Unsupervised Multiresolution Segmentation for Images with Low Depth of Field

  • Authors:
  • James Z. Wang;Jia Li;Robert M. Gray;Gio Wiederhold

  • Affiliations:
  • Pennsylvania State Univ., University Park;Pennsylvania State Univ., University Park;Stanford Univ., Stanford, CA;Stanford Univ., Stanford, CA

  • Venue:
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Year:
  • 2001

Quantified Score

Hi-index 0.15

Visualization

Abstract

Unsupervised segmentation of images with low depth of field (DOF) is highly useful in various applications including image enhancement for digital cameras, target recognition, image indexing for content-based retrieval, and 3D microscopic image analysis. This paper describes a novel multiresolution image segmentation algorithm for low DOF images. The algorithm is designed to separate a sharply focused object-of-interest from other foreground or background objects. The algorithm is fully automatic in that all parameters are image independent. A multiscale approach based on high frequency wavelet coefficients and their statistics is used to perform context-dependent classification of individual blocks of the image. Unlike other edge-based approaches, our algorithm does not rely on the process of connecting object boundaries. The algorithm has achieved high accuracy when tested on more than 100 low DOF images, many with inhomogeneous foreground or background distractions. Compared with the state of the art algorithms, this new algorithm provides better accuracy at higher speed.