GellineauHuangLee - Revision history

imported>Psych2012: /* Data Collection */

2012-03-22T06:05:25Z

Data Collection

← Older revision		Revision as of 06:05, 22 March 2012
Line 11:		Line 11:
	A series of approximately 137 before and after images were collected off of the internet from various sources including: magazine covers, artist demonstrations and collections on discussion forums. Full body, face and torso masks were individually and manually made for each of these images. These were necessary in order to collect relevant statistics. If an object is added to the after photo that doesn't affect our perception we would only be introducing noise by attempting to fit statistics to it. Therefore, fitting blurring filters are only done over the face and geometric distortions are weighted based on where they occur on the body. This step of image preparation is the only non automatic part of the software and was a problem for our source paper as well.		A series of approximately 137 before and after images were collected off of the internet from various sources including: magazine covers, artist demonstrations and collections on discussion forums. Full body, face and torso masks were individually and manually made for each of these images. These were necessary in order to collect relevant statistics. If an object is added to the after photo that doesn't affect our perception we would only be introducing noise by attempting to fit statistics to it. Therefore, fitting blurring filters are only done over the face and geometric distortions are weighted based on where they occur on the body. This step of image preparation is the only non automatic part of the software and was a problem for our source paper as well.

	To collect all of the user data a website was also constructed. This website allowed a user to rate the degree of image manipulation on a scale from 1 to 5 for 70 photos chosen at random from our set of 137. We then used Google's form interface to have that information sent back to us for aggregation.		To collect all of the user data a website was also constructed ([http://www.stanford.edu/~arion http://www.stanford.edu/~arion ]). This website allowed a user to rate the degree of image manipulation on a scale from 1 to 5 for 70 photos chosen at random from our set of 137. We then used Google's form interface to have that information sent back to us for aggregation.

	[[File:Website_Photo.png]][[File:Standard_Error.jpg]]		[[File:Website_Photo.png]][[File:Standard_Error.jpg]]

imported>Psych2012: /* Dataset Filtering */

2012-03-22T06:02:17Z

Dataset Filtering

← Older revision		Revision as of 06:02, 22 March 2012
Line 102:		Line 102:

	=== Parameters ===		=== Parameters ===
	Due to potential implementation flaws in our algorithms, or the way certain images reacted with the algorithms, some of the parameter values produced were unusually large with respect to the trend. These images were also filtered out to maintain a consistency among the parameters, and also such that parameter normalization will not be askew because of these large values.		Due to potential implementation flaws in our algorithms and photomasks, or the way certain images reacted with the algorithms, some of the parameter values produced were unusually large with respect to the trend. These images were also filtered out to maintain a consistency among the parameters, and also such that parameter normalization will not be askew because of these large values.

	In the below graphs, the sorted rating distribution and the corresponding predictions are shown first, followed by a plot of the eight parameters of the corresponding photos. In the pre-filtered selection, you can see very large and clear spikes signifying our outlier parameter values. These photos are filtered out of our training on the next try, and the result is shown in the plots on the right.		In the below graphs, the sorted rating distribution and the corresponding predictions are shown first, followed by a plot of the eight parameters of the corresponding photos. In the pre-filtered selection, you can see very large and clear spikes signifying our outlier parameter values. These photos are filtered out of our training on the next try, and the result is shown in the plots on the right.

imported>Psych2012: /* Image Results */

2012-03-22T05:54:10Z

Image Results

← Older revision		Revision as of 05:54, 22 March 2012
Line 150:		Line 150:
	[[File:ImageComparisons.jpg\|frame\|center\|C and R indicate Classification and Regression results, respectively. The numbers in black are user aggregate ratings, whereas the red numbers are predictions from our model]]		[[File:ImageComparisons.jpg\|frame\|center\|C and R indicate Classification and Regression results, respectively. The numbers in black are user aggregate ratings, whereas the red numbers are predictions from our model]]

	Our model was fairly spot on for the first two selected photos of Kim Kardashian and Megan Fox. We selected the photo of Kim Kardashian in particular, because it was one of the photos in our possession that Kee and Farid had also rated. It is of interest to know that their photo was rated 3.00 by humans and 2.99 by their model.		Our model was fairly spot on for the first two selected photos of Kim Kardashian and Megan Fox. We selected the photo of Kim Kardashian in particular, because it was one of the photos in our possession that Kee and Farid had also rated. It is of interest to know that their photo was rated 3.00 by humans and 2.99 by their model, which are both very close numerically to our own user ratings and model prediction.

	However, for the next three there were deviations of at least 0.8. We can see that our model has the tendency to predict a value between 2-3, based on these results as well as the correlation plots from before. For photos that vary very little or change in a manner significant to the human eye but not to geometric fitting, such as the last photo, our model has difficulty predicting the great difference. These differences may be a result of the algorithms producing poorly matching parameters, or a result of bad user data skewing another image which share very similar parameters to others.		However, for the next three there were deviations of at least 0.8. We can see that our model has the tendency to predict a value between 2-3, based on these results as well as the correlation plots from before. For photos that vary very little or change in a manner significant to the human eye but not to geometric fitting, such as the last photo, our model has difficulty predicting the great difference. These differences may be a result of the algorithms producing poorly matching parameters, or a result of bad user data skewing another image which share very similar parameters to others.

imported>Psych2012: /* Image Results */

2012-03-22T05:53:30Z

Image Results

← Older revision		Revision as of 05:53, 22 March 2012
Line 150:		Line 150:
	[[File:ImageComparisons.jpg\|frame\|center\|C and R indicate Classification and Regression results, respectively. The numbers in black are user aggregate ratings, whereas the red numbers are predictions from our model]]		[[File:ImageComparisons.jpg\|frame\|center\|C and R indicate Classification and Regression results, respectively. The numbers in black are user aggregate ratings, whereas the red numbers are predictions from our model]]

	Our model was fairly spot on for the first two selected photos of Kim Kardashian and Megan Fox. However, for the next three there were deviations of at least 0.8. We can see that our model has the tendency to predict a value between 2-3, based on these results as well as the correlation plots from before. For photos that vary very little or change in a manner significant to the human eye but not to geometric fitting, such as the last photo, our model has difficulty predicting the great difference. These differences may be a result of the algorithms producing poorly matching parameters, or a result of bad user data skewing another image which share very similar parameters to others.		Our model was fairly spot on for the first two selected photos of Kim Kardashian and Megan Fox. We selected the photo of Kim Kardashian in particular, because it was one of the photos in our possession that Kee and Farid had also rated. It is of interest to know that their photo was rated 3.00 by humans and 2.99 by their model.

			However, for the next three there were deviations of at least 0.8. We can see that our model has the tendency to predict a value between 2-3, based on these results as well as the correlation plots from before. For photos that vary very little or change in a manner significant to the human eye but not to geometric fitting, such as the last photo, our model has difficulty predicting the great difference. These differences may be a result of the algorithms producing poorly matching parameters, or a result of bad user data skewing another image which share very similar parameters to others.

	= Conclusions =		= Conclusions =

imported>Psych2012: /* Image Results */

2012-03-22T05:50:10Z

Image Results

← Older revision		Revision as of 05:50, 22 March 2012
Line 150:		Line 150:
	[[File:ImageComparisons.jpg\|frame\|center\|C and R indicate Classification and Regression results, respectively. The numbers in black are user aggregate ratings, whereas the red numbers are predictions from our model]]		[[File:ImageComparisons.jpg\|frame\|center\|C and R indicate Classification and Regression results, respectively. The numbers in black are user aggregate ratings, whereas the red numbers are predictions from our model]]

	Our model was fairly spot on for the first two selected photos of Kim Kardashian and Megan Fox. However, for the next three there were deviations of at least 0.8. We can see that our model has the tendency to predict a value between 2-3, based on these results as well as the correlation plots from before. For photos that vary very little or change in a manner significant to the human eye but not to geometric fitting, such as the last photo, our model has difficulty predicting the great difference.		Our model was fairly spot on for the first two selected photos of Kim Kardashian and Megan Fox. However, for the next three there were deviations of at least 0.8. We can see that our model has the tendency to predict a value between 2-3, based on these results as well as the correlation plots from before. For photos that vary very little or change in a manner significant to the human eye but not to geometric fitting, such as the last photo, our model has difficulty predicting the great difference. These differences may be a result of the algorithms producing poorly matching parameters, or a result of bad user data skewing another image which share very similar parameters to others.

	= Conclusions =		= Conclusions =

imported>Psych2012: /* Supervised Learning */

2012-03-22T05:44:53Z

Supervised Learning

← Older revision		Revision as of 05:44, 22 March 2012
Line 115:		Line 115:
	Following the proper processing of the data, all the parameters were normalized to a range between [-1,1], meaning a median of 0 and a variance of 1. These were done with respect to the same variables over all the photos. These parameters were saved into a .mat file that could be loaded straight into the LIBSVM software, which was developed by Chih-Chung Chang and Chih-Jen Lin at the National Taiwan University.		Following the proper processing of the data, all the parameters were normalized to a range between [-1,1], meaning a median of 0 and a variance of 1. These were done with respect to the same variables over all the photos. These parameters were saved into a .mat file that could be loaded straight into the LIBSVM software, which was developed by Chih-Chung Chang and Chih-Jen Lin at the National Taiwan University.

	[[File:SVM.png\|thumb\|right\|300\|Example of classification by a Support Vector Machine (SVM)]]		[[File:SVM.png\|thumb\|right\|300\|Example of classification by a Support Vector Machine (SVM). Kernel parameters adjust how well the dividing line fits.]]

	=== Classification and Regression ===		=== Classification and Regression ===

imported>Psych2012: /* Supervised Learning */

2012-03-22T05:43:43Z

Supervised Learning

← Older revision		Revision as of 05:43, 22 March 2012
Line 115:		Line 115:
	Following the proper processing of the data, all the parameters were normalized to a range between [-1,1], meaning a median of 0 and a variance of 1. These were done with respect to the same variables over all the photos. These parameters were saved into a .mat file that could be loaded straight into the LIBSVM software, which was developed by Chih-Chung Chang and Chih-Jen Lin at the National Taiwan University.		Following the proper processing of the data, all the parameters were normalized to a range between [-1,1], meaning a median of 0 and a variance of 1. These were done with respect to the same variables over all the photos. These parameters were saved into a .mat file that could be loaded straight into the LIBSVM software, which was developed by Chih-Chung Chang and Chih-Jen Lin at the National Taiwan University.

	[[File:SVM.png\|~~frame~~\|right\|300\|Example of classification by a Support Vector Machine (SVM)]]		[[File:SVM.png\|thumb\|right\|300\|Example of classification by a Support Vector Machine (SVM)]]

	=== Classification and Regression ===		=== Classification and Regression ===

imported>Psych2012: /* Supervised Learning */

2012-03-22T05:43:29Z

Supervised Learning

← Older revision		Revision as of 05:43, 22 March 2012
Line 115:		Line 115:
	Following the proper processing of the data, all the parameters were normalized to a range between [-1,1], meaning a median of 0 and a variance of 1. These were done with respect to the same variables over all the photos. These parameters were saved into a .mat file that could be loaded straight into the LIBSVM software, which was developed by Chih-Chung Chang and Chih-Jen Lin at the National Taiwan University.		Following the proper processing of the data, all the parameters were normalized to a range between [-1,1], meaning a median of 0 and a variance of 1. These were done with respect to the same variables over all the photos. These parameters were saved into a .mat file that could be loaded straight into the LIBSVM software, which was developed by Chih-Chung Chang and Chih-Jen Lin at the National Taiwan University.

	[[SVM.png\|frame\|right\|300\|Example of classification by a Support Vector Machine (SVM)]]		[[File:SVM.png\|frame\|right\|300\|Example of classification by a Support Vector Machine (SVM)]]

	=== Classification and Regression ===		=== Classification and Regression ===

imported>Psych2012: /* Supervised Learning */

2012-03-22T05:43:19Z

Supervised Learning

← Older revision		Revision as of 05:43, 22 March 2012
Line 114:		Line 114:

	Following the proper processing of the data, all the parameters were normalized to a range between [-1,1], meaning a median of 0 and a variance of 1. These were done with respect to the same variables over all the photos. These parameters were saved into a .mat file that could be loaded straight into the LIBSVM software, which was developed by Chih-Chung Chang and Chih-Jen Lin at the National Taiwan University.		Following the proper processing of the data, all the parameters were normalized to a range between [-1,1], meaning a median of 0 and a variance of 1. These were done with respect to the same variables over all the photos. These parameters were saved into a .mat file that could be loaded straight into the LIBSVM software, which was developed by Chih-Chung Chang and Chih-Jen Lin at the National Taiwan University.

			[[SVM.png\|frame\|right\|300\|Example of classification by a Support Vector Machine (SVM)]]

	=== Classification and Regression ===		=== Classification and Regression ===

imported>Psych2012: /* Structural Similarity (SSIM) */

2012-03-22T05:37:02Z

Structural Similarity (SSIM)

← Older revision		Revision as of 05:37, 22 March 2012
Line 76:		Line 76:

	*As shown in the following image, the skin has been greatly smoothed as indicated by large SSIM values.		*As shown in the following image, the skin has been greatly smoothed as indicated by large SSIM values.
	[[File:Ssimexample48.jpg]]		[[File:Ssimexample48.jpg\|center]]
	* For this algorithm we used Matlab code from the research group in ECE, University of Waterloo [https://ece.uwaterloo.ca/~z70wang/research/ssim/]		* For this algorithm we used Matlab code from the research group in ECE, University of Waterloo [https://ece.uwaterloo.ca/~z70wang/research/ssim/]


	=== Perceptual Distortion ===		=== Perceptual Distortion ===