningunsupervised learningIntroduction to machine learningunsupervised learning
Introduction to machine learningunsupervised learningSardar Alam
 
Deep Learning: Evolution of ML from Statistical to Brain-like Computing- Data...
Deep Learning: Evolution of ML from Statistical to Brain-like Computing- Data...Deep Learning: Evolution of ML from Statistical to Brain-like Computing- Data...
Deep Learning: Evolution of ML from Statistical to Brain-like Computing- Data...Impetus Technologies
 
Building a performing Machine Learning model from A to Z
Building a performing Machine Learning model from A to ZBuilding a performing Machine Learning model from A to Z
Building a performing Machine Learning model from A to ZCharles Vestur
 
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine LearningNandita Naik
 
Applications of Machine Learning
Applications of Machine LearningApplications of Machine Learning
Applications of Machine LearningHayim Makabee
 
Introduction to deep learning workshop
Introduction to deep learning workshopIntroduction to deep learning workshop
Introduction to deep learning workshopShamane Siriwardhana
 

What's hot (15)

Towards a Reactive Game Engine
Towards a Reactive Game EngineTowards a Reactive Game Engine
Towards a Reactive Game Engine
 
Data! Data! Data! I Can't Make Bricks Without Clay!
Data! Data! Data! I Can't Make Bricks Without Clay!Data! Data! Data! I Can't Make Bricks Without Clay!
Data! Data! Data! I Can't Make Bricks Without Clay!
 
Jeff Dean at AI Frontiers: Trends and Developments in Deep Learning Research
Jeff Dean at AI Frontiers: Trends and Developments in Deep Learning ResearchJeff Dean at AI Frontiers: Trends and Developments in Deep Learning Research
Jeff Dean at AI Frontiers: Trends and Developments in Deep Learning Research
 
Machine learning basics
Machine learning basics Machine learning basics
Machine learning basics
 
Deep learning Introduction and Basics
Deep learning  Introduction and BasicsDeep learning  Introduction and Basics
Deep learning Introduction and Basics
 
“From Inference to Action: AI Beyond Pattern Recognition,” a Keynote Presenta...
“From Inference to Action: AI Beyond Pattern Recognition,” a Keynote Presenta...“From Inference to Action: AI Beyond Pattern Recognition,” a Keynote Presenta...
“From Inference to Action: AI Beyond Pattern Recognition,” a Keynote Presenta...
 
Deep Learning With Python Tutorial | Edureka
Deep Learning With Python Tutorial | EdurekaDeep Learning With Python Tutorial | Edureka
Deep Learning With Python Tutorial | Edureka
 
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine Learning
 
Introduction to machine learningunsupervised learning
Introduction to machine learningunsupervised learningIntroduction to machine learningunsupervised learning
Introduction to machine learningunsupervised learning
 
Deep learning
Deep learningDeep learning
Deep learning
 
Deep Learning: Evolution of ML from Statistical to Brain-like Computing- Data...
Deep Learning: Evolution of ML from Statistical to Brain-like Computing- Data...Deep Learning: Evolution of ML from Statistical to Brain-like Computing- Data...
Deep Learning: Evolution of ML from Statistical to Brain-like Computing- Data...
 
Building a performing Machine Learning model from A to Z
Building a performing Machine Learning model from A to ZBuilding a performing Machine Learning model from A to Z
Building a performing Machine Learning model from A to Z
 
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine Learning
 
Applications of Machine Learning
Applications of Machine LearningApplications of Machine Learning
Applications of Machine Learning
 
Introduction to deep learning workshop
Introduction to deep learning workshopIntroduction to deep learning workshop
Introduction to deep learning workshop
 

Similar to Computer vision old problems new solutions

Deep Learning behind Prisma
Deep Learning behind PrismaDeep Learning behind Prisma
Deep Learning behind Prismalostleaves
 
HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...
HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...
HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...Tulipp. Eu
 
CSE367 Lecture 1 image processing lecture
CSE367 Lecture 1 image processing lectureCSE367 Lecture 1 image processing lecture
CSE367 Lecture 1 image processing lectureFatmaNewagy1
 
Image Style Transfer and AI on iOS Mobile App
Image Style Transfer and AI on iOS Mobile AppImage Style Transfer and AI on iOS Mobile App
Image Style Transfer and AI on iOS Mobile AppChihyang Li
 
Overview of Computer Vision For Footwear Industry
Overview of Computer Vision For Footwear IndustryOverview of Computer Vision For Footwear Industry
Overview of Computer Vision For Footwear IndustryTanvir Moin
 
Non-Local Means and its Applications
Non-Local Means and its ApplicationsNon-Local Means and its Applications
Non-Local Means and its ApplicationsManchor Ko
 
Introduction to computer vision with Convoluted Neural Networks
Introduction to computer vision with Convoluted Neural NetworksIntroduction to computer vision with Convoluted Neural Networks
Introduction to computer vision with Convoluted Neural NetworksMarcinJedyk
 
2009-07-30 gyovai-intern
2009-07-30 gyovai-intern2009-07-30 gyovai-intern
2009-07-30 gyovai-internKane Gyovai
 
Image style transfer and iOS CoreML, Vision Frameworks
Image style transfer and iOS CoreML, Vision FrameworksImage style transfer and iOS CoreML, Vision Frameworks
Image style transfer and iOS CoreML, Vision FrameworksChihyang Li
 
Bring Satellite and Drone Imagery into your Data Science Workflows
Bring Satellite and Drone Imagery into your Data Science WorkflowsBring Satellite and Drone Imagery into your Data Science Workflows
Bring Satellite and Drone Imagery into your Data Science WorkflowsDatabricks
 
Soumith Chintala at AI Frontiers: A Dynamic View of the Deep Learning World
Soumith Chintala at AI Frontiers: A Dynamic View of the Deep Learning WorldSoumith Chintala at AI Frontiers: A Dynamic View of the Deep Learning World
Soumith Chintala at AI Frontiers: A Dynamic View of the Deep Learning WorldAI Frontiers
 
Extraction of region of interest in an image
Extraction of region of interest in an imageExtraction of region of interest in an image
Extraction of region of interest in an imageHarsukh Chandak
 
Introduction to computer vision
Introduction to computer visionIntroduction to computer vision
Introduction to computer visionMarcin Jedyk
 
Computer Graphics Unit 5 notes for Manonmanium Sundaranar University
Computer Graphics  Unit 5 notes for Manonmanium Sundaranar UniversityComputer Graphics  Unit 5 notes for Manonmanium Sundaranar University
Computer Graphics Unit 5 notes for Manonmanium Sundaranar UniversityRajeswariR45
 
151106 Sketch-based 3D Shape Retrievals using Convolutional Neural Networks
151106 Sketch-based 3D Shape Retrievals using Convolutional Neural Networks151106 Sketch-based 3D Shape Retrievals using Convolutional Neural Networks
151106 Sketch-based 3D Shape Retrievals using Convolutional Neural NetworksJunho Cho
 
Cahall Final Intern Presentation
Cahall Final Intern PresentationCahall Final Intern Presentation
Cahall Final Intern PresentationDaniel Cahall
 

Similar to Computer vision old problems new solutions (20)

Image analytics - A Primer
Image analytics - A PrimerImage analytics - A Primer
Image analytics - A Primer
 
Deep Learning behind Prisma
Deep Learning behind PrismaDeep Learning behind Prisma
Deep Learning behind Prisma
 
HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...
HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...
HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...
 
november29.ppt
november29.pptnovember29.ppt
november29.ppt
 
CSE367 Lecture 1 image processing lecture
CSE367 Lecture 1 image processing lectureCSE367 Lecture 1 image processing lecture
CSE367 Lecture 1 image processing lecture
 
Image processing.pdf
Image processing.pdfImage processing.pdf
Image processing.pdf
 
Image Style Transfer and AI on iOS Mobile App
Image Style Transfer and AI on iOS Mobile AppImage Style Transfer and AI on iOS Mobile App
Image Style Transfer and AI on iOS Mobile App
 
Overview of Computer Vision For Footwear Industry
Overview of Computer Vision For Footwear IndustryOverview of Computer Vision For Footwear Industry
Overview of Computer Vision For Footwear Industry
 
Non-Local Means and its Applications
Non-Local Means and its ApplicationsNon-Local Means and its Applications
Non-Local Means and its Applications
 
Digital image processing
Digital image processingDigital image processing
Digital image processing
 
Introduction to computer vision with Convoluted Neural Networks
Introduction to computer vision with Convoluted Neural NetworksIntroduction to computer vision with Convoluted Neural Networks
Introduction to computer vision with Convoluted Neural Networks
 
2009-07-30 gyovai-intern
2009-07-30 gyovai-intern2009-07-30 gyovai-intern
2009-07-30 gyovai-intern
 
Image style transfer and iOS CoreML, Vision Frameworks
Image style transfer and iOS CoreML, Vision FrameworksImage style transfer and iOS CoreML, Vision Frameworks
Image style transfer and iOS CoreML, Vision Frameworks
 
Bring Satellite and Drone Imagery into your Data Science Workflows
Bring Satellite and Drone Imagery into your Data Science WorkflowsBring Satellite and Drone Imagery into your Data Science Workflows
Bring Satellite and Drone Imagery into your Data Science Workflows
 
Soumith Chintala at AI Frontiers: A Dynamic View of the Deep Learning World
Soumith Chintala at AI Frontiers: A Dynamic View of the Deep Learning WorldSoumith Chintala at AI Frontiers: A Dynamic View of the Deep Learning World
Soumith Chintala at AI Frontiers: A Dynamic View of the Deep Learning World
 
Extraction of region of interest in an image
Extraction of region of interest in an imageExtraction of region of interest in an image
Extraction of region of interest in an image
 
Introduction to computer vision
Introduction to computer visionIntroduction to computer vision
Introduction to computer vision
 
Computer Graphics Unit 5 notes for Manonmanium Sundaranar University
Computer Graphics  Unit 5 notes for Manonmanium Sundaranar UniversityComputer Graphics  Unit 5 notes for Manonmanium Sundaranar University
Computer Graphics Unit 5 notes for Manonmanium Sundaranar University
 
151106 Sketch-based 3D Shape Retrievals using Convolutional Neural Networks
151106 Sketch-based 3D Shape Retrievals using Convolutional Neural Networks151106 Sketch-based 3D Shape Retrievals using Convolutional Neural Networks
151106 Sketch-based 3D Shape Retrievals using Convolutional Neural Networks
 
Cahall Final Intern Presentation
Cahall Final Intern PresentationCahall Final Intern Presentation
Cahall Final Intern Presentation
 

More from Gopi Krishna Nuti

Neural Networks - it’s usage in Corporate
Neural Networks -it’s usage in CorporateNeural Networks -it’s usage in Corporate
Neural Networks - it’s usage in CorporateGopi Krishna Nuti
 
Ai for pharmaceutical industry – a primer
Ai for pharmaceutical industry – a primerAi for pharmaceutical industry – a primer
Ai for pharmaceutical industry – a primerGopi Krishna Nuti
 
Emerging Technology trends and employability skills
Emerging Technology trends and employability skillsEmerging Technology trends and employability skills
Emerging Technology trends and employability skillsGopi Krishna Nuti
 
Classification vis a-vis ranking - gopi
Classification vis a-vis ranking - gopiClassification vis a-vis ranking - gopi
Classification vis a-vis ranking - gopiGopi Krishna Nuti
 
Emerging Trends in Information Technology
Emerging Trends in Information TechnologyEmerging Trends in Information Technology
Emerging Trends in Information TechnologyGopi Krishna Nuti
 

More from Gopi Krishna Nuti (8)

Neural Networks - it’s usage in Corporate
Neural Networks -it’s usage in CorporateNeural Networks -it’s usage in Corporate
Neural Networks - it’s usage in Corporate
 
Ai for pharmaceutical industry – a primer
Ai for pharmaceutical industry – a primerAi for pharmaceutical industry – a primer
Ai for pharmaceutical industry – a primer
 
Softskills orientation
Softskills orientationSoftskills orientation
Softskills orientation
 
Emerging Technology trends and employability skills
Emerging Technology trends and employability skillsEmerging Technology trends and employability skills
Emerging Technology trends and employability skills
 
Classification vis a-vis ranking - gopi
Classification vis a-vis ranking - gopiClassification vis a-vis ranking - gopi
Classification vis a-vis ranking - gopi
 
F2 talk
F2 talkF2 talk
F2 talk
 
Inferene trends in industry
Inferene trends in industryInferene trends in industry
Inferene trends in industry
 
Emerging Trends in Information Technology
Emerging Trends in Information TechnologyEmerging Trends in Information Technology
Emerging Trends in Information Technology
 

Recently uploaded

Arihant handbook biology for class 11 .pdf
Arihant handbook biology for class 11 .pdfArihant handbook biology for class 11 .pdf
Arihant handbook biology for class 11 .pdfchloefrazer622
 
Grant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingGrant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingTechSoup
 
Mastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory InspectionMastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory InspectionSafetyChain Software
 
Hybridoma Technology ( Production , Purification , and Application )
Hybridoma Technology  ( Production , Purification , and Application  ) Hybridoma Technology  ( Production , Purification , and Application  )
Hybridoma Technology ( Production , Purification , and Application ) Sakshi Ghasle
 
A Critique of the Proposed National Education Policy Reform
A Critique of the Proposed National Education Policy ReformA Critique of the Proposed National Education Policy Reform
A Critique of the Proposed National Education Policy ReformChameera Dedduwage
 
Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)eniolaolutunde
 
Paris 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activityParis 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activityGeoBlogs
 
mini mental status format.docx
mini    mental       status     format.docxmini    mental       status     format.docx
mini mental status format.docxPoojaSen20
 
URLs and Routing in the Odoo 17 Website App
URLs and Routing in the Odoo 17 Website AppURLs and Routing in the Odoo 17 Website App
URLs and Routing in the Odoo 17 Website AppCeline George
 
Introduction to AI in Higher Education_draft.pptx
Introduction to AI in Higher Education_draft.pptxIntroduction to AI in Higher Education_draft.pptx
Introduction to AI in Higher Education_draft.pptxpboyjonauth
 
Introduction to ArtificiaI Intelligence in Higher Education
Introduction to ArtificiaI Intelligence in Higher EducationIntroduction to ArtificiaI Intelligence in Higher Education
Introduction to ArtificiaI Intelligence in Higher Educationpboyjonauth
 
microwave assisted reaction. General introduction
microwave assisted reaction. General introductionmicrowave assisted reaction. General introduction
microwave assisted reaction. General introductionMaksud Ahmed
 
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxSOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxiammrhaywood
 
PSYCHIATRIC History collection FORMAT.pptx
PSYCHIATRIC   History collection FORMAT.pptxPSYCHIATRIC   History collection FORMAT.pptx
PSYCHIATRIC History collection FORMAT.pptxPoojaSen20
 
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...EduSkills OECD
 
Alper Gobel In Media Res Media Component
Alper Gobel In Media Res Media ComponentAlper Gobel In Media Res Media Component
Alper Gobel In Media Res Media ComponentInMediaRes1
 
How to Make a Pirate ship Primary Education.pptx
How to Make a Pirate ship Primary Education.pptxHow to Make a Pirate ship Primary Education.pptx
How to Make a Pirate ship Primary Education.pptxmanuelaromero2013
 
Sanyam Choudhary Chemistry practical.pdf
Sanyam Choudhary Chemistry practical.pdfSanyam Choudhary Chemistry practical.pdf
Sanyam Choudhary Chemistry practical.pdfsanyamsingh5019
 

Recently uploaded (20)

Arihant handbook biology for class 11 .pdf
Arihant handbook biology for class 11 .pdfArihant handbook biology for class 11 .pdf
Arihant handbook biology for class 11 .pdf
 
Grant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingGrant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy Consulting
 
Mastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory InspectionMastering the Unannounced Regulatory Inspection
Mastering the Unannounced Regulatory Inspection
 
Hybridoma Technology ( Production , Purification , and Application )
Hybridoma Technology  ( Production , Purification , and Application  ) Hybridoma Technology  ( Production , Purification , and Application  )
Hybridoma Technology ( Production , Purification , and Application )
 
A Critique of the Proposed National Education Policy Reform
A Critique of the Proposed National Education Policy ReformA Critique of the Proposed National Education Policy Reform
A Critique of the Proposed National Education Policy Reform
 
Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)
 
Paris 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activityParis 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activity
 
Staff of Color (SOC) Retention Efforts DDSD
Staff of Color (SOC) Retention Efforts DDSDStaff of Color (SOC) Retention Efforts DDSD
Staff of Color (SOC) Retention Efforts DDSD
 
mini mental status format.docx
mini    mental       status     format.docxmini    mental       status     format.docx
mini mental status format.docx
 
URLs and Routing in the Odoo 17 Website App
URLs and Routing in the Odoo 17 Website AppURLs and Routing in the Odoo 17 Website App
URLs and Routing in the Odoo 17 Website App
 
Introduction to AI in Higher Education_draft.pptx
Introduction to AI in Higher Education_draft.pptxIntroduction to AI in Higher Education_draft.pptx
Introduction to AI in Higher Education_draft.pptx
 
Introduction to ArtificiaI Intelligence in Higher Education
Introduction to ArtificiaI Intelligence in Higher EducationIntroduction to ArtificiaI Intelligence in Higher Education
Introduction to ArtificiaI Intelligence in Higher Education
 
microwave assisted reaction. General introduction
microwave assisted reaction. General introductionmicrowave assisted reaction. General introduction
microwave assisted reaction. General introduction
 
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxSOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
 
PSYCHIATRIC History collection FORMAT.pptx
PSYCHIATRIC   History collection FORMAT.pptxPSYCHIATRIC   History collection FORMAT.pptx
PSYCHIATRIC History collection FORMAT.pptx
 
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
 
Alper Gobel In Media Res Media Component
Alper Gobel In Media Res Media ComponentAlper Gobel In Media Res Media Component
Alper Gobel In Media Res Media Component
 
How to Make a Pirate ship Primary Education.pptx
How to Make a Pirate ship Primary Education.pptxHow to Make a Pirate ship Primary Education.pptx
How to Make a Pirate ship Primary Education.pptx
 
Sanyam Choudhary Chemistry practical.pdf
Sanyam Choudhary Chemistry practical.pdfSanyam Choudhary Chemistry practical.pdf
Sanyam Choudhary Chemistry practical.pdf
 
Código Creativo y Arte de Software | Unidad 1
Código Creativo y Arte de Software | Unidad 1Código Creativo y Arte de Software | Unidad 1
Código Creativo y Arte de Software | Unidad 1
 

Computer vision old problems new solutions

  • 1. Computer Vision – Old Problems and New Solutions Gopi Krishna Nuti Vice President, MUST Research vp@must.co.in, ngopikrishna@gmail.com
  • 2. Computer Vision – The (age) old problems • What should a robot do in “Scene understanding”? • Identify colours, brightness etc • Identify objects a.k.a Image Segmentation • Different things • Multiple occurrences of the same thing • Stuff other than things • Distance of things and stuff • Relative and absolute
  • 3. Colour and Brightness Colour spaces • Grayscale, RGB, CMY, • Transparency/Opacity using a fourth attribute Limitations • Does not represent all colours in nature • colour perception highly susceptible to lighting changes. New Solutions • Colour spaces have been expanded greatly. • With micro and macro level differences, ~250 colour spaces are in vogue • HSV, HSL/HSI, YUV, YPbPr, YCbCr etc
  • 5. Old Problem – Image Segmentation • Image is an matrix of numbers. • How to identify the edges of each object • How to recognize the object correctly • Differentiate between “things” (foreground) and “stuff ” (background)
  • 6. Image Segmentation – Old Solutions Solution Family Algorithm Drawbacks Thresholding • Otsu thresholding • Adaptive local thresholding • Mean • Gaussian For reasonably simple scenarios only Edges and Corners • Canny edges, Sobel Hough, Laplace algorithms • Harris Corner detection • Convolution of kernels Unsuitable for noisy/blurry images Region Growing Watershed • Relatively strong at detecting overlapping/touching objects Super Pixels • SLCI Algorithm • Susceptible to noise • Steep increase in algorithmic complexit Clustering • K-means • Fuzzy C-Means (FCM) • Expectation Maximization (EM) • Relies on low level features like colour etc. • Poor performance on complicated images Clustering • Image Pyramid • Carefully controlled environments only • Cannot handle non-affine transformation like rotation, reflection etc. • Occlusions are a big no-no • Compute intensive
  • 7. Image Segmentation – Convolutional Neural Networks • Specialized kind of neural networks • Process data in known grid-like spatial structures • Comprised of large number of layers like convolution, pooling and Fully connected layers • Usually, very very deep. i.e. lots of layers and lots of weight parameters • Non linear Activation Functions are mandatory for learning complex features
  • 9. Evolution of CNN Classifiers 2014 • Regions with CNN Features 2015 • Fast R-CNN • Faster R-CNN • Inception V3 2016 • YOLO • SSD • UberNet 2017 • Mask R- CNN • Pixel wise Instance Segmentation
  • 10. Some Salient points Regions with CNN FeaturesR-CNN • Uses Selective Search • Significantly reduced the search space to ~2000 region proposal • Very Slow and very complicated Designed to solve the problems with R-CNNFast R-CNN • Region Of Interest is treated as a pooling layer • Jointly trains feature extractor, classifier and bounding box regression into a single model • Almost 25 time faster than R-CNN Replace Selective search with region proposal networkFaster R-CNN • 10 times faster than Fast R-CNN You Only Look OnceYOLO • Detection is considered as a regression problem • Extremely fast but less accurate. Struggles with small objects that appear in groups Single Shot Multi box detectorSSD • Faster than YOLO and more accurate as well. Extension of Faster R-CNNMask R-CNN • Predicts the object masks as well as bounding box • Impressive results
  • 11. Old Problem - Depth Perception Normal vision and depth perception expectation Relative depth Optical illusion based on depth Picture of a picture. All pixels have same depth
  • 12. Old Solutions - Depth Perception • Stereo cameras spaced at a fixed distance apart capture the same image. • Remember trigonometry?  • Algorithm Families • Triangulation • Interferometry • Time of Flight • Many Limitations • Cost • Complexity • Controlled environments only
  • 13. New Solutions - Depth Perception • Furious research in progress • Single camera moving between two fixed positions • Monocular Depth perception • Some interesting proposals • Train NN with depth information and semantically segmented image • Use the models for predicting depth in new images
  • 15. Old Problem - Programmers Dilemma • Which image format should I use? • Which image file format should I code for? Do I have to learn reading and writing image files? • Matlab is expensive 
  • 16. New Solution - OpenCV, Python, PILLOW etc • OpenCV • Democratized image processing • A large number of functionalities provided as APIs • Impressive Python bindings and native support for C, Java • Python • PILLOW and many other libraries for reading images • Vectorization and Numpy Arrays
  • 18. Neural Networks • Data hungry. Lots and lots of training data. • Resource hungry and compute intensive. • Overfitting, Underfitting, Stochasticity • Black box
  • 19. Some solutions • Transfer Learning to reduce training time • Hyper parameter tuning • Hardware based solutions for improving performance • On-going research for explainability • On-going research for reducing the training data requirement 3rd generation neural networks
  • 20. Demos