tunning comskip.int

To discuss the tuning of comskip and for posting your ini files
Post Reply
runningcat
Posts: 3
Joined: Mon Mar 19, 2012 10:19 am

tunning comskip.int

Post by runningcat »

I have been tuning comskip.ini for several days, but the result is always not ideal. the commercials found is about 74%, what's worse, there are many FPs, how can I improve. here is the comskip.ini and log file.

Code: Select all

detect_method=43            ;1=black frame, 2=logo, 4=scene change, 8=fuzzy logic, 16=closed captions, 32=aspect ration, 64=silence, 128=cutscenes, 255=all
validate_silence=1          ; Default, set to 0 to force using this clues if selected above.
validate_uniform=1          ; Default, set to 0 to force using this clues (like pure white frames) if blackframe is selected above.
validate_scenechange=1      ; Default, set to 0 to force using this clues if selected above.
verbose=10              ;show a lot of extra info, level 5 is also OK, set to 0 to disable
non_uniformity=500          ; Set to 0 to disable cutpoints based on uniform frames
max_volume=300              ; any frame with sound volume larger than this will not be regarded as black frame
min_silence=12              ; Any deep silence longer than this amount  of frames is a possible cutpoint
ticker_tape=0               ; Amount of pixels from bottom to ignore in all processing
logo_at_bottom=0            ; Set to 1 to search only for logo at the lower half of the video, do not combine with subtitle setting
punish=0                    ; Compare to average for sum of 1=brightness, 2=uniform 4=volume, 8=silence, 16=schange, set to 0 to disable
punish_threshold=1.3        ; Multiply when amount is above average * punish_threshold
punish_modifier=2           ; When above average * threshold multiply score by this value
intelligent_brightness=0        ; Set to 1 to use a USA specific algorithm to tune some of the settings, not adviced outside the USA
logo_percentile=0.92            ; if more then this amount of logo is found then logo detection will be disabled
logo_threshold=0.75
punish_no_logo=1            ; Default, set to 0 to avoid show segments without logo to be scored towards commercial
aggressive_logo_rejection=0
connect_blocks_with_logo=1      ; set to 1 if you want successive blocks with logo on the transition to be regarded as connected, set to 0 to disable
logo_filter=0               ; set the size of the filter to apply to bad logo detection, 4 seems to be a good value.
cut_on_ar_change=1          ; set to 1 if you want to cut also on aspect ratio changes when logo is present, set to 2 to force cuts on aspect ratio changes. set to 0 to disable
delete_show_after_last_commercial=0 ; set to 1 if you want to delete the last block if its a show and after a commercial
delete_show_before_or_after_current=0   ; set to 1 if you want to delete the previous and the next show in the recording, this can lead to the deletion of trailers of next show
delete_block_after_commercial=0 ;set to max size of block in seconds to be discarded, set to 0 to disable
remove_before=0             ; amount of seconds of show to be removed before ALL commercials
remove_after=0              ; amount of seconds of show to be removed after ALL commercials
shrink_logo=5               ; Reduce the duration of the logo with this amount of seconds
after_logo=0        ; set to number of seconds after logo disappears comskip should start to search for silence to insert an additional cutpoint
padding=0
ms_audio_delay=5
volume_slip=20
skip_b_frames=0             ; Set to 1 to force Comskip to skip frames for higher processing speed.
max_repair_size=200         ; Will repair maximum 200 missing MPEG frames in the timeline, set to 0 to disable repairing for players that don't use PTS. 
disable_heuristics=4        ;bit pattern for disabling heuristics, adding 1 disables heristics 1, adding 2 disables heristics 2, adding 4 disables heristics 3, 255  disables all heuristics 
delete_logo_file=0          ; set to 1 if you want comskip to tidy up after finishing
output_framearray=0         ; create a big excel file for detailed analysis, set to 0 to disable
output_videoredo=0
output_womble=0
output_mls=0            ; set to 1 if you want MPeg Video Wizard bookmark file output
output_cuttermaran=0
output_mpeg2schnitt=0
output_mpgtx=0
output_dvrcut=0
output_zoomplayer_chapter=0
output_zoomplayer_cutlist=0
output_edl=1
output_edlx=0
output_vcf=0
output_bsplayer=0
output_btv=0                ; set to 1 if you want Beyond TV chapter cutlist output
output_projectx=0           ; set to 1 if you want ProjectX cutlist output (Xcl)
output_avisynth=0
output_vdr=0                ; set to 1 if you want XBMC to skipping commercials
output_demux=0              ; set to 1 if you want comskip to demux the mpeg file while scanning
sage_framenumber_bug=0
sage_minute_bug=0
live_tv=0                   ; set to 1 if you use parallelprocessing and need the output while recording
live_tv_retries=4           ; change to 16 when using live_tv in BTV, used for mpeg PS and TS
dvrms_live_tv_retries=300           ; only used for dvr_ms
standoff=0                  ; change to 8000000 when using live_tv in BTV
cuttermaran_options="cut=\"true\" unattended=\"true\" muxResult=\"false\" snapToCutPoints=\"true\" closeApp=\"true\""
mpeg2schnitt_options="mpeg2schnitt.exe /S /E /R25  /Z %2 %1"
avisynth_options="LoadPlugin(\"MPEG2Dec3.dll\") \nMPEG2Source(\"%s\")\n"
dvrcut_options="dvrcut \"%s.dvr-ms\" \"%s_clean.dvr-ms\" "
windowtitle="Comskip - %s"


max_brightness=60               ;frame not black if any pixels checked are greater than this (scale 0 to 255)
test_brightness=40              ;frame not pure black if any pixels checked are greater than this, will check average brightness (scale 0 to 255)
max_avg_brightness=20           ;maximum average brightness for a dim frame to be considered black (scale 0 to 255) 0 means autosetting
max_commercialbreak=600         ;maximum length in seconds to consider a segment a commercial break
min_commercialbreak=10          ;minimum length in seconds to consider a segment a commercial break
max_commercial_size=125         ;maximum time in seconds for a single commercial or multiple commercials if no breaks in between
min_commercial_size=4           ;mimimum time in seconds for a single commercial
min_show_segment_length=120     ; any segment longer than this will be scored towards show.
                                                                                                                                             75,17         Bot
log file

Code: Select all

 #     sbf  bs  be     fs     fe    sc      len   scr cmb   ar                   cut bri  logo   vol  sil corr stdev        cc
  0:++   10   0  10      1   5352   0.02  214.040  0.15   0 2.17          AE         b   751+ 0.00  461+  9+  0.000    75
  1:--   29  10  19   5353   7630   6.00   91.080  0.14   0 2.17          A    S     b   989+ 0.00  386+  9+  0.000    98
  2:++   49  19  30   7631  14843   0.00  288.480  0.08   0 2.17          AE         b   356- 0.00  397+  9+  0.000    35
  3:++   47  31  16  14844  34282   0.00  777.520  0.11   0 1.57           E         b   413- 0.00  407+  9+  0.000    41
  4:++   18  17   1  34283  37792   0.01  140.360  0.17   0 1.57           E         b   831+ 0.00  417+  8+  0.000    83
  5:--    2   2   0  37793  38185   5.44   15.680  0.35   3 1.96          A  C       b  1717+ 0.00  341+  60  0.000   171
  6:--    1   1   0  38186  38403   8.16    8.680  0.54   4 1.96          A  C       b  2848+ 0.00  467+  9+  0.000   284
  7:--   16   1  15  38404  38816   3.63   16.480  0.20   2 1.96          A  C       b  1893+ 0.00  302+  60  0.000   189
  8:++   16  15   1  38817  53008   0.00  567.640  0.10   0 1.96          AE         b   424- 0.00  418+  9+  0.000    42
  9:++   15   1  14  53009  57520   0.02  180.440  0.07   0 1.96          AE         b   554+ 0.00  426+  9+  0.000    55
 10:++   28  14  14  57521  63870   0.00  253.960  0.10   0 1.57           E         b   520+ 0.00  409+  9+  0.000    52
 11:--   16  15   1  63871  64990   3.00   44.760  0.11   0 1.57               S     b   863+ 0.00  409+ 10+  0.000    86
 12:--    2   2   0  64991  65086   2.00    3.800  0.21   0 1.96          A          b   635+ 0.00  404+  7+  0.000    63
 13:--   17   1  16  65087  67500   2.00   96.520  0.16   0 1.96          A          b   699+ 0.00  398+  9+  0.000    69
 14:++   31  16  15  67501  91005   0.00  940.160  0.10   0 1.57           E         b   438- 0.00  407+  8+  0.000    43
 15:++   17  16   1  91006  93115   1.00   84.360  0.09   0 1.57                     b   805+ 0.00  401+  9+  0.000    80
 16:++   15   1  14  93116  94928   1.00   72.480  0.15   0 1.57                     b   722+ 0.00  418+  9+  0.000    72
 17:++   16  15   1  94929 107424   0.00  499.800  0.06   0 1.57           E         b   325- 0.00  394+  8+  0.000    32
 18:++    1   1   0 107425 109228   1.00   72.120  0.18   0 1.57                     b  1000+ 0.00  420+  8+  0.000   100
 19:++   15   1  14 109229 111042   1.00   72.520  0.11   0 1.57                     b   803+ 0.00  426+  9+  0.000    80
 20:++   29  15  14 111043 118071   0.00  281.120  0.13   0 1.96          AE         b   492- 0.00  417+  9+  0.000    49
 21:--   21  15   6 118072 118990   3.45   36.720  0.31   2 1.96          A  C       b  1795+ 0.00  447+  9+  0.000   179
 22:--    9   7   2 118991 119318   3.45   13.080  0.10   2 2.05          A  C       b   432- 0.00  420+  7+  0.000    43
 23:--    5   2   3 119319 119427   2.00    4.320  0.28   0 2.05          A          b   321- 0.00  535+  9+  0.000    32
 24:--    3   3   0 119428 120629   2.00   48.040  0.08   0 2.05          A          b   629+ 0.00  420+  9+  0.000    62
 25:--   18   1  17 120630 121545   2.00   36.600  0.23   0 2.05          A          b   816+ 0.00  471+  9+  0.000    81
 26:++   25  17   8 121546 141627   0.00  803.240  0.10   0 1.57           E         b   406- 0.00  418+  9+  0.000    40
 27:++   11   9   2 141628 144335   1.00  108.280  0.09   0 1.57                     b   667+ 0.00  401+  8+  0.000    66
 28:++   26   3  23 144336 145257   1.00   36.840  0.22   0 1.57                     b   949+ 0.00  414+  7+  0.000    94
 29:++   31  23   8 145258 162005   0.00  669.880  0.06   0 1.57           E         b   306- 0.00   24-  0-  0.000    30
 30:++   10   9   1 162006 165005   1.00  119.960  0.10   0 1.57                     b   669+ 0.00    0-  0-  0.000    66
 31:++   17   1  16 165006 165921   1.00   36.600  0.28   0 1.57                     b  1729+ 0.00    0-  0-  0.000   172
 32:++   33  16  17 165922 175510   0.00  383.520  0.15   0 1.57           E         b   707+ 0.00    0-  0-  0.000    70
 33:++   25  17   8 175511 195825   0.00  812.560  0.08   0 1.57           E         b   369- 0.00    0-  0-  0.000    36
 34:--    9   8   1 195826 195982   2.25    6.240  0.17   2 1.57             C       b  1815+ 0.00    0-  0-  0.000   181
 35:--    2   1   1 195983 197331  10.13   53.920  0.12   4 1.96          A  C       b  1002+ 0.00    0-  0-  0.000   100
 36:--    5   1   4 197332 198225  10.13   35.720  0.03   4 2.43          A  C       b   350- 0.00    0-  0-  0.000    35
 37:--   22   5  17 198226 199596   4.50   54.800  0.19   2 2.43          A  C       b   827+ 0.00    0-  0-  0.000    82
 38:++   26  18   8 199597 212368   0.00  510.840  0.08   0 2.43          AE         b   329- 0.00    0-  0-  0.000    32
 39:--    9   8   1 212369 213277   2.00   36.320  0.15   0 2.43          A          b  1082+ 0.00    0-  0-  0.000   108
 40:--    6   2   4 213278 215289   2.00   80.440  0.15   0 2.43          A          b   693+ 0.00    0-  0-  0.000    69
 41:--    4   4   0 215290 215375   4.50    3.400  0.13   2 1.96          A  C       b   546+ 0.00    0-  0-  0.000    54
 42:--    1   1   0 215376 215787   4.50   16.440  0.04   2 1.96          A  C       b   291- 0.00    0-  0-  0.000    29
erik
Site Admin
Posts: 3368
Joined: Sun Aug 21, 2005 3:49 pm

Re: tunning comskip.int

Post by erik »

Please follow the "how to ask for help" post and I will be glad to help you tune.
LastButNotLeast
Posts: 39
Joined: Tue Jan 31, 2012 12:13 am

Re: tunning comskip.int

Post by LastButNotLeast »

Which is here:
viewtopic.php?f=5&t=34
Post Reply