[Artoolkit] Marker Training

Link: Documentation

About the Traditional Template Square Marker

Limitations (重要)

  • Traditional Template Square Marker

Replacing the marker's pattern of the 4.25 inch square marker (used above) with a pattern of significantly increased complexity reduced the tracking range from 34 to 15 inches.

　　

 

  • Traditional Template Square Marker

The total number of possible barcodes available depends on the number of rows and columns in the barcode and the type of error detection and correction (EDC) algorithm enabled. Using better EDC will result in a smaller set of barcodes being available, but lower likelihood of markers being misrecognized during tracking.

The barcode type is set via the function arSetMatrixCodeType

 

 

Multimarker Tracking

This refers specifically to the use of multiple square markers fixed to a single object. 一个固定物体上的多个识别点。

 

Some of the benefits of multimarkers include:

    • Increased robustness to occlusion: even when one marker is obscured, another may be visible. 提高鲁棒性。
    • Improved pose-estimation accuracy: in a multimarker set, all marker corners are used to calculate the pose, meaning that the markers effectively cover a larger optical angle, resulting in reduced numerical error. 提高计算精确性。
    • Possibility for robust pose estimation (using M-estimation). With multimarker tracking, statistical techniques can be applied to improve rejection of mis-read marker poses. 减少mis-read。

Note that these are the same advantages of using NFT (texture) tracking.

The advantages of multimarker tracking over NFT is that it is less CPU intensive, faster, and can operate reliably at greater distances from the camera.

The obvious disadvantage is that it requires the surface to be covered in square markers.

 

In ARToolKit for Android, any app using the ARBaseLib library or its underlying native implementation, ARWrapper, supports multimarker tracking without any further work by the developer. The code is provided in the ARMarkerMulti C++ class. Thus, the following examples include support for multimarker tracking, as well as other marker types:

    • ARSimple
    • ARSimpleInteraction
    • ARSimpleNative
    • ARSimpleNativeCars

 

A multimarker configuration file is structured as follows:

    • Lines beginning with a # character are treated as comments and ignored.
    • Blank lines are ignored. Blank lines do not play any part in the configuration structure.
    • The first non-blank/comment line in the file must be a single integer specifying the number of markers to be read from the multimarker configuration file. (This will usually be the actual number of markers in the set.)
    • Each five subsequent non-blank/comment lines specify a single marker in the set,
      • The first line of each marker specification is either an integer greater than or equal to 0 (if using barcode markers) or the path to a pictorial (template) marker pattern file, expressed relative to this multimarker configuration.
      • The next line specifies the size of this marker. Usually this will be the width of the outer border in millimeters. (Multiply inches by 25.4 to get millimeters).
      • The last three lines of the marker specification are the first three rows of a standard 4×4 homogenous coordinate transform matrix (in row-major order). This transform is from the combined multimarker set's coordinate system origin to the origin of this marker. More information on this transform is set out below.

 

 

Natural Feature Tracking with Fiducial Markers

The result can be seemingly marker-less tracking (since the fiducial markers need not be obvious to the human viewer). Although ARToolKit offers full marker-less tracking, there are situations where using one or more About the Traditional Template Square Marker has advantages:

    • Using the NFT 1.0 tracker plus fiducial markers is less computationally expensive than NFT 1.0 + 2.0 full marker-less tracking. Thus NFT 1.0 with fiducial markers is more practical for mobile devices.
    • The NFT 2.0 tracker has a practical limit on the number of distinct markers that can be distinguished at any one time. Thus, if a large number of images need to be tracked (e.g. a 100-page book), fiducial markers enable efficient identification of numerous images intended to be tracked.
    • Fiducial marker tracking adds significant robustness to tracking, particularly in poor lighting conditions, or when the camera is far away from the tracked image.

 

To use only the standard 1.0 version of ARToolKit's NFT tracking with a fiducial marker,

    • the tracked surface must have the marker either in the image or around the outside of it,
    • there must be at least one in each image,
    • the marker(s) must be square, and
    • the markers must all have a black border and lie on a white background, or vice-versa.

The marker(s) are not required to be of a particular size and the marker can embed colored patterns that blend with the image background.

 

/* 虽然简单，但用户体验不好 */

  

If implementing an app using standard ARToolKit NFT in which one or more fiducial markers is required,

an image and markers input set configuration file (.iset) is required to generate recognition and tracking data set files.

The generated files are a marker file (.mrk) and one (or more) pattern files (.pat-xx).

 

 

The output of this training is a set of data that can be used for realtime tracking in application using the ARToolKit SDK.

The following constraints apply to surfaces which can be used with ARToolKit NFT.

    • The surfaces to be tracked must be supplied as a rectangular image.
    • The images must be supplied in jpeg format.
    • The surface must be textured and have a reasonable amount of fine detail and sharp edges (a low degree of self-similarity and high spatial-frequency). Images with large areas of single flat color, that are blurred or have soft detail will not track well, if at all. In such images, it's difficult to locate distinct feature points.
    • Larger or higher resolution images (more pixels) will allow the extraction of feature points at higher levels of detail, and thus will track better when the camera is closer to the image, or when a higher resolution camera is used.

 

 

  • 特征点提取： 

unsw@unsw-UX303UB$ ./genTexData ~/Desktop/pinball.jpg 
--
Generator started at 2017-02-15 09:41:53 +1100
Select extraction level for tracking features, 0(few) <--> 4(many), [default=2]: 
MAX_THRESH  = 0.900000
MIN_THRESH  = 0.550000
SD_THRESH   = 8.000000
Select extraction level for initializing features, 0(few) <--> 3(many), [default=1]: 
SURF_FEATURE = 100
Reading JPEG file...
   Done.
JPEG image '/home/unsw/Desktop/pinball.jpg' is 1637x2048.
JPEG image '/home/unsw/Desktop/pinball.jpg' does not contain embedded resolution data, and no resolution specified on command-line.
Enter resolution to use (in decimal DPI): 220
Enter the minimum image resolution (DPI, in range [3.762, 220.000]): 50
Enter the maximum image resolution (DPI, in range [50.000, 220.000]): 120
Image DPI (1): 50.000000
Image DPI (2): 62.996056
Image DPI (3): 79.370056
Image DPI (4): 100.000008
Image DPI (5): 120.000000
Generating ImageSet...
   (Source image xsize=1637, ysize=2048, channels=3, dpi=220.0).
  Done.
Saving to /home/unsw/Desktop/pinball.iset...
  Done.
Generating FeatureList...
Start for 120.000000 dpi image.
         ImageSize =  997481[pixel]
Extracted features =   62395[pixel]
 Filtered features =   20049[pixel]
1116/1117.
  Done.
Max feature = 966
  1: (765, 89) : 0.321772 min=0.427143 max=0.805384, sd=29.091545
  2: ( 23,1053) : 0.379421 min=0.402622 max=0.801940, sd=50.645126
  3: ( 22,1017) : 0.380300 min=0.416025 max=0.776800, sd=48.386406
  4: ( 22,1091) : 0.445152 min=0.492460 max=0.809735, sd=61.714653
  5: (852, 98) : 0.524282 min=0.524524 max=0.876935, sd=36.742512
  6: (732, 92) : 0.545269 min=0.566303 max=0.859710, sd=32.648140
  7: (689,106) : 0.556919 min=0.602261 max=0.858849, sd=19.694742
  8: ( 47,899) : 0.558706 min=0.550294 max=0.766749, sd=36.739986
  9: (818, 99) : 0.566552 min=0.560816 max=0.818152, sd=28.520765
 10: (655,254) : 0.573113 min=0.567233 max=0.856610, sd=15.011593
 11: (452,521) : 0.597921 min=0.619703 max=0.885224, sd=46.743130
 12: (678,324) : 0.606832 min=0.579851 max=0.871763, sd=16.810856
 13: (691,261) : 0.613515 min=0.595888 max=0.881752, sd=17.100351
 14: (534,530) : 0.636611 min=0.587019 max=0.850623, sd=40.108799
 15: (649,105) : 0.653610 min=0.605613 max=0.887962, sd=17.939051
 16: (437,621) : 0.658504 min=0.595797 max=0.910285, sd=33.621487
 17: (840,270) : 0.661558 min=0.615135 max=0.905841, sd=20.568960
 18: (506,471) : 0.668593 min=0.707550 max=0.914466, sd=33.422256
 19: (457,569) : 0.676129 min=0.555997 max=0.890244, sd=34.606815
 20: (768,349) : 0.678596 min=0.594938 max=0.927675, sd=48.889709
 21: (498,504) : 0.690536 min=0.666195 max=0.903544, sd=35.013893
 22: (802,429) : 0.693664 min=0.641845 max=0.876466, sd=21.594414
 23: (644,306) : 0.693795 min=0.660852 max=0.915004, sd=18.491032
 24: (639,551) : 0.694179 min=0.557615 max=0.909218, sd=26.793728
 25: (376,602) : 0.699786 min=0.554285 max=0.879627, sd=34.442245
 26: (601,528) : 0.704756 min=0.566293 max=0.910918, sd=35.633511
 27: (257,494) : 0.705136 min=0.568435 max=0.935403, sd=28.677387
 28: (696,223) : 0.713484 min=0.644575 max=0.927928, sd=17.596481
 29: ( 47,935) : 0.714487 min=0.657192 max=0.824285, sd=43.777817
 30: (318,545) : 0.716575 min=0.620929 max=0.936591, sd=25.896675
 31: (336,501) : 0.717786 min=0.557178 max=0.897819, sd=27.770891
 32: (632,412) : 0.718309 min=0.653641 max=0.932392, sd=14.924490
 33: (387,544) : 0.719238 min=0.558125 max=0.874271, sd=33.856152
 34: (347,391) : 0.722319 min=0.699285 max=0.908542, sd=15.166432
 35: ( 43,659) : 0.724148 min=0.706359 max=0.914760, sd=13.407082
 36: (682,153) : 0.724617 min=0.654127 max=0.917548, sd=25.730522
 37: (416,485) : 0.732004 min=0.569813 max=0.931096, sd=39.249733
 38: (851,231) : 0.732772 min=0.630711 max=0.931409, sd=16.155327
 39: (116,659) : 0.739840 min=0.738301 max=0.927481, sd=14.799817
 40: (726,536) : 0.740248 min=0.552373 max=0.947546, sd=50.131382
 41: ( 48,790) : 0.744986 min=0.554222 max=0.816545, sd=26.980175
 42: (726,335) : 0.749057 min=0.760236 max=0.933896, sd=29.690248
 43: (340,308) : 0.752918 min=0.746642 max=0.934489, sd=33.118176
 44: (152,523) : 0.753736 min=0.622629 max=0.942594, sd=61.595882
 45: (135,557) : 0.755940 min=0.583711 max=0.943352, sd=38.911907
 46: ( 31,500) : 0.756052 min=0.619902 max=0.899679, sd=32.681084
 47: (165,474) : 0.757011 min=0.552756 max=0.924492, sd=30.765591
 48: (855,454) : 0.759391 min=0.610077 max=0.886740, sd=21.421764
 49: (546,454) : 0.762225 min=0.670046 max=0.942259, sd=22.942366
 50: (112,512) : 0.763535 min=0.690581 max=0.915867, sd=39.687431
 51: (304,592) : 0.769279 min=0.686215 max=0.942906, sd=54.398426
 52: (272,550) : 0.771564 min=0.552272 max=0.937441, sd=60.583969
 53: (852,584) : 0.771654 min=0.555382 max=0.947278, sd=44.201382
 54: (383,446) : 0.771842 min=0.619332 max=0.956403, sd=27.837420
 55: (751,297) : 0.773208 min=0.703353 max=0.915948, sd=41.982334
 56: (362,641) : 0.774456 min=0.552266 max=0.938892, sd=26.683750
 57: (158,429) : 0.776526 min=0.570332 max=0.963384, sd=21.844723
 58: (687,190) : 0.776703 min=0.657934 max=0.951301, sd=24.961845
 59: (545,293) : 0.778658 min=0.796329 max=0.946868, sd=32.560452
 60: (817,383) : 0.779287 min=0.552390 max=0.951855, sd=42.422295
 61: (869,136) : 0.783576 min=0.776523 max=0.952139, sd=20.210348
 62: (383,500) : 0.783823 min=0.657023 max=0.945138, sd=46.254639
 63: (129,472) : 0.785681 min=0.561756 max=0.934968, sd=16.123209
 64: (761,560) : 0.787113 min=0.605538 max=0.961287, sd=51.377285
 65: ( 45,533) : 0.788313 min=0.771169 max=0.944046, sd=41.105404
 66: (833,546) : 0.788655 min=0.561266 max=0.961304, sd=53.177109
 67: (407,655) : 0.790683 min=0.770458 max=0.938919, sd=32.166893
 68: (773,122) : 0.792271 min=0.815125 max=0.937002, sd=39.905476
 69: (743,413) : 0.793819 min=0.754895 max=0.927860, sd=25.337523
 70: (860,355) : 0.794728 min=0.557320 max=0.941102, sd=47.142551
 71: (218,549) : 0.794926 min=0.551109 max=0.947475, sd=66.032494
 72: (767,204) : 0.798013 min=0.770284 max=0.940773, sd=26.754530
 73: (437,302) : 0.798614 min=0.732842 max=0.942958, sd=42.600384
 74: (476,290) : 0.800596 min=0.829372 max=0.951824, sd=37.470352
 75: (620,209) : 0.803065 min=0.660888 max=0.955436, sd=11.616018
 76: (158,599) : 0.803943 min=0.554751 max=0.941155, sd=28.632961
 77: (568,539) : 0.805024 min=0.709963 max=0.943415, sd=51.277973
 78: (308,714) : 0.805752 min=0.803591 max=0.947742, sd=20.102901
 79: (431,452) : 0.808967 min=0.626351 max=0.918251, sd=32.227089
 80: (804,350) : 0.809588 min=0.677511 max=0.961718, sd=55.540771
 81: (777,598) : 0.811643 min=0.661945 max=0.962027, sd=49.692898
 82: (763,527) : 0.812565 min=0.626655 max=0.962040, sd=51.609238
 83: (701,570) : 0.812870 min=0.672399 max=0.955859, sd=56.590508
 84: (722,606) : 0.815031 min=0.715614 max=0.958174, sd=39.535885
 85: (415,579) : 0.815342 min=0.618177 max=0.923080, sd=29.515026
 86: (394,746) : 0.815806 min=0.810054 max=0.962029, sd=27.898920
 87: (600,488) : 0.817358 min=0.553375 max=0.960826, sd=39.964111
 88: (219,424) : 0.818157 min=0.723989 max=0.931619, sd=20.796185
 89: (727,130) : 0.821157 min=0.815103 max=0.945559, sd=30.023014
 90: (801,294) : 0.821407 min=0.575552 max=0.958943, sd=41.523037
 91: (526,386) : 0.821567 min=0.740057 max=0.931550, sd=11.429000
 92: (611,309) : 0.821830 min=0.778294 max=0.956450, sd=28.585604
 93: (388,713) : 0.823122 min=0.813342 max=0.953675, sd=35.274818
 94: (511,295) : 0.823791 min=0.830091 max=0.956633, sd=42.739384
 95: (567,703) : 0.826842 min=0.750164 max=0.960751, sd=8.835805
 96: (796,493) : 0.827690 min=0.568595 max=0.969311, sd=30.543201
 97: (458,394) : 0.828143 min=0.727661 max=0.933358, sd=13.682913
 98: (313,461) : 0.830045 min=0.574181 max=0.950994, sd=48.069145
 99: (258,583) : 0.831641 min=0.618019 max=0.939475, sd=50.981564
100: (478,758) : 0.833958 min=0.827165 max=0.963935, sd=25.540611
101: (314,397) : 0.835869 min=0.789372 max=0.966805, sd=26.814104
102: (181,719) : 0.836005 min=0.812730 max=0.955963, sd=12.860432
103: (121,623) : 0.836044 min=0.604176 max=0.956743, sd=19.173864
104: ( 81,676) : 0.836234 min=0.787960 max=0.949651, sd=15.605202
105: (472,444) : 0.836281 min=0.699476 max=0.967093, sd=24.709869
106: (858,401) : 0.837824 min=0.593167 max=0.970227, sd=26.464079
107: (691,524) : 0.840960 min=0.553339 max=0.948325, sd=36.042049
108: (731,368) : 0.841294 min=0.758295 max=0.973126, sd=34.514381
109: (647,493) : 0.841896 min=0.590983 max=0.962583, sd=50.893532
110: (634,370) : 0.843767 min=0.806483 max=0.963405, sd=25.815924
111: (555,631) : 0.845366 min=0.722404 max=0.954271, sd=37.854237
112: (819,608) : 0.845988 min=0.744495 max=0.955452, sd=35.659744
113: (523,217) : 0.848209 min=0.794219 max=0.964603, sd=12.703241
114: (684,617) : 0.849532 min=0.735853 max=0.953528, sd=25.841204
115: (630,445) : 0.850685 min=0.720676 max=0.973533, sd=42.023205
116: (532,595) : 0.854030 min=0.763552 max=0.957243, sd=50.512386
117: ( 79,499) : 0.854542 min=0.694400 max=0.950297, sd=31.094616
118: (859,512) : 0.855381 min=0.586259 max=0.964453, sd=26.304533
119: ( 46,385) : 0.855954 min=0.769122 max=0.972207, sd=20.885775
120: ( 85,385) : 0.856343 min=0.773897 max=0.969731, sd=20.200569
121: ( 24,449) : 0.857231 min=0.660279 max=0.956343, sd=32.089931
122: (643,149) : 0.858417 min=0.864698 max=0.961342, sd=28.840944
123: (217,264) : 0.859689 min=0.874637 max=0.968092, sd=35.191395
124: (159,672) : 0.859825 min=0.732891 max=0.969872, sd=21.927061
125: ( 28,568) : 0.860233 min=0.817094 max=0.950137, sd=42.408623
126: (198,458) : 0.861762 min=0.729305 max=0.938121, sd=32.645248
127: (757,263) : 0.861990 min=0.760457 max=0.954904, sd=21.279266
128: (540,260) : 0.863062 min=0.803295 max=0.972987, sd=31.389893
129: (245,757) : 0.864507 min=0.835527 max=0.959412, sd=20.633755
130: (252,397) : 0.865973 min=0.786729 max=0.961551, sd=14.772161
131: (584,242) : 0.866957 min=0.723921 max=0.965726, sd=11.908808
132: (635,613) : 0.868613 min=0.738751 max=0.978283, sd=37.001854
133: (566,590) : 0.870105 min=0.705080 max=0.976399, sd=54.416012
134: (374,335) : 0.870555 min=0.862716 max=0.963986, sd=52.231186
135: (798,538) : 0.870636 min=0.690222 max=0.977169, sd=58.460876
136: (654,193) : 0.871547 min=0.770074 max=0.969915, sd=34.714687
137: (369,221) : 0.874115 min=0.807111 max=0.948065, sd=18.809776
138: (783,631) : 0.874244 min=0.752791 max=0.974438, sd=49.741753
139: (540,497) : 0.875194 min=0.829383 max=0.959214, sd=30.424299
140: (870,737) : 0.875575 min=0.882799 max=0.965087, sd=29.212736
141: (404,296) : 0.876628 min=0.789074 max=0.967728, sd=62.113373
142: ( 27,334) : 0.876748 min=0.857133 max=0.972427, sd=23.289173
143: (693,398) : 0.877818 min=0.833317 max=0.967093, sd=28.822382
144: (821,194) : 0.878718 min=0.553808 max=0.966976, sd=46.079399
145: (735,475) : 0.878864 min=0.688680 max=0.978990, sd=39.045341
146: (364,170) : 0.882400 min=0.883747 max=0.967839, sd=11.069722
147: (124,412) : 0.883863 min=0.666569 max=0.977000, sd=19.543068
148: (259,862) : 0.884313 min=0.883567 max=0.971846, sd=25.047188
149: (135,352) : 0.886579 min=0.776824 max=0.980528, sd=24.436762
150: (126,700) : 0.887615 min=0.869838 max=0.963468, sd=15.290141
151: (689,357) : 0.888368 min=0.835151 max=0.970944, sd=21.854877
152: ( 72,275) : 0.888613 min=0.852755 max=0.977012, sd=20.664570
153: (346,739) : 0.888915 min=0.701890 max=0.984152, sd=29.184855
154: (480,139) : 0.889197 min=0.869495 max=0.974459, sd=11.696819
155: (579,209) : 0.889327 min=0.768717 max=0.955065, sd=9.827321
156: (195,626) : 0.890800 min=0.844556 max=0.972270, sd=45.839676
157: ( 77,713) : 0.891264 min=0.842872 max=0.966874, sd=14.982453
158: (196,331) : 0.891386 min=0.867655 max=0.976589, sd=21.863575
159: ( 75,434) : 0.892803 min=0.558333 max=0.976258, sd=27.073399
160: ( 79,542) : 0.894027 min=0.705994 max=0.960748, sd=47.561893
161: (594,423) : 0.895706 min=0.875279 max=0.975085, sd=21.784636
162: (858,633) : 0.896295 min=0.792583 max=0.952621, sd=30.285173
163: (443,854) : 0.896768 min=0.902650 max=0.975427, sd=24.457178
164: (336,351) : 0.897500 min=0.860278 max=0.969825, sd=25.603603
165: (695,456) : 0.899012 min=0.742119 max=0.980758, sd=29.279078
---------------------------------------------------------------
Start for 100.000008 dpi image.
         ImageSize =  692664[pixel]
Extracted features =   45048[pixel]
 Filtered features =   13864[pixel]
 930/ 931.
  Done.
Max feature = 697
  1: ( 22,852) : 0.349771 min=0.360501 max=0.744216, sd=41.464252
  2: (642, 80) : 0.429173 min=0.450797 max=0.820948, sd=28.798695
  3: ( 22,895) : 0.495620 min=0.514524 max=0.820361, sd=55.195919
  4: (362,521) : 0.540511 min=0.554955 max=0.876519, sd=33.614693
  5: (388,453) : 0.550542 min=0.584428 max=0.874724, sd=44.443565
  6: (566,270) : 0.579497 min=0.577781 max=0.858645, sd=16.590513
  7: (605, 77) : 0.580266 min=0.609462 max=0.853004, sd=32.476265
  8: (408,410) : 0.603162 min=0.574921 max=0.914763, sd=40.661861
  9: (712, 83) : 0.609202 min=0.567525 max=0.890933, sd=38.770107
 10: (544,216) : 0.616884 min=0.606193 max=0.875591, sd=16.212690
 11: (461,429) : 0.628818 min=0.559989 max=0.900930, sd=27.543072
 12: (584,215) : 0.635330 min=0.626998 max=0.896662, sd=16.847752
 13: (642,292) : 0.650199 min=0.647228 max=0.913099, sd=49.786121
 14: (701,221) : 0.651661 min=0.594898 max=0.884969, sd=19.759203
 15: ( 40,750) : 0.658277 min=0.567431 max=0.797774, sd=41.324944
 16: ( 47,532) : 0.678970 min=0.587551 max=0.900196, sd=9.418509
 17: (601,281) : 0.680367 min=0.718519 max=0.903553, sd=26.929148
 18: (264,450) : 0.681953 min=0.608243 max=0.916120, sd=24.941013
 19: (522,352) : 0.684182 min=0.628596 max=0.899572, sd=19.304512
 20: (530,270) : 0.687030 min=0.691926 max=0.904222, sd=20.165924
 21: (303,504) : 0.689154 min=0.554634 max=0.882771, sd=31.895771
 22: (275,417) : 0.692668 min=0.553819 max=0.885160, sd=29.862997
 23: (566,128) : 0.698154 min=0.686290 max=0.910936, sd=27.024332
 24: (322,372) : 0.706138 min=0.584959 max=0.939056, sd=30.012547
 25: (538, 83) : 0.712576 min=0.613834 max=0.908894, sd=18.724792
 26: (623,466) : 0.714373 min=0.562389 max=0.940864, sd=49.591454
 27: (625,247) : 0.715808 min=0.675634 max=0.894476, sd=40.163506
 28: (507,449) : 0.716119 min=0.553789 max=0.909884, sd=40.418575
 29: (328,418) : 0.718154 min=0.555006 max=0.899249, sd=42.681839
 30: (448,380) : 0.718935 min=0.719889 max=0.912257, sd=25.185150
 31: ( 26,419) : 0.723047 min=0.618165 max=0.883976, sd=34.748173
 32: (398,239) : 0.724391 min=0.753250 max=0.932683, sd=35.783329
 33: (281,328) : 0.724423 min=0.727763 max=0.924733, sd=24.401085
 34: (705,504) : 0.725066 min=0.690492 max=0.903710, sd=30.823107
 35: (565,162) : 0.732351 min=0.614862 max=0.938736, sd=27.832005
 36: (125,391) : 0.735772 min=0.594621 max=0.926791, sd=27.280273
 37: ( 90,425) : 0.736865 min=0.673546 max=0.909998, sd=39.099915
 38: (328,549) : 0.737894 min=0.633605 max=0.939472, sd=30.476837
 39: (253,493) : 0.738853 min=0.659323 max=0.929609, sd=54.537189
 40: (472,582) : 0.739663 min=0.654575 max=0.935527, sd=8.129897
 41: (220,446) : 0.741649 min=0.550038 max=0.927463, sd=47.063629
 42: (676,325) : 0.742404 min=0.563019 max=0.938434, sd=36.728741
 43: (113,466) : 0.743374 min=0.608728 max=0.937417, sd=40.978153
 44: (591,433) : 0.746148 min=0.585350 max=0.942217, sd=45.961983
 45: (677, 84) : 0.753436 min=0.617630 max=0.877274, sd=31.570230
 46: ( 28,567) : 0.761727 min=0.681742 max=0.932394, sd=16.555164
 47: (329,604) : 0.765684 min=0.773074 max=0.937355, sd=33.883102
 48: ( 96,519) : 0.767817 min=0.567909 max=0.948462, sd=20.247709
 49: (365,382) : 0.768283 min=0.569190 max=0.913823, sd=34.821491
 50: (587,471) : 0.768309 min=0.666192 max=0.946166, sd=58.605701
 51: ( 23,465) : 0.770354 min=0.778513 max=0.925996, sd=38.811043
 52: (163,384) : 0.771773 min=0.574935 max=0.904084, sd=31.134045
 53: (383,328) : 0.774122 min=0.692096 max=0.922728, sd=16.165672
 54: (284,256) : 0.774494 min=0.716437 max=0.938284, sd=34.749088
 55: (669,254) : 0.777300 min=0.721448 max=0.943146, sd=49.991234
 56: (458,232) : 0.779303 min=0.764945 max=0.942154, sd=28.175735
 57: (588,518) : 0.780279 min=0.675982 max=0.933175, sd=27.235748
 58: (704,461) : 0.781473 min=0.559618 max=0.960531, sd=54.379498
 59: (400,371) : 0.783618 min=0.733629 max=0.951897, sd=27.815334
 60: (257,595) : 0.783918 min=0.747439 max=0.937585, sd=20.855389
 61: (132,433) : 0.785236 min=0.650604 max=0.949868, sd=61.160797
 62: (210,485) : 0.786531 min=0.578740 max=0.913663, sd=49.674171
 63: (607,112) : 0.788960 min=0.791741 max=0.932309, sd=29.295910
 64: ( 95,555) : 0.792241 min=0.742653 max=0.933782, sd=19.222088
 65: (355,487) : 0.794687 min=0.573511 max=0.945379, sd=35.262123
 66: (660,494) : 0.795262 min=0.654301 max=0.947514, sd=49.084759
 67: (126,351) : 0.795678 min=0.573610 max=0.956396, sd=20.190624
 68: (142,602) : 0.795682 min=0.776003 max=0.947548, sd=12.490466
 69: (177,454) : 0.797272 min=0.557524 max=0.948486, sd=63.610645
 70: (501,407) : 0.799923 min=0.555282 max=0.961721, sd=44.629402
 71: (202,389) : 0.802478 min=0.601059 max=0.943534, sd=35.261177
 72: (428,448) : 0.804194 min=0.710041 max=0.922557, sd=40.691563
 73: (717,296) : 0.806315 min=0.608797 max=0.944379, sd=48.967579
 74: (239,391) : 0.808142 min=0.576898 max=0.961420, sd=47.375114
 75: (453,516) : 0.810069 min=0.777759 max=0.936012, sd=49.606281
 76: (515,176) : 0.813310 min=0.749286 max=0.952836, sd=15.288591
 77: (529,306) : 0.813820 min=0.711653 max=0.959155, sd=26.287123
 78: (441,324) : 0.814018 min=0.727951 max=0.945214, sd=15.996302
 79: (272,384) : 0.814950 min=0.623571 max=0.934842, sd=48.547501
 80: (397,640) : 0.816466 min=0.811953 max=0.953758, sd=26.179842
 81: (546,498) : 0.817719 min=0.609840 max=0.957496, sd=42.775417
 82: (178,338) : 0.818825 min=0.582188 max=0.937556, sd=15.957503
 83: ( 32,316) : 0.821449 min=0.768726 max=0.962716, sd=22.648594
 84: (296,617) : 0.821810 min=0.679549 max=0.969090, sd=31.047991
 85: (715,370) : 0.823769 min=0.737173 max=0.916993, sd=26.225739
 86: (173,209) : 0.826986 min=0.850557 max=0.959225, sd=28.628393
 87: (207,634) : 0.827244 min=0.798162 max=0.945608, sd=19.601036
 88: (536,407) : 0.830883 min=0.607147 max=0.965684, sd=54.631756
 89: (609,316) : 0.836093 min=0.793517 max=0.968007, sd=31.316650
 90: ( 56,452) : 0.836616 min=0.653788 max=0.952659, sd=42.899467
 91: (308,187) : 0.837480 min=0.763232 max=0.934290, sd=22.683899
 92: (624,499) : 0.838315 min=0.715505 max=0.965667, sd=54.165775
 93: (676,289) : 0.838711 min=0.793895 max=0.959914, sd=62.036308
 94: (635,158) : 0.839506 min=0.767848 max=0.931084, sd=35.545204
 95: (671,460) : 0.839917 min=0.555733 max=0.956972, sd=52.317551
 96: (201,727) : 0.841604 min=0.861368 max=0.963973, sd=20.879715
 97: (362,250) : 0.842808 min=0.754224 max=0.954782, sd=54.285854
 98: (543,448) : 0.845329 min=0.553511 max=0.926626, sd=41.643665
 99: ( 23,272) : 0.846493 min=0.833716 max=0.968426, sd=25.085428
100: (131,499) : 0.846976 min=0.725040 max=0.952806, sd=38.080383
101: (448,168) : 0.847458 min=0.755793 max=0.957917, sd=12.502056
102: (441,482) : 0.849991 min=0.842787 max=0.951000, sd=54.654308
103: (675,171) : 0.851661 min=0.574917 max=0.971784, sd=30.201307
104: ( 66,322) : 0.852652 min=0.766265 max=0.971219, sd=22.590155
105: (634,433) : 0.852832 min=0.699309 max=0.968999, sd=59.428711
106: (532,120) : 0.852927 min=0.862234 max=0.959935, sd=26.915020
107: (111,292) : 0.862949 min=0.723908 max=0.977276, sd=26.256006
108: ( 57,232) : 0.863810 min=0.805212 max=0.972493, sd=19.950893
109: (665,370) : 0.864329 min=0.805604 max=0.943216, sd=30.024204
110: (329,260) : 0.865367 min=0.781967 max=0.963534, sd=67.723061
111: (510,234) : 0.865708 min=0.737720 max=0.973541, sd=22.597073
112: (679,406) : 0.866283 min=0.699912 max=0.969503, sd=29.106453
113: (157,274) : 0.866821 min=0.826003 max=0.972615, sd=20.816010
114: (720,611) : 0.868287 min=0.869113 max=0.959400, sd=27.837845
115: (416,697) : 0.870643 min=0.864857 max=0.969128, sd=25.967972
116: (580,377) : 0.870670 min=0.792058 max=0.972979, sd=34.387306
117: (579,552) : 0.871728 min=0.858575 max=0.964524, sd=33.288044
118: ( 24,376) : 0.872096 min=0.604563 max=0.956886, sd=36.394798
119: (281,293) : 0.872780 min=0.869573 max=0.963620, sd=29.785576
120: (302,708) : 0.873608 min=0.851892 max=0.969760, sd=32.824219
121: (619,389) : 0.874400 min=0.744619 max=0.963165, sd=30.772835
122: (670,534) : 0.878943 min=0.781091 max=0.975440, sd=45.422569
123: ( 30,170) : 0.879397 min=0.814378 max=0.975241, sd=32.467449
124: (214,323) : 0.880246 min=0.843402 max=0.963770, sd=14.246877
125: (106,207) : 0.880284 min=0.828107 max=0.973935, sd=19.723745
126: ( 65,361) : 0.880380 min=0.559535 max=0.967921, sd=28.355925
127: (382,707) : 0.880651 min=0.871150 max=0.972230, sd=26.882008
128: (714,426) : 0.888315 min=0.724110 max=0.981333, sd=43.108688
129: (709,146) : 0.891364 min=0.593559 max=0.945580, sd=32.062984
130: (140,562) : 0.893007 min=0.726803 max=0.979778, sd=23.888241
131: (564,327) : 0.893668 min=0.838500 max=0.968492, sd=29.345287
132: (486,493) : 0.895055 min=0.643808 max=0.981625, sd=56.210423
133: (259,185) : 0.897087 min=0.774011 max=0.979710, sd=24.162752
134: (342,334) : 0.898018 min=0.887572 max=0.975908, sd=80.565010
135: (138,132) : 0.898896 min=0.861754 max=0.979334, sd=22.827488
---------------------------------------------------------------
Start for 79.370056 dpi image.
         ImageSize =  436749[pixel]
Extracted features =   29923[pixel]
 Filtered features =    8833[pixel]
 738/ 739.
  Done.
Max feature = 434
  1: (287,402) : 0.424587 min=0.495490 max=0.841241, sd=33.538174
  2: (451,208) : 0.574265 min=0.568550 max=0.848501, sd=16.525414
  3: (320,322) : 0.574748 min=0.559441 max=0.872997, sd=38.725376
  4: (260,436) : 0.581560 min=0.550665 max=0.893702, sd=30.718977
  5: (304,359) : 0.585792 min=0.567457 max=0.861221, sd=43.476383
  6: (461, 74) : 0.607475 min=0.626667 max=0.851842, sd=25.428596
  7: (368,340) : 0.615521 min=0.570816 max=0.862881, sd=32.116570
  8: (205,353) : 0.629906 min=0.550059 max=0.890384, sd=26.679115
  9: (448,172) : 0.633249 min=0.558702 max=0.838462, sd=16.410463
 10: ( 30,602) : 0.655022 min=0.556795 max=0.809541, sd=44.237373
 11: (204,394) : 0.663904 min=0.616690 max=0.902155, sd=47.889595
 12: (495,365) : 0.664576 min=0.575173 max=0.918581, sd=48.777203
 13: (255,483) : 0.669407 min=0.694718 max=0.916036, sd=32.513351
 14: (494, 66) : 0.671808 min=0.606392 max=0.854163, sd=34.949917
 15: ( 35,352) : 0.674519 min=0.668164 max=0.886650, sd=38.646778
 16: (315,190) : 0.678237 min=0.652017 max=0.926134, sd=38.604790
 17: (356,301) : 0.680022 min=0.651290 max=0.889282, sd=24.601427
 18: (494,189) : 0.680802 min=0.637456 max=0.873574, sd=35.485271
 19: (504,235) : 0.682513 min=0.718521 max=0.912211, sd=48.597336
 20: ( 86,372) : 0.685274 min=0.563088 max=0.913361, sd=39.962543
 21: (561,170) : 0.699254 min=0.657650 max=0.888837, sd=17.774458
 22: (445,107) : 0.700724 min=0.602724 max=0.916041, sd=28.082132
 23: ( 48,440) : 0.701424 min=0.598771 max=0.906770, sd=13.176127
 24: (235,273) : 0.707155 min=0.656612 max=0.900852, sd=23.163576
 25: (563, 66) : 0.707671 min=0.620504 max=0.895905, sd=38.397793
 26: (554,404) : 0.709412 min=0.653853 max=0.892614, sd=31.383821
 27: (251,333) : 0.713921 min=0.567554 max=0.883052, sd=43.222118
 28: (567,265) : 0.721515 min=0.580028 max=0.920115, sd=31.940937
 29: (425, 70) : 0.723166 min=0.588885 max=0.909064, sd=18.062485
 30: (156,331) : 0.724533 min=0.553878 max=0.932290, sd=44.227341
 31: (230,201) : 0.728015 min=0.685503 max=0.918389, sd=35.047256
 32: (139,293) : 0.731852 min=0.568805 max=0.895599, sd=26.331055
 33: (307,261) : 0.731864 min=0.661568 max=0.914380, sd=16.817749
 34: ( 73,338) : 0.735963 min=0.629409 max=0.909261, sd=43.005833
 35: (462,350) : 0.753156 min=0.589768 max=0.933392, sd=50.755322
 36: (408,184) : 0.754838 min=0.639366 max=0.934599, sd=21.371698
 37: (309,507) : 0.756133 min=0.755408 max=0.934132, sd=24.268871
 38: (527,195) : 0.758750 min=0.709395 max=0.930400, sd=43.539856
 39: (349,259) : 0.759112 min=0.665806 max=0.928001, sd=16.578856
 40: (364,184) : 0.760905 min=0.758426 max=0.925954, sd=31.667768
 41: (155,365) : 0.762531 min=0.552516 max=0.917358, sd=59.276340
 42: (214,467) : 0.765042 min=0.658591 max=0.928408, sd=26.152805
 43: (416,285) : 0.766182 min=0.645952 max=0.950609, sd=34.620697
 44: (285,299) : 0.766313 min=0.617227 max=0.925215, sd=40.149860
 45: (528, 65) : 0.768620 min=0.562859 max=0.902211, sd=33.340858
 46: (557,370) : 0.771844 min=0.569429 max=0.952980, sd=52.301632
 47: (114,335) : 0.771881 min=0.611211 max=0.940073, sd=56.177685
 48: ( 85,276) : 0.775593 min=0.553823 max=0.945913, sd=23.561525
 49: (211,310) : 0.782274 min=0.585329 max=0.928564, sd=44.898174
 50: (514,401) : 0.783475 min=0.616240 max=0.956559, sd=51.606834
 51: (348,381) : 0.784641 min=0.773819 max=0.921683, sd=52.746880
 52: (467,399) : 0.784750 min=0.712745 max=0.942072, sd=46.240128
 53: (422,324) : 0.786412 min=0.553672 max=0.941945, sd=53.564259
 54: (468,247) : 0.787911 min=0.798048 max=0.943097, sd=27.948755
 55: ( 32,249) : 0.787959 min=0.670910 max=0.956550, sd=22.670534
 56: (166,508) : 0.796028 min=0.722197 max=0.925336, sd=19.043421
 57: (452,432) : 0.796624 min=0.774988 max=0.935034, sd=27.751265
 58: (406,358) : 0.801342 min=0.570171 max=0.929650, sd=48.721424
 59: (504,130) : 0.802855 min=0.704131 max=0.903552, sd=32.415211
 60: (374,424) : 0.803728 min=0.735531 max=0.937777, sd=35.249271
 61: (294,557) : 0.816205 min=0.808897 max=0.954073, sd=23.818476
 62: (206,500) : 0.817869 min=0.696211 max=0.937664, sd=23.392765
 63: (434,395) : 0.819297 min=0.662518 max=0.955639, sd=45.326519
 64: (532,319) : 0.821661 min=0.731614 max=0.960118, sd=36.159546
 65: ( 23,215) : 0.822996 min=0.782434 max=0.964339, sd=25.203840
 66: ( 80,407) : 0.829268 min=0.722506 max=0.956091, sd=33.387890
 67: (117,238) : 0.830372 min=0.682733 max=0.974954, sd=35.768021
 68: (564,231) : 0.832604 min=0.691795 max=0.948959, sd=55.398605
 69: (166,569) : 0.833067 min=0.795034 max=0.950528, sd=24.224396
 70: (269,202) : 0.833721 min=0.697016 max=0.953199, sd=62.431587
 71: ( 98,448) : 0.835240 min=0.743466 max=0.962460, sd=28.871698
 72: (381,391) : 0.835508 min=0.641716 max=0.968347, sd=58.081131
 73: (227,557) : 0.837043 min=0.799750 max=0.957189, sd=32.878773
 74: (552,136) : 0.838220 min=0.552711 max=0.951419, sd=35.211857
 75: (506,270) : 0.839198 min=0.821844 max=0.942766, sd=33.345402
 76: (135,177) : 0.840291 min=0.830696 max=0.961088, sd=31.853945
 77: (234,238) : 0.844873 min=0.818146 max=0.956324, sd=34.399776
 78: ( 23,294) : 0.844943 min=0.621022 max=0.949541, sd=37.764103
 79: (346,138) : 0.845700 min=0.810804 max=0.953110, sd=14.134200
 80: ( 77,234) : 0.846210 min=0.686036 max=0.971412, sd=27.332991
 81: (246,147) : 0.847355 min=0.761658 max=0.934810, sd=25.801853
 82: ( 36,387) : 0.849379 min=0.556978 max=0.939926, sd=31.266600
 83: ( 37,132) : 0.858980 min=0.840427 max=0.964846, sd=28.677284
 84: (377,588) : 0.862735 min=0.872237 max=0.970159, sd=32.134697
 85: (414,219) : 0.862884 min=0.800279 max=0.964310, sd=49.752388
 86: (487,438) : 0.863833 min=0.747059 max=0.979435, sd=45.216511
 87: (410,252) : 0.866536 min=0.715012 max=0.973130, sd=40.093792
 88: (456,316) : 0.868468 min=0.763651 max=0.974714, sd=58.789257
 89: (122,372) : 0.868802 min=0.729907 max=0.961441, sd=56.564838
 90: (496,327) : 0.870879 min=0.763004 max=0.973176, sd=58.681850
 91: (329,556) : 0.874254 min=0.881908 max=0.970896, sd=31.454390
 92: (526,438) : 0.879686 min=0.762893 max=0.976885, sd=47.450890
 93: (150,220) : 0.881814 min=0.882721 max=0.967957, sd=32.738708
 94: (131,111) : 0.882507 min=0.872872 max=0.968983, sd=20.447971
 95: ( 81,162) : 0.884201 min=0.817418 max=0.973225, sd=20.495485
 96: (469,282) : 0.884335 min=0.824047 max=0.957199, sd=31.815765
 97: (329, 44) : 0.885706 min=0.709386 max=0.981219, sd=11.307715
 98: (132,520) : 0.891750 min=0.843875 max=0.961289, sd=29.145561
---------------------------------------------------------------
Start for 62.996056 dpi image.
         ImageSize =  274834[pixel]
Extracted features =   19678[pixel]
 Filtered features =    5546[pixel]
 585/ 586.
  Done.
Max feature = 264
  1: (218,316) : 0.299073 min=0.304809 max=0.759917, sd=32.745316
  2: (241,264) : 0.442451 min=0.468650 max=0.852405, sd=42.800758
  3: (343,162) : 0.522291 min=0.532134 max=0.832662, sd=19.292013
  4: (291,266) : 0.555949 min=0.566430 max=0.818171, sd=32.972832
  5: (198,377) : 0.579144 min=0.599708 max=0.885088, sd=31.428690
  6: (361, 58) : 0.597356 min=0.563315 max=0.838101, sd=24.265625
  7: ( 30,274) : 0.610389 min=0.558533 max=0.839348, sd=37.398823
  8: (356, 93) : 0.642492 min=0.562582 max=0.910453, sd=27.557285
  9: (272,146) : 0.642625 min=0.647387 max=0.888142, sd=36.778751
 10: (247,203) : 0.655644 min=0.607522 max=0.888964, sd=18.774765
 11: (445,129) : 0.657492 min=0.605634 max=0.900354, sd=21.833158
 12: (386,141) : 0.658648 min=0.580634 max=0.875339, sd=28.909412
 13: (164,318) : 0.660399 min=0.594899 max=0.871427, sd=41.966988
 14: (401,176) : 0.663473 min=0.615330 max=0.870816, sd=50.706532
 15: ( 25,476) : 0.666142 min=0.584288 max=0.796997, sd=44.584316
 16: (193,249) : 0.669973 min=0.557561 max=0.886984, sd=36.507587
 17: (397,307) : 0.678793 min=0.555734 max=0.922214, sd=51.067528
 18: (442,212) : 0.682467 min=0.583947 max=0.883672, sd=32.440998
 19: (111,247) : 0.684187 min=0.559310 max=0.916330, sd=43.400223
 20: (152,275) : 0.689893 min=0.553736 max=0.890511, sd=35.821602
 21: (360,334) : 0.698504 min=0.557189 max=0.904574, sd=27.466637
 22: (438,318) : 0.698831 min=0.568155 max=0.895427, sd=40.536594
 23: ( 75,307) : 0.725661 min=0.559957 max=0.916791, sd=35.221291
 24: (274,303) : 0.728531 min=0.707978 max=0.893694, sd=49.709797
 25: ( 66,274) : 0.730254 min=0.614685 max=0.896509, sd=48.425060
 26: (402,209) : 0.736482 min=0.695286 max=0.911938, sd=34.966595
 27: (400, 99) : 0.743005 min=0.676776 max=0.887349, sd=31.384359
 28: (363,295) : 0.744255 min=0.611384 max=0.929750, sd=53.099842
 29: (239,406) : 0.745581 min=0.713959 max=0.927647, sd=23.504589
 30: (164,382) : 0.747095 min=0.629141 max=0.908642, sd=24.382439
 31: (183,159) : 0.748735 min=0.667454 max=0.915189, sd=36.248268
 32: ( 34,192) : 0.750530 min=0.621623 max=0.944685, sd=23.935856
 33: (238,161) : 0.751193 min=0.552309 max=0.936504, sd=48.880821
 34: (166,200) : 0.753600 min=0.732554 max=0.925742, sd=25.132555
 35: (394, 58) : 0.756253 min=0.734319 max=0.884349, sd=37.938808
 36: ( 50,353) : 0.756988 min=0.690384 max=0.918900, sd=17.579617
 37: (206,445) : 0.760528 min=0.729659 max=0.946594, sd=32.205280
 38: ( 95,196) : 0.763886 min=0.569165 max=0.962252, sd=30.607454
 39: (349,196) : 0.764020 min=0.751454 max=0.930103, sd=27.746256
 40: (112,280) : 0.766336 min=0.572956 max=0.935878, sd=60.856461
 41: ( 28,307) : 0.773962 min=0.570268 max=0.905427, sd=30.422049
 42: (399,274) : 0.777244 min=0.585151 max=0.950410, sd=54.523579
 43: (328,250) : 0.777600 min=0.550693 max=0.945888, sd=51.436474
 44: (308,216) : 0.782334 min=0.799339 max=0.939470, sd=38.733139
 45: (444, 56) : 0.783281 min=0.681836 max=0.903799, sd=36.793564
 46: (125,449) : 0.796063 min=0.708768 max=0.926375, sd=21.610285
 47: (433,285) : 0.798618 min=0.595742 max=0.955567, sd=55.855915
 48: ( 23,227) : 0.801412 min=0.592979 max=0.937581, sd=36.052185
 49: (254,452) : 0.804453 min=0.748329 max=0.949197, sd=32.405952
 50: (190,124) : 0.808169 min=0.688386 max=0.911626, sd=28.636442
 51: (124,406) : 0.809441 min=0.732770 max=0.930859, sd=25.023130
 52: (352,402) : 0.810944 min=0.826716 max=0.954733, sd=36.062248
 53: (171,439) : 0.821105 min=0.781620 max=0.950627, sd=36.201202
 54: (281,105) : 0.825273 min=0.758560 max=0.943409, sd=13.854691
 55: (107,140) : 0.826479 min=0.774573 max=0.955824, sd=32.626545
 56: (287,336) : 0.826928 min=0.759029 max=0.939734, sd=48.020237
 57: (287,464) : 0.827072 min=0.842281 max=0.957651, sd=37.085400
 58: (157,242) : 0.829749 min=0.709671 max=0.956223, sd=54.552681
 59: (438,352) : 0.831481 min=0.772146 max=0.956499, sd=40.525841
 60: (365,259) : 0.833032 min=0.636060 max=0.960499, sd=53.648716
 61: (437,176) : 0.835733 min=0.706491 max=0.948475, sd=57.130863
 62: (437,250) : 0.846487 min=0.736950 max=0.949449, sd=35.986832
 63: (104, 86) : 0.848287 min=0.819719 max=0.960537, sd=20.586964
 64: (395,355) : 0.853023 min=0.674944 max=0.976931, sd=43.385296
 65: (206,208) : 0.855907 min=0.814666 max=0.962084, sd=64.798088
 66: (261, 35) : 0.857782 min=0.658946 max=0.974178, sd=9.765615
 67: (311,299) : 0.859072 min=0.721597 max=0.964489, sd=64.371178
 68: (129,174) : 0.863501 min=0.847128 max=0.957214, sd=30.939293
 69: (437,389) : 0.867711 min=0.800812 max=0.967650, sd=39.102413
 70: (307,161) : 0.871376 min=0.724515 max=0.966266, sd=48.850288
 71: ( 28,109) : 0.876220 min=0.845073 max=0.971295, sd=42.473747
 72: (243,373) : 0.892422 min=0.717912 max=0.979466, sd=28.400930
 73: (138, 87) : 0.892945 min=0.786420 max=0.979330, sd=20.448406
 74: (391,393) : 0.896210 min=0.851089 max=0.980158, sd=41.161392
 75: (160,472) : 0.898482 min=0.736852 max=0.979373, sd=40.656662
 76: ( 91,405) : 0.898493 min=0.820945 max=0.958475, sd=29.872866
---------------------------------------------------------------
Start for 50.000000 dpi image.
         ImageSize =  172980[pixel]
Extracted features =   13198[pixel]
 Filtered features =    3487[pixel]
 464/ 465.
  Done.
Max feature = 160
  1: (190,217) : 0.409095 min=0.423076 max=0.786830, sd=38.354855
  2: (157,322) : 0.565809 min=0.609225 max=0.883308, sd=27.912880
  3: (285,131) : 0.576045 min=0.579438 max=0.813340, sd=21.002932
  4: (200,113) : 0.579516 min=0.587601 max=0.884169, sd=38.661457
  5: (231,211) : 0.644444 min=0.625607 max=0.872402, sd=40.615192
  6: (126,251) : 0.656507 min=0.591580 max=0.855815, sd=43.474426
  7: (321, 75) : 0.657504 min=0.555764 max=0.898058, sd=30.923130
  8: (280, 75) : 0.662833 min=0.576045 max=0.902070, sd=26.458992
  9: (320,140) : 0.662949 min=0.665047 max=0.875006, sd=49.367023
 10: ( 28,235) : 0.670349 min=0.561400 max=0.865629, sd=37.549335
 11: (293,238) : 0.675475 min=0.555582 max=0.905002, sd=48.826569
 12: (197,344) : 0.677357 min=0.646990 max=0.927771, sd=27.972940
 13: ( 74,207) : 0.686276 min=0.550450 max=0.910061, sd=53.431999
 14: (284,272) : 0.689275 min=0.618263 max=0.907108, sd=31.436350
 15: (138,194) : 0.709105 min=0.581470 max=0.902980, sd=40.365704
 16: (178,184) : 0.713734 min=0.673753 max=0.908628, sd=50.451111
 17: (285, 42) : 0.714805 min=0.704401 max=0.883490, sd=31.044941
 18: ( 27,148) : 0.716260 min=0.604710 max=0.933287, sd=26.231071
 19: ( 76,149) : 0.717083 min=0.556839 max=0.948899, sd=29.302229
 20: (348,253) : 0.718400 min=0.567854 max=0.910843, sd=47.042545
 21: (235,100) : 0.720351 min=0.730358 max=0.906248, sd=25.519068
 22: (265,181) : 0.720452 min=0.635529 max=0.935623, sd=45.270584
 23: (226,245) : 0.729541 min=0.752331 max=0.915800, sd=54.769844
 24: (112,345) : 0.730325 min=0.650699 max=0.904523, sd=28.654446
 25: (326,175) : 0.734137 min=0.726759 max=0.906466, sd=32.581650
 26: ( 26,381) : 0.742655 min=0.622288 max=0.815669, sd=40.283253
 27: (163,355) : 0.745526 min=0.664041 max=0.940655, sd=36.527069
 28: (147,116) : 0.752473 min=0.553108 max=0.913527, sd=40.662380
 29: (279,319) : 0.754339 min=0.768570 max=0.938685, sd=34.522438
 30: (342, 40) : 0.781405 min=0.728405 max=0.901987, sd=37.145031
 31: ( 36,184) : 0.797876 min=0.558383 max=0.915193, sd=32.620537
 32: ( 62,264) : 0.799267 min=0.722797 max=0.931799, sd=40.063858
 33: (109,141) : 0.799847 min=0.774071 max=0.929137, sd=28.837950
 34: (317,292) : 0.803153 min=0.607517 max=0.961875, sd=44.224556
 35: (327,220) : 0.805617 min=0.606686 max=0.948058, sd=57.030193
 36: (207, 28) : 0.806086 min=0.553510 max=0.963031, sd=8.954105
 37: (248,147) : 0.813065 min=0.590033 max=0.949263, sd=49.212040
 38: ( 79,313) : 0.814844 min=0.726460 max=0.922312, sd=27.738249
 39: (147,149) : 0.854165 min=0.788547 max=0.963051, sd=63.804325
 40: ( 22, 91) : 0.863481 min=0.822804 max=0.965674, sd=48.539753
 41: (213,379) : 0.864024 min=0.814080 max=0.966658, sd=43.544121
 42: (343,326) : 0.868105 min=0.831030 max=0.970583, sd=46.397461
 43: (123, 82) : 0.877267 min=0.830728 max=0.967012, sd=36.181847
 44: (123,378) : 0.886550 min=0.733276 max=0.976608, sd=42.743977
 45: ( 67, 60) : 0.897586 min=0.874908 max=0.975650, sd=26.763504
---------------------------------------------------------------
  Done.
Saving FeatureSet...
  Done.
Generating FeatureSet3...
(893, 1117) 120.000000[dpi]
Freak features - 636========= 636 ===========
(744, 931) 100.000008[dpi]
Freak features - 654========= 654 ===========
(591, 739) 79.370056[dpi]
Freak features - 613========= 613 ===========
(469, 586) 62.996056[dpi]
Freak features - 600========= 600 ===========
(372, 465) 50.000000[dpi]
Freak features - 589========= 589 ===========
  Done.
Saving FeatureSet3...
  Done.
Generator finished at 2017-02-15 09:40:42 +1100
--

 

  • 查看特征点

 

After launching dispFeatureSet, the various image resolutions will be displayed on screen with the tracking features overlaid. The features used in continuous tracking are outlined by red boxes, and the features used in identifying the pages andinitializing tracking are marked by green crosses. 

 

 

 

Debugging Marker Recognition Problems

If you also wish to display pose-estimates errors or wish to check recognition of template markers, you will need to define a multi-marker configuration file first.

By default, check_id reads its multimarker configuration from up to two multimarker configuration files specified on the command line. You can test (for example) using the pre-supplied file Data/cubeMarkerConfig.dat (which is set to track the cube marker whose image is supplied in PDF form in doc/patterns/Cubes/cube00-05-a4.pdf or /doc/patterns/Cubes/cube00-05-latter.pdf) using the following launch syntax. On Linux / OS X, type:

  1 #the number of patterns to be recognized
  2 6
  3 
  4 #marker 1
  5 00
  6 40.0
  7  1.0000  0.0000  0.0000    0.0000
  8  0.0000  1.0000  0.0000    0.0000
  9  0.0000  0.0000  1.0000    0.0000
 10 
 11 #marker 2
 12 01
 13 40.0
 14  1.0000  0.0000  0.0000    0.0000
 15  0.0000  0.0000  1.0000   30.0000
 16  0.0000 -1.0000  0.0000  -30.0000
 17 
 18 #marker 3
 19 02
 20 40.0
 21  0.0000  0.0000  1.0000   30.0000
 22  0.0000  1.0000  0.0000    0.0000
 23 -1.0000  0.0000  0.0000  -30.0000
 24 
 25 #marker 4
 26 03
 27 40.0
 28  1.0000  0.0000  0.0000    0.0000
 29  0.0000 -1.0000  0.0000    0.0000
 30  0.0000  0.0000 -1.0000  -60.0000
 31 
 32 #marker 5
 33 04
 34 40.0
 35  1.0000  0.0000  0.0000    0.0000
 36  0.0000  0.0000 -1.0000  -30.0000
 37  0.0000  1.0000  0.0000  -30.0000
 38 
 39 #marker 6
 40 05
 41 40.0
 42  0.0000  0.0000 -1.0000  -30.0000
 43  0.0000  1.0000  0.0000    0.0000
 44  1.0000  0.0000  0.0000  -30.0000
cubeMarkerConfig.dat

 

日后再说。

posted @ 2017-02-15 06:59  郝壹贰叁  阅读(1477)  评论(0)  编辑  收藏  举报