ClassesClasses | | Operators

segment_image_mserT_segment_image_mserSegmentImageMserSegmentImageMser (Operator)

Name

segment_image_mserT_segment_image_mserSegmentImageMserSegmentImageMser — Segment image using Maximally Stable Extremal Regions (MSER).

Signature

segment_image_mser(Image : MSERDark, MSERLight : Polarity, MinArea, MaxArea, Delta, GenParamName, GenParamValue : )

Herror T_segment_image_mser(const Hobject Image, Hobject* MSERDark, Hobject* MSERLight, const Htuple Polarity, const Htuple MinArea, const Htuple MaxArea, const Htuple Delta, const Htuple GenParamName, const Htuple GenParamValue)

void SegmentImageMser(const HObject& Image, HObject* MSERDark, HObject* MSERLight, const HTuple& Polarity, const HTuple& MinArea, const HTuple& MaxArea, const HTuple& Delta, const HTuple& GenParamName, const HTuple& GenParamValue)

HRegion HImage::SegmentImageMser(HRegion* MSERLight, const HString& Polarity, const HTuple& MinArea, const HTuple& MaxArea, const HTuple& Delta, const HTuple& GenParamName, const HTuple& GenParamValue) const

HRegion HImage::SegmentImageMser(HRegion* MSERLight, const HString& Polarity, Hlong MinArea, Hlong MaxArea, Hlong Delta, const HTuple& GenParamName, const HTuple& GenParamValue) const

HRegion HImage::SegmentImageMser(HRegion* MSERLight, const char* Polarity, Hlong MinArea, Hlong MaxArea, Hlong Delta, const HTuple& GenParamName, const HTuple& GenParamValue) const

static void HOperatorSet.SegmentImageMser(HObject image, out HObject MSERDark, out HObject MSERLight, HTuple polarity, HTuple minArea, HTuple maxArea, HTuple delta, HTuple genParamName, HTuple genParamValue)

HRegion HImage.SegmentImageMser(out HRegion MSERLight, string polarity, HTuple minArea, HTuple maxArea, HTuple delta, HTuple genParamName, HTuple genParamValue)

HRegion HImage.SegmentImageMser(out HRegion MSERLight, string polarity, int minArea, int maxArea, int delta, HTuple genParamName, HTuple genParamValue)

Description

segment_image_msersegment_image_mserSegmentImageMserSegmentImageMserSegmentImageMser segments an image into regions of homogenous gray values using the approach of Maximally Stable Extremal Regions (MSER). The segmentation process determines if a region is homogenous by observing the local region surrounding. Therefore, the operator is particularly suited to robustly segment objects in front of inhomogeneous background or in applications with changing illumination.

Parameters

PolarityPolarityPolarityPolaritypolarity

The PolarityPolarityPolarityPolaritypolarity determines the type of the regions that are extracted.

Value Meaning
'dark'"dark""dark""dark""dark" Only MSERs that are darker than their surroundings are extracted
'light'"light""light""light""light" Only MSERs that are lighter than their surroundings are extracted
'both'"both""both""both""both" (default) Both types of MSERs are extracted

MinAreaMinAreaMinAreaMinAreaminArea, MaxAreaMaxAreaMaxAreaMaxAreamaxArea

The values MinAreaMinAreaMinAreaMinAreaminArea and MaxAreaMaxAreaMaxAreaMaxAreamaxArea restrict the size of the returned MSERs.

Note that very small values of MinAreaMinAreaMinAreaMinAreaminArea, e.g., values smaller than 5, can increase the runtime significantly, especially for noisy images.

If MaxAreaMaxAreaMaxAreaMaxAreamaxArea is set to an empty tuple (default), the MSERs are restricted to be true subsets of the connected components of the input domain.

DeltaDeltaDeltaDeltadelta

The value of DeltaDeltaDeltaDeltadelta influences the selectivity of the algorithm. Larger values lead to fewer MSERs. Smaller values lead to more MSERs.

Please read the description of the segmentation process below to help understand the effect of this parameter.

The following generic parameters can be used to fine-tune the segmentation of MSERs. The generic parameters can be set with GenParamNameGenParamNameGenParamNameGenParamNamegenParamName and GenParamValueGenParamValueGenParamValueGenParamValuegenParamValue.

'max_variation'"max_variation""max_variation""max_variation""max_variation":

The maximum variation of a component's area within the range of DeltaDeltaDeltaDeltadelta thresholds. Larger values lead to more MSERs. Smaller values lead to fewer MSERs.

Please read the description of the segmentation process below for a definition of 'variation' and to help understand the effect of this generic parameter.

Values: real values larger than or equal to 0.0

Suggested values: 0.1, 0.2, 0.5, 1.0, 2.0, 5.0

Default: 0.2

'min_diversity'"min_diversity""min_diversity""min_diversity""min_diversity":

The minimum relative difference of the sizes of two overlapping MSERs. Smaller values lead to more overlapping MSERs. Larger values lead to fewer overlapping MSERs.

Please read the description of the segmentation process below for a definition of 'diversity' and to help understand the effect of this generic parameter.

Setting 'min_diversity'"min_diversity""min_diversity""min_diversity""min_diversity" very close to 0.0 may increase the runtime.

Values: real values larger than or equal to 0.0

Suggested values: 0.1, 0.5, 0.8, 1.0, 2.0, 5.0

Default: 0.8

'may_touch_border'"may_touch_border""may_touch_border""may_touch_border""may_touch_border":

Controls if regions that touch the border of the input domain are returned ('true'"true""true""true""true") or rejected ('false'"false""false""false""false").

Values: 'false'"false""false""false""false", 'true'"true""true""true""true"

Default: 'false'"false""false""false""false" if a full domain is used, 'true'"true""true""true""true" if the input domain is reduced.

'min_gray'"min_gray""min_gray""min_gray""min_gray", 'max_gray'"max_gray""max_gray""max_gray""max_gray":

The values 'min_gray'"min_gray""min_gray""min_gray""min_gray" and 'max_gray'"max_gray""max_gray""max_gray""max_gray" reduce the input domain dynamically by applying a thresholdthresholdThresholdThresholdThreshold to the input image. All pixels outside the specified gray value range are ignored in the segmentation process. This may reduce the runtime considerably.

Please note, that if ImageImageImageImageimage has a full domain and the domain is reduced by the settings of 'min_gray'"min_gray""min_gray""min_gray""min_gray" or 'max_gray'"max_gray""max_gray""max_gray""max_gray", the default behavior of 'may_touch_border'"may_touch_border""may_touch_border""may_touch_border""may_touch_border" may lead to more result regions than without restricted gray value range.

Values: integer values larger than or equal to 0

Default: 'min_gray'"min_gray""min_gray""min_gray""min_gray": 0, 'max_gray'"max_gray""max_gray""max_gray""max_gray": 255 for byte images, 65535 for uint2 images

Segmentation Process

In a first step, the image is segmented with all threshold values t, from 0 to the maximal present gray value.

To illustrate this, the following example input image with twelve gray values (0...11) is used. On the right, the boundaries of the resulting threshold regions are shown.

Example input image with twelve gray values reaching from 0 (= black) to 11 (= white)
Boundaries of the threshold regions for all thresholds (t = 0...11)

The resulting threshold regions are split into their connected components (4-connected neighborhood) and the area increase of the individual components is monitored over the increasing thresholds. The area of each individual component increases monotonically with each (increasing) threshold. An MSER is a component whose area does not vary significantly within the range of DeltaDeltaDeltaDeltadelta thresholds. To be accepted as an MSER, the variation of the component's area within the range of DeltaDeltaDeltaDeltadelta thresholds must be a local minimum and it must be lower than 'max_variation'"max_variation""max_variation""max_variation""max_variation". Furthermore, the diversity of overlapping MSERs must be greater than 'min_diversity'"min_diversity""min_diversity""min_diversity""min_diversity" (see below).

The variation of a component's area is defined by

Decreasing the value of 'max_variation'"max_variation""max_variation""max_variation""max_variation" will reduce the number of accepted regions.

In our example, each threshold region consists of only one component. Therefore, the terms 'threshold region' and 'component' are used synonymously hereinafter. The following table shows the area of the threshold regions and their variations for DeltaDeltaDeltaDeltadelta set to 1 and for DeltaDeltaDeltaDeltadelta set to 2.

Threshold value t Threshold region Area of the threshold region Variation of the area (for DeltaDeltaDeltaDeltadelta = 1) Variation of the area (for DeltaDeltaDeltaDeltadelta = 2)

0
320 0.28 0.53
1
410 0.41 0.54
2
490 0.27 0.49
3
540 0.13 0.31
4
560 0.07 0.25
5
580 0.12 0.29
6
630 0.21 0.38
7
710 0.24 0.44
8
800 0.23 0.41
9
890 0.18 1.67
10
960 1.36 1.46
11
2200 0.56 0.60

The area of the threshold regions increases with the threshold value t. If DeltaDeltaDeltaDeltadelta is set to 1, the local minima of the variation are obtained for the threshold values t = 0, t = 4, t = 9, and t = 11. Therefore, the threshold regions for t = 0, t = 4, t = 9, and t = 11 are MSER candidates. If DeltaDeltaDeltaDeltadelta is set to 2, the MSER candidates correspond to the threshold regions for t = 0, t = 4, t = 8, t = 11.

Per default, the connected components of the image domain will not be returned as MSER. This behaviour can be altered by explicitly setting MaxAreaMaxAreaMaxAreaMaxAreamaxArea to a value larger than the area of the input domain and 'may_touch_border'"may_touch_border""may_touch_border""may_touch_border""may_touch_border" to 'true'"true""true""true""true". In our example, the default behavior eliminates the MSER candidates that correspond to the threshold regions for t = 11.

The following figure shows the resulting MSER candidates for DeltaDeltaDeltaDeltadelta = 1 and for DeltaDeltaDeltaDeltadelta = 2 (with 'max_variation' set to 1.0), overlaid over the input image.

MSER candidates for Delta = 1 MSER candidates for Delta = 2
corresponds to t = 0
corresponds to t = 0
corresponds to t = 4
corresponds to t = 4
corresponds to t = 9
corresponds to t = 8

The MSER segmentation does not divide the image into disjunct regions, but rather determines all MSERs within the input image. Hence for one image, multiple mutual overlapping regions may be returned as MSER candidates. Since the MSERs are calculated by continuously increasing the threshold t, two regions that overlap each other always consist of a larger region that completely contains the smaller one. The 'diversity' measures, how much the areas of two overlapping MSERs differ. It is calculated as the relative difference of the areas of the two MSER candidates:

If the diversity of an MSER candidate is smaller than 'min_diversity'"min_diversity""min_diversity""min_diversity""min_diversity", it is discarded. Hence the parameter 'min_diversity'"min_diversity""min_diversity""min_diversity""min_diversity" is used to control the amount of overlapping regions. Higher values of 'min_diversity'"min_diversity""min_diversity""min_diversity""min_diversity" reduce the number of overlapping regions and lower values increase it. Note that the largest MSER candidates, i.e., those candidates that are not contained in another MSER candidate are always kept.

Delta = 1 Delta = 2
MSER candidate index i Threshold value t Area of the threshold region Diversity of the MSER candidate MSER candidate index i Threshold value t Area of the threshold region Diversity of the MSER candidate
0 0 320 0.75 0 0 320 0.75
1 4 560 0.59 1 4 560 0.43
2 9 890 N/A 2 8 800 N/A

First, the MSER candidate with the smallest diversity is eliminated if its diversity is less than 'min_diversity'"min_diversity""min_diversity""min_diversity""min_diversity". In our example, the value for 'min_diversity'"min_diversity""min_diversity""min_diversity""min_diversity" is set to 0.5. For delta = 2, the MSER candidate with the diversity of 0.43 is eliminated. Then, the diversity is recalculated for the remaining MSER candidates. In our example, this yields a diversity of 1.5 for the MSER candidate 0. Now, all remaining MSER candidates have a diversity greater than 0.5 and are therefore accepted as MSERs.

The segmentation process calculates MSERs for each connected component of the input domain independently.

Execution Information

This operator supports cancelling timeouts.

Parameters

ImageImageImageImageimage (input_object)  singlechannelimage objectHImageHImageHobject (byte / uint2)

Input image.

MSERDarkMSERDarkMSERDarkMSERDarkMSERDark (output_object)  region-array objectHRegionHRegionHobject *

Segmented dark MSERs.

MSERLightMSERLightMSERLightMSERLightMSERLight (output_object)  region-array objectHRegionHRegionHobject *

Segmented light MSERs.

PolarityPolarityPolarityPolaritypolarity (input_control)  string HTupleHTupleHtuple (string) (string) (HString) (char*)

The polarity of the returned MSERs.

Default value: 'both' "both" "both" "both" "both"

List of values: 'both'"both""both""both""both", 'dark'"dark""dark""dark""dark", 'light'"light""light""light""light"

MinAreaMinAreaMinAreaMinAreaminArea (input_control)  number(-array) HTupleHTupleHtuple (integer / real) (int / long / double) (Hlong / double) (Hlong / double)

Minimal size of an MSER.

Default value: 10

Suggested values: 1, 10, 100, 10000

Typical range of values: 1 ≤ MinArea MinArea MinArea MinArea minArea

MaxAreaMaxAreaMaxAreaMaxAreamaxArea (input_control)  number(-array) HTupleHTupleHtuple (integer / real) (int / long / double) (Hlong / double) (Hlong / double)

Maximal size of an MSER.

Default value: []

Suggested values: 1, 10, 100, 10000

Typical range of values: 1 ≤ MaxArea MaxArea MaxArea MaxArea maxArea

DeltaDeltaDeltaDeltadelta (input_control)  number HTupleHTupleHtuple (integer / real) (int / long / double) (Hlong / double) (Hlong / double)

Amount of thresholds for which a region needs to be stable.

Default value: 15

Suggested values: 5, 10, 20, 50

Typical range of values: 1 ≤ Delta Delta Delta Delta delta ≤ 65535

GenParamNameGenParamNameGenParamNameGenParamNamegenParamName (input_control)  attribute.name-array HTupleHTupleHtuple (string) (string) (HString) (char*)

List of generic parameter names.

Default value: []

List of values: 'max_gray'"max_gray""max_gray""max_gray""max_gray", 'max_variation'"max_variation""max_variation""max_variation""max_variation", 'may_touch_border'"may_touch_border""may_touch_border""may_touch_border""may_touch_border", 'min_diversity'"min_diversity""min_diversity""min_diversity""min_diversity", 'min_gray'"min_gray""min_gray""min_gray""min_gray"

GenParamValueGenParamValueGenParamValueGenParamValuegenParamValue (input_control)  attribute.value-array HTupleHTupleHtuple (string / real / integer) (string / double / int / long) (HString / double / Hlong) (char* / double / Hlong)

List of generic parameter values.

Default value: []

Suggested values: 0.5, 0.8, 'true'"true""true""true""true", 'false'"false""false""false""false", 30, 50, 200, 230

Example (HDevelop)

read_image (Image,'pellets')
segment_image_mser (Image, MSERDark, MSERLight, 'light', 1000, 10000, 3, [],[])

Result

segment_image_msersegment_image_mserSegmentImageMserSegmentImageMserSegmentImageMser returns 2 (H_MSG_TRUE) if all parameter values are correct. If necessary, an exception is raised.

Possible Successors

select_shapeselect_shapeSelectShapeSelectShapeSelectShape, select_grayselect_graySelectGraySelectGraySelectGray

Alternatives

auto_thresholdauto_thresholdAutoThresholdAutoThresholdAutoThreshold, binary_thresholdbinary_thresholdBinaryThresholdBinaryThresholdBinaryThreshold, char_thresholdchar_thresholdCharThresholdCharThresholdCharThreshold, local_thresholdlocal_thresholdLocalThresholdLocalThresholdLocalThreshold, watershedswatershedsWatershedsWatershedsWatersheds, regiongrowingregiongrowingRegiongrowingRegiongrowingRegiongrowing

References

J. Matas, O. Chum, M. Urban, and T. Pajdla: “Robust wide baseline stereo from maximally stable extremal regions.”; Proc. of British Machine Vision Conference, pages 384-396; 2002.

Module

Foundation


ClassesClasses | | Operators