A presentation on Image Recognition, the basic definition and working of Image Recognition, Edge Detection, Neural Networks, use of Convolutional Neural Network in Image Recognition, Applications, Future Scope and Conclusion
3. Motivation
•Makes computer vision a possibility,
hence enhancing power of Artificial
Intelligence.
•There is significant interest in creating
light weight and mobile systems that can
identify objects using vision
•Numerous practical application makes
Image Recognition a motivating field of
study.
4. Studying the basic principles of
Image Recognition, and
understanding the practical
applications with state of art
facilities and tremendous future
possibilities.
Objective
5. What is Image Recognition?
Image recognition is the process of identifying and
detecting an object or a feature in a Digital Image.
It is also known as Computer Vision.
6. What is a digital image?
A digital image is a representation of a 2D image using
a finite set of digital values for each pixel.
A pixel is the smallest independent block of a digital
image.
The digital values of these pixels are processed and
used in Image Recognition and in other areas of Image
Processing.
8. Steps in Image Recognition
Data acquisition and sensing
Preprocessing
Removal of noise
Isolation of patterns of interest from the background
(Segmentation)
Feature Extraction
Finding a new representation in terms of features
(Detection)
9. Steps in Image Recognition
Model Learning and Estimation
-Learning a mapping between features and
pattern groups.
Classification
- Using learned models to assign a pattern to a
predefined category
Post processing
- Evaluation of confidence in decisions.
- Exploitation of context to improve performances.
10. Edge Detection
•Images are preprocessed to be fed as input into the network.
•Preprocessing helps in better feature extraction from the image.
11. Edge detection
Common methods of Edge Detection:-
• Canny Edge Detection: Uses calculus
of variations (most widely used) –
optimizes a given functional
• Sobel Edge Detection: It is a discrete
differentiation operator, computing an
approximation of the gradient of the
image intensity function
12. Classification using Neural Networks
A neural network is a computer system modeled on a
human brain.
It is extensively used in Image Recognition / Image
processing
Implemented using Convolutional Neural Network to
detect edges.
13. What is a neural network?
An artificial neural network is an interconnected group of nodes, akin to the vast
network of neurons in a brain. Here, each circular node represents an artificial neuron
and an arrow represents a connection from the output of one neuron to the input of
another. Advantages of using Neural Network for Image Recognition is increased
accuracy up to 95% and it does not require separate training for each data set.
14. Neural Network for Image
Recognition ( CNN )
•Convolution Neural
Networks are used for
Image Recognition.
•Convolutions are
implemented using Fast
Fourier Transforms.
F[f*g] = F[f]F[g]
16. Practical Applications
Medical Imaging
extensively used for cancer detection, retinopathy
detection, improving quality of
imperfect images.
Industrial Application
fault detection in manufacturing
17. Practical Applications
Security
- Face and fingerprint recognition
- Law enforcement
Applications for creative media
- Deep dream
- Neural style transfer (prizma)
- Human and Computer interface
18. Practical Applications
Geographic Information Systems
- Terrain Classification
- Meteorology
- Global inventory of human
settlement
Astronomy
- Enhancement of telescopic images
- Recognition of astronomical bodies
- Eg: The Hubble Telescope
19. Future Scope and Conclusion
Image recognition is a futuristic and relatively
unexplored field, with wide areas of practical
applications, including industrial, scientific and
medical applications.
This field has a lot of potential for development and
implementation in new areas like space exploration,
processing signal images, computer vision etc.
A lot of tasks can be automated using Image
Recognition like processing cheques in banks etc.
20. References:
Edge Detection in Digital Image Processing by Debosmit Ray (Research Paper)
Pattern Recognition in Medical Imaging – Anke Mayer & Base (Book)
Image Style Transfer Using Convolutional Neural Network – Leon A. Gatys,
Alexander S. Ecker, Matthias Bethge (Research Paper)
Image-based pattern recognition project by Dr. Jian Jiun Ding, Ph.D from National
Taiwan University, Taiwan.
Machine Learning is fun – Adam Geitey (Blog)
Image Recognition in Industrial Application – Mobgen – A part a Accenture Digital
– 22/02/2016 (Article)
Wikipedia and google for images and basic definitions.
Editor's Notes
The proposal for Image Recognition was first invented by Paul Viola and Michael Jones. Their demonstration was first showed on face being detected in real time on a webcam feed was the most stunning demonstration of the Computer Vision. Every few years a new idea came along that forces the people to pause and take a note.
For the location, we need to be able to have some measure that increases as the localization improves. So, we use the reciprocal of the root-mean-squared distance of the marked edge from the centre of the true edge.