Home  > AI Exhibit Scorers - Alpha > FREE for your Website, PC and...   [+]
77GB+ of FREE images, sounds and more! (Exhibits: 35,951)
DHD Multimedia Gallery
[mirrors: home us uk]       [en_GB][de][es]
 
 

AI Exhibit Scorers - Alpha

FREE for your Website, PC and Projects!

 

Gallery AI Exhibit Scorers Alpha

This is a small project to try to develop (using Genetic Algorithms) a set of simple Java classes for guessing an exhibit's likely appeal to Gallery users. In the first instance this is restricted to 2D still images.

Though this is based on classical GA techniques for finding optimal Scorers (eg random mutation, breeding, selection, etc) this also attempts to speed up the search for optimality by using conventional mathematical "error minimisation" techniques/algorithms (such as the FreeHEP Java Minuit minimiser/optimiser) widely used in numerical optimisation in the physical sciences and the financial markets for example. This brings the exotic skills of the numerical mathematicians to bear on the problem in tandem with the Artificial Intelligenciers!

One use of this is to help predict at or before upload of new images to the Gallery those that are likely to be most popular. The contributor may then choose to upload or not, and/or create more variations rather than waiting for bouquets or brickbats from the users.

Another possible use is to automatically produce a "tweaked" version of an existing exhibit more likely to appeal to Gallery visitors.

Status

The current set of available "best" exhibit Scorers (with a total population of 7788) is: [FixedScore:resultScore=82, LocalSampler:sampleSizePower=11:outlierFractionPower=6:component=Y:sampleCombination=RANGE:pixelSampleMethod=VALUE:S0=23171:S1=26688:S2=26054:S3=1486:S4=23747:S5=22576:S6=25098:S7=22158:S8=14588:S9=20142:Sa=25884:Sb=23946:Sc=19480:Sd=25053:Se=14405:Sf=23285:Sg=13558:C0=32767:C1=32762:C2=32638:C3=32767:C4=32767:C5=32767:C6=32767:C7=32767:C8=32767:C9=32767:Ca=32765:Cb=32767:Cc=32767:Cd=32767:Ce=32765:Cf=32767:Cg=32767, LocalSampler:sampleSizePower=11:outlierFractionPower=6:component=Y:sampleCombination=RANGE:pixelSampleMethod=VALUE:S0=23316:S1=24856:S2=23610:S3=2117:S4=23428:S5=12724:S6=25178:S7=23910:S8=15196:S9=20638:Sa=24299:Sb=24276:Sc=19133:Sd=25170:Se=13838:Sf=24069:Sg=16372:C0=32762:C1=32743:C2=32767:C3=32583:C4=32767:C5=32767:C6=32767:C7=32747:C8=32756:C9=32767:Ca=32767:Cb=32767:Cc=32767:Cd=32767:Ce=32767:Cf=32767:Cg=32723, LocalSampler:sampleSizePower=11:outlierFractionPower=6:component=Y:sampleCombination=RANGE:pixelSampleMethod=VALUE:S0=24128:S1=26276:S2=25273:S3=3581:S4=23135:S5=20878:S6=22928:S7=20256:S8=17290:S9=19802:Sa=22787:Sb=23206:Sc=21089:Sd=23447:Se=16594:Sf=23746:Sg=13265:C0=32767:C1=32489:C2=32767:C3=32651:C4=32718:C5=32767:C6=32764:C7=32767:C8=32767:C9=32767:Ca=32767:Cb=32767:Cc=32767:Cd=32767:Ce=32767:Cf=32767:Cg=32767, MaxScore, RandomPositiveScore, RandomScore, SimpleExposure:sampleSizePower=12:brightnessRangePercent=27:outlierFractionPower=7, SimpleExposure:sampleSizePower=9:brightnessRangePercent=19:outlierFractionPower=5, SimpleExposure:sampleSizePower=9:brightnessRangePercent=34:outlierFractionPower=9, ZeroScore].

The current raw unweighted score of a popular JPEG (bell of four masted barque Sedov mono tweaked retouched 2 BG.jpg) by of each of the Scorers is as follows:

  • FixedScore:resultScore=82: score=20970/32767:confidence=32767/32767
  • LocalSampler:sampleSizePower=11:outlierFractionPower=6:component=Y:sampleCombination=RANGE:pixelSampleMethod=VALUE:S0=23171:S1=26688:S2=26054:S3=1486:S4=23747:S5=22576:S6=25098:S7=22158:S8=14588:S9=20142:Sa=25884:Sb=23946:Sc=19480:Sd=25053:Se=14405:Sf=23285:Sg=13558:C0=32767:C1=32762:C2=32638:C3=32767:C4=32767:C5=32767:C6=32767:C7=32767:C8=32767:C9=32767:Ca=32765:Cb=32767:Cc=32767:Cd=32767:Ce=32765:Cf=32767:Cg=32767: score=23659/32767:confidence=32767/32767
  • LocalSampler:sampleSizePower=11:outlierFractionPower=6:component=Y:sampleCombination=RANGE:pixelSampleMethod=VALUE:S0=23316:S1=24856:S2=23610:S3=2117:S4=23428:S5=12724:S6=25178:S7=23910:S8=15196:S9=20638:Sa=24299:Sb=24276:Sc=19133:Sd=25170:Se=13838:Sf=24069:Sg=16372:C0=32762:C1=32743:C2=32767:C3=32583:C4=32767:C5=32767:C6=32767:C7=32747:C8=32756:C9=32767:Ca=32767:Cb=32767:Cc=32767:Cd=32767:Ce=32767:Cf=32767:Cg=32723: score=23660/32767:confidence=32767/32767
  • LocalSampler:sampleSizePower=11:outlierFractionPower=6:component=Y:sampleCombination=RANGE:pixelSampleMethod=VALUE:S0=24128:S1=26276:S2=25273:S3=3581:S4=23135:S5=20878:S6=22928:S7=20256:S8=17290:S9=19802:Sa=22787:Sb=23206:Sc=21089:Sd=23447:Se=16594:Sf=23746:Sg=13265:C0=32767:C1=32489:C2=32767:C3=32651:C4=32718:C5=32767:C6=32764:C7=32767:C8=32767:C9=32767:Ca=32767:Cb=32767:Cc=32767:Cd=32767:Ce=32767:Cf=32767:Cg=32767: score=22857/32767:confidence=32767/32767
  • MaxScore: score=32767/32767:confidence=32767/32767
  • RandomPositiveScore: score=2837/32767:confidence=2837/32767
  • RandomScore: score=9613/32767:confidence=32767/32767
  • SimpleExposure:sampleSizePower=12:brightnessRangePercent=27:outlierFractionPower=7: score=32767/32767:confidence=32767/32767
  • SimpleExposure:sampleSizePower=9:brightnessRangePercent=19:outlierFractionPower=5: score=32767/32767:confidence=32767/32767
  • SimpleExposure:sampleSizePower=9:brightnessRangePercent=34:outlierFractionPower=9: score=32767/32767:confidence=32767/32767
  • ZeroScore: score=0:confidence=32767/32767
with the composite predicted exhibit score: score=23334/32767:confidence=2898/32767.

The current "ratings" of each of the best and base Scorers is as follows:

  • FixedScore: score=9327/32767:confidence=4254/32767 [0.03695439]
  • FixedScore:resultScore=82: score=22293/32767:confidence=4254/32767 [0.088326834]
  • LocalSampler: score=20438/32767:confidence=3050/32767 [0.058058374]
  • LocalSampler:sampleSizePower=11:outlierFractionPower=6:component=Y:sampleCombination=RANGE:pixelSampleMethod=VALUE:S0=23171:S1=26688:S2=26054:S3=1486:S4=23747:S5=22576:S6=25098:S7=22158:S8=14588:S9=20142:Sa=25884:Sb=23946:Sc=19480:Sd=25053:Se=14405:Sf=23285:Sg=13558:C0=32767:C1=32762:C2=32638:C3=32767:C4=32767:C5=32767:C6=32767:C7=32767:C8=32767:C9=32767:Ca=32765:Cb=32767:Cc=32767:Cd=32767:Ce=32765:Cf=32767:Cg=32767: score=22454/32767:confidence=4228/32767 [0.08842098]
  • LocalSampler:sampleSizePower=11:outlierFractionPower=6:component=Y:sampleCombination=RANGE:pixelSampleMethod=VALUE:S0=23316:S1=24856:S2=23610:S3=2117:S4=23428:S5=12724:S6=25178:S7=23910:S8=15196:S9=20638:Sa=24299:Sb=24276:Sc=19133:Sd=25170:Se=13838:Sf=24069:Sg=16372:C0=32762:C1=32743:C2=32767:C3=32583:C4=32767:C5=32767:C6=32767:C7=32747:C8=32756:C9=32767:Ca=32767:Cb=32767:Cc=32767:Cd=32767:Ce=32767:Cf=32767:Cg=32723: score=22416/32767:confidence=4228/32767 [0.08827134]
  • LocalSampler:sampleSizePower=11:outlierFractionPower=6:component=Y:sampleCombination=RANGE:pixelSampleMethod=VALUE:S0=24128:S1=26276:S2=25273:S3=3581:S4=23135:S5=20878:S6=22928:S7=20256:S8=17290:S9=19802:Sa=22787:Sb=23206:Sc=21089:Sd=23447:Se=16594:Sf=23746:Sg=13265:C0=32767:C1=32489:C2=32767:C3=32651:C4=32718:C5=32767:C6=32764:C7=32767:C8=32767:C9=32767:Ca=32767:Cb=32767:Cc=32767:Cd=32767:Ce=32767:Cf=32767:Cg=32767: score=22515/32767:confidence=4228/32767 [0.088661194]
  • MaxScore: score=16991/32767:confidence=4254/32767 [0.06731983]
  • MinScore: score=-21981/32767:confidence=4254/32767 [-0.087090656]
  • NoConfidence: score=0:confidence=0 [0.0]
  • RandomPositiveScore: score=19624/32767:confidence=2178/32767 [0.039808154]
  • RandomScore: score=2511/32767:confidence=4254/32767 [0.009948803]
  • SimpleExposure: score=17678/32767:confidence=3941/32767 [0.064888276]
  • SimpleExposure:sampleSizePower=12:brightnessRangePercent=27:outlierFractionPower=7: score=17044/32767:confidence=4197/32767 [0.066624984]
  • SimpleExposure:sampleSizePower=9:brightnessRangePercent=19:outlierFractionPower=5: score=17112/32767:confidence=4192/32767 [0.06681111]
  • SimpleExposure:sampleSizePower=9:brightnessRangePercent=34:outlierFractionPower=9: score=17100/32767:confidence=4195/32767 [0.06681203]
  • ZeroScore: score=9327/32767:confidence=4254/32767 [0.03695439]

You can interact with the AI system on the remote page.

20-Nov-2017 You may wish to use the Reload/Refresh button on your browser to ensure that this page is up-to-date.
Site copyright (c) Damon Hart-Davis 1996-2013; exhibit content copyright of specified creator; see terms and conditions for use. Site sponsored by ExNet. Powered by Javatm, tuned with JProfilertm.0u 3ms-