Alternative String Alignment methods for Object Recognition based on Image Segmentation
This is a semester project I currently work on under the leadership of Volker Roth of the Institute of Computional Science
at ETH Zürich. I implement a method to recognize objects using low level segmentations as a Matlab Toolbox. The method
follows the paper "Exploiting Low-level Image Segmentation for Object Recognition" from Volker Roth and Björn Ommer.
Here the reference to the paper:
Abstract. A method for exploiting the information in low-level image segmentations
for the purpose of object recognition is presented. The key idea is to use
a whole ensemble of segmentations per image, computed on different random
samples of image sites. Along the boundaries of those segmentations that are
stable under the sampling process we extract strings of vectors that contain local
image descriptors like shape, texture and intensities. Pairs of such strings are
aligned, and based on the alignment scores a mixture model is trained which divides
the segments in an image into fore- and background. Given such candidate
foreground segments, we show that it is possible to build a state-of-the-art object
recognition system that exhibits excellent performance on a standard benchmark
database. This result shows that despite the inherent problems of low-level image
segmentation in poor data conditions, segmentation can indeed be a valuable tool
for object recognition in real-world images.
segmentation_recognition.pdf
|