Measuring the Objectness of Image Windows

B. Alexe, T. Deselaers, V. Ferrari

Research output: Contribution to journalArticlepeer-review

Abstract / Description of output

We present a generic objectness measure, quantifying how likely it is for an image window to contain an object of any class. We explicitly train it to distinguish objects with a well-defined boundary in space, such as cows and telephones, from amorphous background elements, such as grass and road. The measure combines in a Bayesian framework several image cues measuring characteristics of objects, such as appearing different from their surroundings and having a closed boundary. These include an innovative cue to measure the closed boundary characteristic. In experiments on the challenging PASCAL VOC 07 dataset, we show this new cue to outperform a state-of-the-art saliency measure, and the combined objectness measure to perform better than any cue alone. We also compare to interest point operators, a HOG detector, and three recent works aiming at automatic object segmentation. Finally, we present two applications of objectness. In the first, we sample a small numberof windows according to their objectness probability and give an algorithm to employ them as location priors for modern class-specific object detectors. As we show experimentally, this greatly reduces the number of windows evaluated by the expensive class-specific model. In the second application, we use objectness as a complementary score in addition to the class-specific model, which leads to fewer false positives. As shown in several recent papers, objectness can act as a valuable focus of attention mechanism in many other applications operating on image windows, including weakly supervised learning of object categories, unsupervised pixelwise segmentation, and object tracking in video. Computing objectness is very efficient and takes only about 4 sec. per image.
Original languageEnglish
Pages (from-to)2189-2202
Number of pages14
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Issue number11
Publication statusPublished - 1 Nov 2012

Keywords / Materials (for Non-textual outputs)

  • Bayes methods
  • image segmentation
  • learning (artificial intelligence)
  • object detection
  • object tracking
  • video signal processing
  • Bayesian framework
  • HOG detector
  • PASCAL VOC 07 dataset
  • amorphous background element
  • attention mechanism
  • automatic object segmentation
  • class-specific object detector
  • closed boundary characteristic
  • generic objectness measure
  • image window
  • interest point operator
  • object boundary
  • object category
  • objectness probability
  • supervised learning
  • unsupervised pixelwise segmentation
  • video object tracking
  • Area measurement
  • Detectors
  • Image color analysis
  • Image edge detection
  • Image segmentation
  • Kernel
  • Training
  • Objectness measure
  • object recognition
  • Algorithms
  • Artificial Intelligence
  • Bayes Theorem
  • Image Enhancement
  • Image Interpretation, Computer-Assisted
  • Imaging, Three-Dimensional
  • Pattern Recognition, Automated
  • Reproducibility of Results
  • Sensitivity and Specificity
  • Subtraction Technique


Dive into the research topics of 'Measuring the Objectness of Image Windows'. Together they form a unique fingerprint.

Cite this