selective-search 0.1.0a0

Selective Search in Python

Selective Search

This is a full implementation of selective search in Python. The implementation is typically based on this paper[1]. It have three selective search modes according to various diversification strategies as in the paper.

Installation

Installing from PyPI is recommended :

$ pip install selective-search

It is also possible to install the latest version from Github source:

$ git clone https://github.com/ChenjieXu/selective_search.git
$ cd selective_search
$ python setup.py install

Quick Start

import skimage.io
from selective_search import selective_search

# Load image as NumPy array from image files
image = skimage.io.imread('path/to/image')

# Run selective search using single mode
boxes = selective_search(image, mode='single')

For detailed examples, refer this part of the repository.

Search Mode

Mode	Color Spaces	Similarity Measures	Starting Regions (k)	Number of Combinations
single	HSV	CTSF	100	1
fast	HSV, Lab	CTSF, TSF	50, 100	8
quality	HSV, Lab, rgI, H, I	CTSF, TSF, F, S	50, 100, 150, 300	80

References

[1] J. R. R. Uijlings et al., Selective Search for Object Recognition, IJCV, 2013