Image sensatory Style transfer

using TensorFlow algorithm

Introduction
What does it mean to be an human in the visual world? It does not just
mean just seeing. Countless blind artists could not see, yet they
produced some of the most outstanding artwork of all time. These
people do not just use sight to classify an object, they use touch.
There's something deeper here - texture and color are different parts of
art. As we drive forward in the world of computational photography,
we can see that the latest developments have focused on teaching
machines how to actually create visual beauty. Just like a child, we want
to teach them not only how to classify these images but also how to
construct textures and objects. We want to teach them to be artists.
This is the ambitious goal of this project.
Existing system
• Existing style transfer methods are mostly example-based [13, 25, 24,
7, 21]. The image analogy method [13] aims to determine the
relationship between a pair of images and then apply it to stylize 2
other images. As it is based on finding dense correspondence,
analogy-based approaches [25, 24, 7, 21] often require that a pair of
image depicts the same type of scene. Therefore these methods do
not scale to the setting of arbitrary style images well.
Proposed system
• We formulate style transfer as an image reconstruction process
coupled with feature transformation, i.e., whitening and coloring. The
reconstruction part is responsible for inverting features back to the
RGB space and the feature transformation matches the statistics of a
content image to a style image.
• In this process we use TensorFlow. TensorFlow is the machine
learning algorithm.
Requirements
• s/w requirements:
• Operating system: windows, Linux
• Programming language: python
• Front end: angular

• h/w requirements:
• processer: intel core
• Ram: 4 gb
• HardDisk:40 gb
Output solution
Conclusion
• From a practical point of view, neural style transfer provides people
with a way to create interesting artwork. The ability to generate
artwork of different styles is one type of visual intelligence. style
transfer can also have important applications in photo editing.
Any queries
Thankyou
•