SoC 2008 Masking in GUI - Revision history

Flixh: Undo revision 12364 by Paola09, revert link spamming

2010-05-07T06:34:59Z

Undo revision 12364 by Paola09, revert link spamming

2010-05-07T03:24:39Z

2008-08-19T20:17:25Z

‎Timeline

2008-08-13T21:16:47Z

‎Timeline

2008-08-05T16:49:19Z

‎Timeline

2008-08-05T16:34:14Z

‎User Guide

2008-07-08T01:36:10Z

‎Timeline

2008-06-24T01:49:27Z

‎Basic Polygon Masking

2008-06-24T01:43:34Z

2008-06-03T05:44:00Z

‎Algorithm

← Older revision		Revision as of 06:34, 7 May 2010
Line 279:		Line 279:

	* Multi-label Image Segmentation: In this kind of segmentation problem multiple labels are assigned. For instance different regions of an image can be labeled based on the content of that region eg. people, trees, sky, water, etc.		* Multi-label Image Segmentation: In this kind of segmentation problem multiple labels are assigned. For instance different regions of an image can be labeled based on the content of that region eg. people, trees, sky, water, etc.
−
−
−	~~==Related LInks:==~~
−
−	~~[http://www.healthmuscle.com/'''fat-burning-furnace-review''']~~
−

	==References==		==References==

← Older revision		Revision as of 03:24, 7 May 2010
Line 279:		Line 279:

	* Multi-label Image Segmentation: In this kind of segmentation problem multiple labels are assigned. For instance different regions of an image can be labeled based on the content of that region eg. people, trees, sky, water, etc.		* Multi-label Image Segmentation: In this kind of segmentation problem multiple labels are assigned. For instance different regions of an image can be labeled based on the content of that region eg. people, trees, sky, water, etc.
		+
		+
		+	==Related LInks:==
		+
		+	[http://www.healthmuscle.com/'''fat-burning-furnace-review''']
		+

	==References==		==References==

@@ Line 59: / Line 59: @@
 * Load/Store masks
 **<s>Save Bitmap mask</s>
-**Store brush strokes
+**<s>Store brush strokes</s>
 **<s>Store mask from hugin</s>
 * <s>Integration with Hugin</s>

@@ Line 60: / Line 60: @@
 **<s>Save Bitmap mask</s>
 **Store brush strokes
-**Store mask from hugin
+**<s>Store mask from hugin</s>
-* Integration with Hugin
+* <s>Integration with Hugin</s>
 * Remapping support
 * <s>Implement custom max flow/min cut algorithm (the one that is going to be used initially is under research only license).</s> <s>Use [http://www.boost.org/doc/libs/1_35_0/libs/graph/doc/kolmogorov_max_flow.html kolmogorov_max_flow()] from Boost library (thanks to Stephan Diederich for the suggestion)</s>[Not needed. maxflow v2.2 (GPLed version) is used]

@@ Line 45: / Line 45: @@
 * <s>Allow users to mark regions</s>
 * <s>Zoom in/out</s>
-* LazySnapping without pre-segmentation.
+* <s>LazySnapping without pre-segmentation.</s>
-* Start implementing support for polygon mode editing.
+* <s>Start implementing support for polygon mode editing.</s>
 .2 After Mid Term Evaluation
 * Fix issues with first phase(bugs, usability, etc.)
-**Fix LazySnapping without pre-segmentation.
+**<s>Fix LazySnapping without pre-segmentation.</s>
-**Add preview option and choosing multiple images to display
+**<s>Add preview option and choosing multiple images to display</s>
 **Performing segmentation on overlapped region
 * Undo/Redo operation
 * Load/Store masks
 * Integration with Hugin
 * Remapping support

@@ Line 208: / Line 208: @@
 ==User Guide==
 . Load an image: File->Load Images->(select an image)
-. Edit->Add Point (zoom in/out if requried)
+. Choose PolyEd_Basic from the drop down menu
 . Left click to add point and right click to finish adding points
@@ Line 221: / Line 222: @@
 [[Image:PolyEd_Basic_sample3_1.PNG|300px]]
-[[Image:PolyEd_Basic_sample3_mask.jpg|300px]]
+[[Image:PolyEd_Basic_sample3_mask.jpg|center|300px]]
-[[Image:PolyEd_Basic_sample3_mask.svg|300px]]
 ==Test Dataset==

@@ Line 39: / Line 39: @@
 .1 Before Mid Term Evaluation
-* Stand-alone application for testing the basic framework
+* <s>Stand-alone application for testing the basic framework</s>
-* Second iteration of design
+* <s>Second iteration of design</s>
 Implement a basic framework that can –
-* Take a set of aligned images of a particular format
+* <s>Take a set of aligned images of a particular format</s>
-* Allow users to mark regions
+* <s>Allow users to mark regions</s>
-* Zoom in/out
+* <s>Zoom in/out</s>
-* Incorporate algorithm to learn the color model from the user defined area (more likely to be needed for 3D segmentation)
+* LazySnapping without pre-segmentation.
 * Start implementing support for polygon mode editing.
 .2 After Mid Term Evaluation
 * Fix issues with first phase(bugs, usability, etc.)
 * Undo/Redo operation
 * Load/Store masks
 * Perform 3D image segmentation
 * Allow creating masks for bright region
 ===Deliverables===

← Older revision		Revision as of 01:43, 24 June 2008
Line 187:		Line 187:

	This class is concerned with loading and storing masks in different ways. The import/export functionality will also be provided by this component.		This class is concerned with loading and storing masks in different ways. The import/export functionality will also be provided by this component.
		+
		+	====Sequence Diagram====
		+	'''Open Mask Project'''
		+
		+	[[Image:OpenMaskProject.svg\|center\|300px]]
		+
		+	'''Segmentation'''
		+
		+	[[Image:Segmentation.svg\|center\|300px]]
		+
		+	==User Guide==
		+	===Basic Polygon Masking===
		+	1. Load an image: File->Load Images->(select an image)
		+
		+	2. Edit->Add Point (zoom in/out if requried)
		+
		+	3. Left click to add point and right click to finish adding points
		+
		+	4. File->Save Mask->(provide a filename and location) mask will be stored as a bitmap file
		+
		+
		+	[[Image:PolyEd_Basic_sample3.PNG\|300px]]
		+	[[Image:PolyEd_Basic_sample3_1.PNG\|300px]]
		+
		+	[[Image:PolyEd_Basic_sample3_mask.jpg\|center\|300px]]

	==Test Dataset==		==Test Dataset==

← Older revision		Revision as of 05:44, 3 June 2008
Line 128:		Line 128:

	Since in [1] the number of nodes is equal to the number of pixels, for large images runtime will be very slow. To mitigate this problem [2] performs an additional preprocessing step where the image is over-segmented using watershed filtering algorithm. Additionally, for fine-tuning the segmentation [2] performs graph cut segmentation in a smaller region that is define by the user, around the boundary.		Since in [1] the number of nodes is equal to the number of pixels, for large images runtime will be very slow. To mitigate this problem [2] performs an additional preprocessing step where the image is over-segmented using watershed filtering algorithm. Additionally, for fine-tuning the segmentation [2] performs graph cut segmentation in a smaller region that is define by the user, around the boundary.
		+
		+	For pre-segmentation, I also tried out automatic segmentation as outlined in "Efficient Graph-Based Image Segmentation" (http://people.cs.uchicago.edu/~pff/segment/) using code from the authors website. The size of the original image was 3008x2000 pixel ie. 6016000 nodes. It took about 2mins to process and the resulting number of nodes was 5657. The result is shown below -
		+
		+	[[Image:MiG_Segimg_in.JPG\|300px]]
		+	[[Image:MiG_Segimg_out.jpg\|300px]]

	===Architecture===		===Architecture===