Efficient and Scalable Image Segmentation Using Bag-of-Features and Stochastic Region Merging
This work presents an efficient and scalable texture segmentation
algorithm based on bag-of-features and stochastic region merging.
The image is partitioned into blocks and processed independently
to obtain regions, which are then merged to obtain the final
segmentation. Experimental results shows the proposed method
achieves an overall speed improvement of at least 4.5x and requires
6.5x less memory, while still improving segmentation accuracy
for large images.