Skip to main content

Table 1 The results of the gel segment detection classifiers (top) and the gel panel detection algorithm (bottom)

From: Mining images in biomedical publications: Detection and analysis of gel diagrams

  Method Threshold Precision Recall F-score ROC area
   0.15 0.439 0.909 0.592  
  Random forests 0.30 0.765 0.739 0.752 0.980
   0.60 0.926 0.301 0.455  
Segments Naive Bayes   0.172 0.739 0.279 0.883
  Bayesian network   0.394 0.531 0.452 0.914
  PART decision list   0.631 0.496 0.555 0.777
  Convolutional networks   0.142 0.949 0.248  
Panels Hand-coded rules   0.951 0.368 0.530