selective search（RCNN使用的ROI提取方法）

最新推荐文章于 2025-10-17 14:54:17 发布

原创最新推荐文章于 2025-10-17 14:54:17 发布 · 5.3k 阅读

4 ·

CC 4.0 BY-SA版权

深度学习同时被 2 个专栏收录

17 篇文章

订阅专栏

机器视觉

15 篇文章

订阅专栏

本文介绍如何使用SelectiveSearch库进行图像分割，并提供了一个具体的Python实现案例。通过加载图像、执行SelectiveSearch算法来生成候选区域，最后在原始图像上绘制这些候选区域。

安装selective search

$ pip install selectivesearch

读取并显示图片

import matplotlib.pyplot as plt
import matplotlib.patches as mpatches
import selectivesearch
from skimage import io


# img = io.imread('/home/lxq/testImage/00000.ppm')
# io.imshow(img)
# plt.show()

def main():

    # loading  image
    img = io.imread('/home/lxq/testImage/00000.ppm')

    # perform selective search
    img_lbl, regions = selectivesearch.selective_search(
        img, scale=500, sigma=0.9, min_size=10)

    candidates = set()
    for r in regions:
        # excluding same rectangle (with different segments)
        if r['rect'] in candidates:
            continue
        # excluding regions smaller than 2000 pixels
        if r['size'] < 2000:
            continue
        # distorted rects
        x, y, w, h = r['rect']
        if w / h > 1.2 or h / w > 1.2:
            continue
        candidates.add(r['rect'])

    # draw rectangles on the original image
    fig, ax = plt.subplots(ncols=1, nrows=1, figsize=(6, 6))
    ax.imshow(img)
    for x, y, w, h in candidates:
        print x, y, w, h
        rect = mpatches.Rectangle(
            (x, y), w, h, fill=False, edgecolor='red', linewidth=1)
        ax.add_patch(rect)

    plt.show()

if __name__ == "__main__":
     main()

输出结果