Plate detection algorithm - Revision history

AlessandroGiusti: /* Documentation and useful files */

2008-06-23T09:33:27Z

‎Documentation and useful files

AlessandroGiusti at 09:32, 23 June 2008

2008-06-23T09:32:30Z

AndreaMachina: /* Documentation and useful files */

2008-06-18T21:27:09Z

‎Documentation and useful files

AndreaMachina: /* Results and problems */

2008-06-18T15:25:36Z

‎Results and problems

AndreaMachina: /* Results and problems */

2008-06-18T15:23:44Z

‎Results and problems

AndreaMachina: /* Documentation and useful files */

2008-06-18T14:48:14Z

‎Documentation and useful files

AndreaMachina: /* Results and problems */

2008-06-18T14:42:10Z

‎Results and problems

AndreaMachina: /* Adopted solution */

2008-06-18T14:35:03Z

‎Adopted solution

AndreaMachina: /* Project short description */

2008-06-18T14:26:54Z

‎Project short description

AndreaMachina: /* Project short description */

2008-06-18T14:26:24Z

‎Project short description

← Older revision		Revision as of 09:33, 23 June 2008
Line 97:		Line 97:

	* [[Media:Plate detection Andrea Machina.pdf \| Project Documentation (in italian)]]		* [[Media:Plate detection Andrea Machina.pdf \| Project Documentation (in italian)]]
		+
		+	Additional materials (source codes, datasets) available in AIRWiki private layer.

	=== Useful link ===		=== Useful link ===

← Older revision		Revision as of 09:32, 23 June 2008
Line 97:		Line 97:

	* [[Media:Plate detection Andrea Machina.pdf \| Project Documentation (in italian)]]		* [[Media:Plate detection Andrea Machina.pdf \| Project Documentation (in italian)]]
−
−	* [[Media:Plate_detection_src.zip \| C Source code]]
−
−	* [[Media:Plate_detection_Data_set.zip \| Data set]]

	=== Useful link ===		=== Useful link ===

← Older revision		Revision as of 21:27, 18 June 2008
Line 99:		Line 99:

	* [[Media:Plate_detection_src.zip \| C Source code]]		* [[Media:Plate_detection_src.zip \| C Source code]]
		+
		+	* [[Media:Plate_detection_Data_set.zip \| Data set]]

	=== Useful link ===		=== Useful link ===

← Older revision		Revision as of 15:25, 18 June 2008
Line 92:		Line 92:


−	3) This solution didn’t give good results because it is heavy influenced by noises. Small white areas in candidates can in fact ~~change~~ the order of the elements in the list ~~influencing the medium value calculated~~.	+	3) This solution didn’t give good results because it is heavy influenced by noises. Small white areas in candidates can in fact influence the medium value calculated, changing the order of the elements in the list.

	=== Documentation and useful files ===		=== Documentation and useful files ===

← Older revision		Revision as of 15:23, 18 June 2008
Line 92:		Line 92:


−	3) This solution didn’t ~~gave~~ good results because it is heavy influenced by noises. Small white areas in candidates can in fact change the order of the elements in the list influencing the medium value calculated.	+	3) This solution didn’t give good results because it is heavy influenced by noises. Small white areas in candidates can in fact change the order of the elements in the list influencing the medium value calculated.

	=== Documentation and useful files ===		=== Documentation and useful files ===

← Older revision		Revision as of 14:48, 18 June 2008
Line 97:		Line 97:

	* [[Media:Plate detection Andrea Machina.pdf \| Project Documentation (in italian)]]		* [[Media:Plate detection Andrea Machina.pdf \| Project Documentation (in italian)]]
		+
		+	* [[Media:Plate_detection_src.zip \| C Source code]]

	=== Useful link ===		=== Useful link ===

@@ Line 78: / Line 78: @@
 ) The first approach is the one that gave the best results, as we can see in the images the candidates in the end of the algorithm are reduced by the second algorithm and, in some images where the second algorithm returned the wrong candidate, applying the first algorithm gave the right result.
 ) This approach gave good results only in few cases. The idea was to reduce the area analyzed by the first algorithm but the second algorithm applied on some images returned a lot of candidates, the sum of the pixels of the whole candidates found was bigger than the number of pixels in the original image.
 ) This solution didn’t gave good results because it is heavy influenced by noises. Small white areas in candidates can in fact change the order of the elements in the list influencing the medium value calculated.

← Older revision		Revision as of 14:35, 18 June 2008
Line 61:		Line 61:

	1) The second algorithm (the faster one) is applied to the original image performing a first selection of region of interest based on geometrical characteristics. Each candidate found with this algorithm has been used to build a new binary mask (a selection mask), with the dimensions of the original image, where, if a pixel (x, y) is part of a candidate the corresponding element of the mask (x, y) is put to 1, 0 otherwise. The first algorithm is then applied to the original image but, during the merging mask is considered also the new selection mask. In this way we can reduce the amount of false positives.		1) The second algorithm (the faster one) is applied to the original image performing a first selection of region of interest based on geometrical characteristics. Each candidate found with this algorithm has been used to build a new binary mask (a selection mask), with the dimensions of the original image, where, if a pixel (x, y) is part of a candidate the corresponding element of the mask (x, y) is put to 1, 0 otherwise. The first algorithm is then applied to the original image but, during the merging mask is considered also the new selection mask. In this way we can reduce the amount of false positives.
		+
		+	[[Image:plate_detection_approach_1_a.jpg\|center\|frame\|On the left: candidates found by the second algorithm. On the right: the selection mask calculated.]]
		+
		+	[[Image:plate_detection_approach_1_b.jpg\|center\|frame\|On the left: candidates found by the second algorithm. On the right: the selection mask calculated.]]
		+

	2) As in the first solution the second algorithm is applied. The first algorithm is then applied not on the whole original image but on each candidate found by the second algorithm. This solution aims to reduce the first algorithm complexity applying it only on the selected candidates.		2) As in the first solution the second algorithm is applied. The first algorithm is then applied not on the whole original image but on each candidate found by the second algorithm. This solution aims to reduce the first algorithm complexity applying it only on the selected candidates.

@@ Line 9: / Line 9: @@
 The aim of the project is to merge two plate detection algorithms previously developed trying to make the best of them.
 Different approaches were studied underlying pro and con.
 [[Image:plate detection intro.jpg|center|Plate detected]]