AAMToolbox simplify point model - Revision history

AndrewBangham at 20:39, 20 February 2012

2012-02-20T20:39:40Z

← Older revision		Revision as of 20:39, 20 February 2012
Line 4:		Line 4:

	[[File:Loading_point_model_walk_AAMToolbox.png\|700px\|Loading a point model into ModelViewer]]<br>		[[File:Loading_point_model_walk_AAMToolbox.png\|700px\|Loading a point model into ModelViewer]]<br>
	In the act of''' loading an image file''' (highlighted in sub-window). Red ellipses highlight the buttons needed to load an image - actually the point model associated with an image - calculate the associated weights and reset the model back to the mean again.<br>		In the act of''' loading an image file''' (highlighted in sub-window). Red ellipses highlight the buttons needed to load an image - actually the point model associated with an image - calculate the associated weights and reset the model back to the mean again. It is important to reset back to the mean before each import.<br>
	~~You can also ''~~'load ~~point models directly''' but clicking~~ the ''Import Ref. shape'' button.<br><br>		The reset is required because each time a point model is imported, it's deviation from the mean is added to the current model. Thus, to add the deviations for one place in shape space to another, first load the other (reference shape) by using the ''Import Ref. shape'' button.<br><br>
	[[File:Deviations_of_a_particular_point_model_AAMToolbox.png\|700px\|Point model in ModelViewer]]<br>		[[File:Deviations_of_a_particular_point_model_AAMToolbox.png\|700px\|Point model in ModelViewer]]<br>
	Result of Calculating the Weights (see button) . Notice that the bars representing the principle components have been adjusted to show how far this approximation to the point model deviates from the mean.<br><br>		Result of Calculating the Weights (see button) . Notice that the bars representing the principle components have been adjusted to show how far this approximation to the point model deviates from the mean.<br><br>

	Here, we have referred to''' shape space but what is it'''? Project into shape space? See next tutorial.		Here, we have referred to''' shape space but what is it'''? Project into shape space? See next tutorial.

AndrewBangham at 19:36, 20 February 2012

2012-02-20T19:36:46Z

← Older revision		Revision as of 19:36, 20 February 2012
Line 8:		Line 8:
	[[File:Deviations_of_a_particular_point_model_AAMToolbox.png\|700px\|Point model in ModelViewer]]<br>		[[File:Deviations_of_a_particular_point_model_AAMToolbox.png\|700px\|Point model in ModelViewer]]<br>
	Result of Calculating the Weights (see button) . Notice that the bars representing the principle components have been adjusted to show how far this approximation to the point model deviates from the mean.<br><br>		Result of Calculating the Weights (see button) . Notice that the bars representing the principle components have been adjusted to show how far this approximation to the point model deviates from the mean.<br><br>

			Here, we have referred to''' shape space but what is it'''? Project into shape space? See next tutorial.

AndrewBangham at 19:34, 20 February 2012

2012-02-20T19:34:37Z

← Older revision		Revision as of 19:34, 20 February 2012
Line 1:		Line 1:
	[[Tutorials on the Shape modelling toolbox#1\|Back to Tutorial pages]]<br>		[[Tutorials on the Shape modelling toolbox#1\|Back to Tutorial pages]]<br>
	==<span style="color:Navy;">'''What does it mean''' to best fit the shape model to a particular image point model</span>==		==<span style="color:Navy;">'''What does it mean''' to best fit the shape model to a particular image point model</span>==
	All the point models were used to find the shape model. If there were just two dimensions, this would be similar to fitting a straight line to ''y=ax'' by finding ''a''. In the Cartoons shape model, there are 34*2=68 dimensions yielding 68 components. However, most of these represent noise and the Stats Model Generator found that 95% of the variance could be accounted for by just 5 of the components. So we should (actually, might is a better word) be able to represent any of the point models that we used to build the shape model. Here, we project a particular point model into shape space, take the 5 principle components (setting the rest to zero), and project the result back into our normal viewing space. The result should look similar to the point model itself.<br><br>		All the point models were used to find the shape model. If there were just two dimensions, this would be similar to fitting a straight line to ''y=ax'' by finding ''a''. In the Cartoons shape model, there are 34*2=68 dimensions yielding 68 components. However, most of these represent noise and the Stats Model Generator found that 95% of the variance could be accounted for by just 5 of the components. So we should (actually, might is a better word) be able to represent any of the point models that we used to build the shape model. Here, we '''project a particular point model into shape space, take the 5 principle components (setting the rest to zero), and project the result back into our normal viewing space'''. The result should look similar to the point model itself.<br><br>

	[[File:Loading_point_model_walk_AAMToolbox.png\|700px\|Loading a point model into ModelViewer]]<br>		[[File:Loading_point_model_walk_AAMToolbox.png\|700px\|Loading a point model into ModelViewer]]<br>
	In the act of loading an image file (highlighted in sub-window). Red ellipses highlight the buttons needed to load an image - actually the point model associated with an image - calculate the associated weights and reset the model back to the mean again.<br><br>		In the act of''' loading an image file''' (highlighted in sub-window). Red ellipses highlight the buttons needed to load an image - actually the point model associated with an image - calculate the associated weights and reset the model back to the mean again.<br>
			You can also '''load point models directly''' but clicking the ''Import Ref. shape'' button.<br><br>
	[[File:Deviations_of_a_particular_point_model_AAMToolbox.png\|700px\|Point model in ModelViewer]]<br>		[[File:Deviations_of_a_particular_point_model_AAMToolbox.png\|700px\|Point model in ModelViewer]]<br>
	Result of Calculating the Weights (see button) . Notice that the bars representing the principle components have been adjusted to show how far this approximation to the point model deviates from the mean.<br><br>		Result of Calculating the Weights (see button) . Notice that the bars representing the principle components have been adjusted to show how far this approximation to the point model deviates from the mean.<br><br>

AndrewBangham at 19:32, 20 February 2012

2012-02-20T19:32:03Z

← Older revision		Revision as of 19:32, 20 February 2012
Line 4:		Line 4:

	[[File:Loading_point_model_walk_AAMToolbox.png\|700px\|Loading a point model into ModelViewer]]<br>		[[File:Loading_point_model_walk_AAMToolbox.png\|700px\|Loading a point model into ModelViewer]]<br>
	In the act of loading an image file (highlighted in sub-window). ~~The~~ buttons needed to load an image - actually the point model associated with an image - calculate the associated weights and ~~resetting~~ the model again.<br><br>		In the act of loading an image file (highlighted in sub-window). Red ellipses highlight the buttons needed to load an image - actually the point model associated with an image - calculate the associated weights and reset the model back to the mean again.<br><br>
	[[File:Deviations_of_a_particular_point_model_AAMToolbox.png\|700px\|Point model in ModelViewer]]<br>		[[File:Deviations_of_a_particular_point_model_AAMToolbox.png\|700px\|Point model in ModelViewer]]<br>
	Result of Calculating the Weights (see button) . Notice that <br><br>		Result of Calculating the Weights (see button) . Notice that the bars representing the principle components have been adjusted to show how far this approximation to the point model deviates from the mean.<br><br>

AndrewBangham at 19:30, 20 February 2012

2012-02-20T19:30:01Z

← Older revision		Revision as of 19:30, 20 February 2012
Line 1:		Line 1:
	[[Tutorials on the Shape modelling toolbox#1\|Back to Tutorial pages]]<br>		[[Tutorials on the Shape modelling toolbox#1\|Back to Tutorial pages]]<br>
	==<span style="color:Navy;">'''What does it mean''' to best fit the shape model to a particular image point model</span>==		==<span style="color:Navy;">'''What does it mean''' to best fit the shape model to a particular image point model</span>==
	All the point models were used to find the shape model. ~~This~~ is ~~equivalent~~ to <br>		All the point models were used to find the shape model. If there were just two dimensions, this would be similar to fitting a straight line to ''y=ax'' by finding ''a''. In the Cartoons shape model, there are 34*2=68 dimensions yielding 68 components. However, most of these represent noise and the Stats Model Generator found that 95% of the variance could be accounted for by just 5 of the components. So we should (actually, might is a better word) be able to represent any of the point models that we used to build the shape model. Here, we project a particular point model into shape space, take the 5 principle components (setting the rest to zero), and project the result back into our normal viewing space. The result should look similar to the point model itself.<br><br>
	~~PCA finds all the coefficients need to exactly represent a part~~
	[[File:Loading_point_model_walk_AAMToolbox.png\|700px\|Loading a point model into ModelViewer]]<br>		[[File:Loading_point_model_walk_AAMToolbox.png\|700px\|Loading a point model into ModelViewer]]<br>
	In the act of loading an image file (highlighted in sub-window). The buttons needed to load an image - actually the point model associated with an image - calculate the associated weights and resetting the model again.<br><br>		In the act of loading an image file (highlighted in sub-window). The buttons needed to load an image - actually the point model associated with an image - calculate the associated weights and resetting the model again.<br><br>
	[[File:Deviations_of_a_particular_point_model_AAMToolbox.png\|700px\|Point model in ModelViewer]]<br>		[[File:Deviations_of_a_particular_point_model_AAMToolbox.png\|700px\|Point model in ModelViewer]]<br>
	Result of Calculating the Weights (see button) . Notice that <br><br>		Result of Calculating the Weights (see button) . Notice that <br><br>

AndrewBangham at 18:52, 20 February 2012

2012-02-20T18:52:50Z

← Older revision		Revision as of 18:52, 20 February 2012
Line 1:		Line 1:
	[[Tutorials on the Shape modelling toolbox#1\|Back to Tutorial pages]]<br>		[[Tutorials on the Shape modelling toolbox#1\|Back to Tutorial pages]]<br>
			==<span style="color:Navy;">'''What does it mean''' to best fit the shape model to a particular image point model</span>==
	~~[[File:Walk_model_AAMToolbox.png\|700px\|Model Viewer]]<br><br>~~		All the point models were used to find the shape model. This is equivalent to <br>
	===<span style="color:~~FireBrick~~;">~~Finding the~~ best fit to ~~the~~ point model ~~of an image~~</span>===		PCA finds all the coefficients need to exactly represent a part
	~~{\| border="0" cellpadding="5" cellspacing="3"~~		[[File:Loading_point_model_walk_AAMToolbox.png\|700px\|Loading a point model into ModelViewer]]<br>
	~~\|- valign="top"~~		In the act of loading an image file (highlighted in sub-window). The buttons needed to load an image - actually the point model associated with an image - calculate the associated weights and resetting the model again.<br><br>
	~~\|width="700pt"\|The dots on~~ the ~~right represent the mean positions of the landmarks averaged over all the images in~~ the model. ~~These points mean more~~ to ~~us once they are joined by lines (see above screenshot). Capturing that higher meaning requires more analysis or, as in this case, human interaction (when we created the template).~~<br><br>~~Note that~~ the point ~~models had been normalised to~~ the~~''' same scale, same rotation~~ and ~~same translational''' position~~.<br>		[[File:Deviations_of_a_particular_point_model_AAMToolbox.png\|700px\|Point model in ModelViewer]]<br>
	~~\|width="200pt"\|~~[[File:~~Mean_shape~~.png\|~~200px~~\|~~The Model generator control panel~~]]		Result of Calculating the Weights (see button) . Notice that <br><br>
	\|}

AndrewBangham: Created page with 'Back to Tutorial pages
Model Viewer

===Finding…'

2012-02-20T18:28:35Z

Created page with 'Back to Tutorial pages 700px|Model Viewer ===Finding…'

New page

[[Tutorials on the Shape modelling toolbox#1|Back to Tutorial pages]] 

[[File:Walk_model_AAMToolbox.png|700px|Model Viewer]] 
===Finding the best fit to the point model of an image===
{| border="0" cellpadding="5" cellspacing="3"
|- valign="top"
|width="700pt"|The dots on the right represent the mean positions of the landmarks averaged over all the images in the model. These points mean more to us once they are joined by lines (see above screenshot). Capturing that higher meaning requires more analysis or, as in this case, human interaction (when we created the template). Note that the point models had been normalised to the''' same scale, same rotation and same translational''' position. 
|width="200pt"|[[File:Mean_shape.png|200px|The Model generator control panel]]
|}