Image Enhancement using Machine Learning

-
Image Enhancement using Machine Learning

 OUTPUT



OVERVIEW

Automatic image enhancement is an active field of research and is used widely in professional image processing software. For our project, we want to create an automatic image enhancement tool that learns a user’s preferences so that subsequent images can be automatically enhanced in a personalized
way. Our work will be mainly derived from [1]. The parameters learned in [1] are associated with
contrast and color correction. We will attempt to learn these parameters, and if time permits, experiment with other parameters as well.

The first part of this project is to select an optimal subset of training images from a large set of
images, using the optimization technique described in [1] and [3]. The subset will be around 15-20
training images. For each training image, there will be a large possible number of combinations of
parameters (depending on how many we choose to learn). To reduce the subset of possible parameter
combinations used for training, we can apply the same optimization mentioned earlier. In the end, we will get 8-10 “optimal” parameter combinations per training image, which again represent the parameter space maximally. By doing these two steps, the amount of training time per user is lower, and the number of computations to train is also lower. After we have our training set, we will perform user studies on 5 to 7 subjects to acquire personalized training data. The parameter selection algorithm essentially uses a distance metric to find the closest neighbor in the training set to the test image and applies the parameters accordingly. We plan to form an optimal linear combination of multiple distance metrics to best match the test image. We will then test our algorithm and compare results to a few professional auto enhancement tools. Also, if time permits, we would like to make the enhancement tool more content aware using some principles mentioned in [2]. Techniques in [4] can also be used to preprocess the image before the personalized enhancement step.

In conclusion, we expect the results of the user study to indicate whether or not people would
prefer a personalized enhancement tool over a conventional auto-enhancement tool found in common
image processing software.

We will NOT​ be using an Android device

References:

[1] Kang, Sing Bing, Ashish Kapoor, and Dani Lischinski. "Personalization of image enhancement."
Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on. IEEE, 2010.
[2] Kaufman, Liad, Dani Lischinski, and Michael Werman. "Content-Aware Automatic Photo
Enhancement." Computer Graphics Forum. Vol. 31. No. 8. Blackwell Publishing Ltd, 2012.
[3] Krause, Andreas, Ajit Singh, and Carlos Guestrin. "Near-optimal sensor placements in Gaussian
processes: Theory, efficient algorithms and empirical studies." Journal of Machine Learning Research
9.Feb (2008): 235-284.
[4] Celik, Turgay, and Tardi Tjahjadi. "Automatic image equalization and contrast enhancement using
Gaussian mixture modeling." IEEE Transactions on Image Processing 21.1 (2012): 145-156.

FOR BASE PAPER PLEASE MAIL US

DOWNLOAD SOURCE CODE CLICK HERE

Comments

Post a Comment

Popular posts from this blog

Light Field Images for Background Removal

-
Image
Light Field Images for Background Removal OUTPUT OVERVIEW Standard edge detection or foreground/background separation techniques, such as Otzu’smethod, require color or intensity differences between the background and regions that need tobe separated. For example, green screens are routinely set up as the background in a scene so thatthere is a clear difference in color between the background and foreground.Light filed images, captured in 4D and passively containing depth information for thescene can be used to approximate this effect. Depth estimation in the scene alone could provide a metric to separate the foreground and background, but more sophisticated methods are available.Considering the edge detection from a single image from a single viewpoint and analyzing the depths from the light field around the edges in that image, occluded edges and intensity or color edges can be distinguished. Along with the rest of the depth information this can allow the foreground and b
Read more

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 darts and to det
Read more

Digital Make up Face Generation

-
Image
Digital Make up Face Generation Goal Current make-up applications rely on using photoshop tools to apply makeup on the target's digital  faces and generate results. While these applications allow customization, a customer who wants to  quickly decide on the type of makeup kit to buy at a store will not find it useful. The customer might just  want to find out how the make-up look on the cover or billboard will look like on her face. The goal of  this project is to use an existing reference image of another subject with a make-up applied, and  transfer the reference's make up on the target's face. The application can be further extended to photo  retouching and illumination transfer from the reference image to the target. Methodology In order to transfer the make-up from the reference onto target in a pixel by pixel basis, the areas of  interest must align. Face features such as eyes, nose, mouth and contours of the face, will be recognized  using Active Shape
Read more