Artistic Style-Transfer

-
Artistic Style-Transfer

Output


Description:

It has been shown that a convolutional neural net algorithm can distinguish between the content
of a piece of art and the style that it was painted in ([1] Leon Gatys). For our final project, we would like to explore this idea in the context of image processing. Specifically, we want to create an image filter that transfers the style of one painting to the content of another image. A clear motivation for finding a solution is for applications that handle many images at a time or for applications that cannot tolerate the training/learning time overhead that comes with the CNN([2] Michael Elad).

Proposed Methods:
 0. Define style transfer from style of image 2 to content of image 1
1. Extract the “content” from image 1
a. This may be achieved by feature detection (edges, corners, lines, circles, uniform
b. Rank which features are more important to the scene overall - some metrics that
may be considered are nominal size of the feature, centricity, brightness, color,
contrast, etc
2. Extract the “content” from image 2
3. Extract the “style” from image 2
a. This may be accomplished by segmenting the image and trying to find key similarities between different patches i.e. themes throughout the image
b. Map styles to features
4. Find sufficiently matched areas of “content” between image 1 and 2 and apply the appropriate “style” that fits the content given : its ranked importance in the scene, how similar it is to the “content” of image 2,
5. Fill in empty spaces and stitch / blend the various areas of the image

References:
[1] Leon A. Gatys, Alexander S. Ecker,Matthias Bethge. “A Neural Algorithm of Artistic Style.”
https://arxiv.org/pdf/1508.06576.pdf
[2] Michael Elad and Peyman Milanfar “Style-Transfer via Texture-Synthesis” arXiv:1609.03057
[3] Wei Zhang, Chen Cao, Shifeng Chen, Jianzhuang Liu, Senior Member, IEEE, and Xiaoou
Tang, Fellow, IEEE “Style Transfer Via Image Component Analysis"
ieeexplore.ieee.org/iel7/6046/6630084/06522845.pdf
[4] V. Kwatra, I. Essa, A. Bobick, and N. Kwatra, “Texture Optimization for Example-Based
Synthesis”, ACM ToG, Vol. 24, No. 3, pp. 795-802, 2005.

FOR BASE PAPER PLEASE MAIL US

DOWNLOAD SOURCE CODE CLICK HERE

Comments

Post a Comment

Popular posts from this blog

Using Image Processing to Identify and Score Darts thrown into a Dartboard

-
Image
✔️Using Image Processing to Identify and Score Darts thrown into a Dartboard ✔️Introduction The game of darts is a throwing sport in which participants toss projectiles into a circular target  attached to a vertical surface. The target is divided into many regions which correspond to different point and multiplier values. Darts is commonly played across North America and Europe and is a popular past time for many so an application that allows players to more conveniently keep score would be widely  beneficial. “Darts” is a general term for a targeting game following this basic premise and many game variations exist within this archetype; all utilizing the standard dart projectiles with a regulation dart board. Each game variant may have different objectives for which players to aim but identifying the region in  which the dart has hit in the dartboard is necessary for proper scoring. This project proposes the use of image processing to identify thrown da...
Read more

Create Pointillism Art with 3 Primary Colors from Natural Images

-
Image
Create Pointillism Art with 3 Primary Colors from Natural Images Description Pointillism is a branch of impressionism that can be dated back to the late 19th century. It is a painting technique that only uses tiny, distinct dots to form patterns of color. It enjoys a duality in being both discrete up close (the dots) and continuous from distance (the patterns). Combining this artistic inspiration with the techniques of digital image processing, we want to develop a special image filter that creates pointillism art from ordinary digital images. Plan he process of creating pointillism art will be as followed: (1) We take an image. (2) We will apply various image processing techniques to our image, such as blurring the image with a structuring element that is larger and proportional to the size of the dots we want to use in our pointil...
Read more

Chess Board Detection

-
Image
 Chess Board Detection ✔️  Introduction Chinese chess is one of the most popular board games in China. It is a two-player strategy board  game set up with 32 chess pieces on a board nine lines wide and ten lines long. The chess pieces  are all of the same flat circular disk shape. Each piece is labeled with a Chinese character to  represent one of the seven types. The color of the piece indicates the player‘s ownership. ✔️ Project Goal The goal of the proposed project is to correctly recognize the state of a Chinese chess game by  processing the images captured by the camera of an Android mobile phone. With the essential  information extracted from the images, we will be able to save and share the record of a game  very efficiently. ✔️ Work Flow To reach the goal, we need to detect the chess board, identify the location of each chess piece and  recognize the type of the piece. Chess Board Detection To ext...
Read more