Scribd
Upload
463 views

Artificial Intelligence in Image Processing

Duke University researchers have developed an AI tool called PULSE that can generate high-resolution images of faces from low-resolution inputs with unprecedented detail. PULSE uses a generative adversarial network to score generated high-resolution images and search for ones that best match the input when downscaled, rather than slowly adding pixels like previous methods. It can create realistic portraits with up to 64 times more pixels than the original while adding subtle details. In tests, images generated by PULSE were rated nearly as high-quality as actual photos of people. The technique could potentially be applied to other types of images in fields like medicine and astronomy.

Uploaded by

Ashutosh Prasad Yadav
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
463 views

Artificial Intelligence in Image Processing

Duke University researchers have developed an AI tool called PULSE that can generate high-resolution images of faces from low-resolution inputs with unprecedented detail. PULSE uses a generative adversarial network to score generated high-resolution images and search for ones that best match the input when downscaled, rather than slowly adding pixels like previous methods. It can create realistic portraits with up to 64 times more pixels than the original while adding subtle details. In tests, images generated by PULSE were rated nearly as high-quality as actual photos of people. The technique could potentially be applied to other types of images in fields like medicine and astronomy.

Uploaded by

Ashutosh Prasad Yadav
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 12

ARTIFICIAL INTELLIGENCE IN IMAGE

PROCESSING
[email protected]
Name: Ashutosh Prasad Yadav
 
FINDINGS:
It is the researchers of Duke University have made the AI tool that can turn fuzzy, unrecognizable
images of people’s faces into eerily convincing portraits generated by computers, in more detail than
ever. Previous methods can scale up to eight times its original resolution for a face image. But the
Duke team has come up with a way to take a handful of pixels and create realistic-looking faces with
up to 64 times the size, ‘imagining’ features like fine lines, eyelashes, and stubbles that weren’t
there in the first place.

“Never before have super-resolution images been created with this much detail at this resolution,”
Duke computer scientist Cynthia Rudin, who led the team, said.

The program cannot be used to recognize individuals; the researchers say: it does not transform an
unrecognizable out-of-focus photo from a surveillance camera into a crystal-clear image of a real
individual. Instead, it is able to create new faces that do not exist but look plausibly real.

The researchers have focused on faces as the proof of concept, the same technique could, in theory,
take low-res shots of almost anything and create sharp, realistic-looking images, with applications
ranging from medicine and microscopy to astronomy and satellite imaging, said co-author Sachit
Menon ’20, who just graduated from Duke with a double-major in mathematics and computer
science.

At the 2020 Conference on Computer Vision and Pattern Recognition (CVPR), held practically from
June 14 to June 19, the researchers will present their method, called PULSE.

Traditional approaches take a low-resolution image and ‘guess’ what extra pixels are needed by
trying to match them on average in high-resolution images that the computer has seen before. As a
result of this average, textured hair and skin areas that may not perfectly align from one pixel to the
next end up looking fuzzy and indistinguishable.

Unit Duke has come up with a new strategy. Instead of taking a low-resolution image and slowly
adding new detail, the system scores AI-generated examples of high-resolution faces, searching for
ones that look like the input image as much as possible when shrunk to the same size.

The team has used a machine learning tool called a “generative adversarial network,” or GAN, which
is two neural networks trained on the same photo data set. One network comes up with human
faces created by AI which mimics those on which it was trained, while the other takes this output
and decides whether it is sufficiently convincing to be mistaken for the real thing.

Rudin said that PULSE can create realistic-looking images from noisy, poor-quality inputs other
methods cannot. It can spit out any number of uncannily lifelike possibilities from a single blurred
image of a face, each of which appears subtly as a different person.

In a few seconds, the system can convert a face image of 16×16-pixels to 1024 x 1024 pixels, adding
more than a million pixels, similar to HD resolution. In the computer-generated versions, details such
as pores, wrinkles, and wisps of hair that are imperceptible in the low-res photos become crisp and
clear.

The researchers asked 40 people to rate 1,440 images generated on a scale of one to five via PULSE
and five other scaling methods, and PULSE did the best, scoring nearly as high-quality photos of
actual people. 
INTRODUCTION:
From the inception of AI, image processing to be incorporated in smart
systems is a perennial project for people working on it. In its initial phase, it
required a lot of manual input, providing instructions to computers, to get
some output. These machines, or known as Expert Systems, were trained to
recognize images.
According to Gartner, the total number of AI adopters across different
industries has increased by 270% over the last 4 years.
We want the machines to do more than just recognize images. With the
advancement in Artificial Intelligence, it has helped engineers to design
software that can impersonate the human capacity to observe, understand,
recognize and describe the photo and video content with great accuracy.
In general terms, manipulating an image to amplify the same to generate
information out of it is called image processing. There are 2 methods of image
processing:
– Analog image processing, which is used for processing photographs,
printouts, and other image hard copies.
– Digital image processing, which is used for manipulating digital images with
the help of complex algorithms
Main Purpose of Image Processing
• Representing processed data in a visual way one can understand, for
instance, giving a visual form to invisible objects.
• To improve the processed image quality, image sharpening and
restoration works well.
• Image convalescence helps in searching images.
• Helps to measure objects in the image.
• With pattern recognition, it becomes easy to classify objects in the
image, locate their position and get an overall understanding of the scene.

 
RELEVANT DETAILS OF CASE:
Types of Image Processing Phases-
There are 8 phases for image processing which goes step-wise:

• Image acquisition: Captures the image with a sensor and


converts it into a manageable entity

• Image enhancement The input image quality is improved


and also extracts details hidden in it

• Image restoration Any possible corruption like blur,


noise, or camera misfocus is removed
to get a cleaner vision on probabilistic
and mathematical model basis
• Colour image processing The coloured images and varied
colour spaces are processed with
pseudo-colour or RGB processing way.
• Image compression and decompression This allows for changes in image
resolution and size, be it for reduction
or restoring images depending on the
need.
• Morphological processing Defines the object structure and
shape in the image.

• Image recognition For a particular object, the specific


features are identified in the image
and techniques like object detection
are used for the same.

• Representation and description It is all about visualizing the processed


data.
ANALYSIS:

It is not easy to accomplish processing massive amounts of data manually.


Here’s where Artificial Intelligence and machine learning algorithms become
very helpful. The use of ML and AI to boost the data processing speed and
generate quality image result. But of course, in order to get high-quality
results, all we need is to pick the right tools and methods.
• Image processing methods, techniques, and tools
The images captured with regular sensors need pre-processing as some could
contain too much noise or are misfocused. There are two detection techniques
to be used for processing digital images as well as for pre-processing.
• Filtering
Used to modify and enhance the input image. With various filters available,
certain features in the image can be emphasized or removed, can also reduce
the image noise and so on.
• Edge detection
Used for data extraction and image segmentation, to find meaningful object
edges in the images that are pre-processed.
To make things easier, there are specific libraries and frameworks that can be
used to implement image processing functionalities.
• Open-source libraries for AI-based image processing
Computer vision libraries contain common image processing functions and
algorithms. Several open-source libraries are available that can be used to
develop image processing and computer vision features.
• OpenCV
The Open Source Computer Vision Library (OpenCV) is a popular computer
vision library that provides ample algorithms and functions that support the
algorithms. It includes various modules like, image processing module, object
detection module, and machine learning module to name some. This library
can be used to perform image processing tasks like image acquisition,
compression, enhancement, restoration, and data extraction.
• VXL
The VXL library is a set of libraries for computer vision and implements a
number of popular computer vision technology algorithms and related
functionalities.
• AForge.NET
AForge.NET, a computer vision library with multiple libraries that can be used
for image processing and computer vision to neural networks and fuzzy
computations. Additionally, AForge.NET provides help files and a set of sample
applications demonstrating how to use this framework.
• LTI-Lib
LTI-Lib library makes it easier to share and maintain code while still providing
fast algorithms for real-world applications.
It provides a wide range of features that can be used for solving mathematical
problems, a set of classification tools, and multiple image processing and
computer vision algorithms.
REFLECTION:
I personally am very excited to see where we land with such fast changes in
method of image processing. I have been in image processing for years now
and from my experience I can say that the speed at which AI in image
processing is developing and changing the whole industry in recent years,
changes of this kind has never been seen by this industry.
Things which were impossible like upscaling images with creating new details,
can now be achieved in matter of seconds, face map can be made to replace a
face from a video with someone’s else face. Things like this was next to
impossible few years ago. No one knows what will be the next major
breakthrough in this field, but one this can be said surely is that AI is the future
of image processing.

JUSTIFICATION:
AI base image processing is the future of image processing without any doubt.
A person has his limit as to how much image can he/she edit and how deep
can they go while editing, focusing on each and every pixel is not possible for
any human plus editing the image in an content aware method is very hard
even for the best of the professionals and it also needs huge amount of time.
AI can do image processing in factor of minutes which would have required
huge amount of man hour. Companies are also now Focusing on AI based
image processing, companies like Adobe has started to implement AI in their
recent products.

CONCLUSION:
With AI algorithms, machines can be taught to interpret images for a particular
task based on the requirement. There are immense opportunities to
implement AI based image processing in every industry. It depends on how you
want to make the most out of it.
The road to building a better AI for image processing will lead us to a world
where camera will have intelligence like a human being. Self-driving cars to
detecting asteroid in piles of data, all uses AI base image processing. AI can
also be used in medical sector as well.
REFERENCES:
[1] Raveena Gohil, “Image Processing in AI – A Beginner’s Guide”, Wed 6 Feb
2019
[2] Passionate Analytics, “Artificial intelligence in Image processing: Case
Study”, June 24, 2020
[3] S.s. Kumar, “Artificial Intelligence and Image Processing Approaches in
Damage Assessment and Material Evaluation”, December, 2005

 
APPENDICES:

You might also like