多尺度图片滑动窗口输出

简介

上一篇我们介绍了图片Gaussian pyramid（一、二）图片不压缩的情况下，重新resize到不同大小，这样做的目的是为这一节做准备，即利用滑动窗口圈住图片的文字信息内容等，例如车牌的获取。

'''
Created on 2017年8月19日

@author: XT
'''
# import the necessary packages
import helpers
import argparse
import time
import cv2


# load the image and define the window width and height
image = cv2.imread('./image/cat.jpg')  
(winW, winH) = (200, 128)

# loop over the image pyramid
for resized in helpers.pyramid(image, scale=1.5):
    # loop over the sliding window for each layer of the pyramid
    for (x, y, window) in helpers.sliding_window(resized, stepSize=32, windowSize=(winW, winH)):
        # if the window does not meet our desired window size, ignore it
        if window.shape[0] != winH or window.shape[1] != winW:
            continue

        # THIS IS WHERE YOU WOULD PROCESS YOUR WINDOW, SUCH AS APPLYING A
        # MACHINE LEARNING CLASSIFIER TO CLASSIFY THE CONTENTS OF THE
        # WINDOW

        # since we do not have a classifier, we'll just draw the window
        clone = resized.copy()
        cv2.rectangle(clone, (x, y), (x + winW, y + winH), (0, 255, 0), 2)
        cv2.imshow("Window", clone)
        cv2.waitKey(1)
#         time.sleep(0.025)

helpers:

'''
Created on 2017年8月19日

@author: XuTing
'''
# import the necessary packages
import imutils
from skimage.transform import pyramid_gaussian
import cv2

def pyramid(image, scale=1.5, minSize=(30, 30)):
    # yield the original image
    yield image

    # keep looping over the pyramid
    while True:
        # compute the new dimensions of the image and resize it
        w = int(image.shape[1] / scale)
        image = imutils.resize(image, width=w)

        # if the resized image does not meet the supplied minimum
        # size, then stop constructing the pyramid
        if image.shape[0] < minSize[1] or image.shape[1] < minSize[0]:
            break

        # yield the next image in the pyramid
        yield image

def sliding_window(image, stepSize, windowSize):
    # slide a window across the image
    for y in range(0, image.shape[0], stepSize):
        for x in range(0, image.shape[1], stepSize):
            # yield the current window
            yield (x, y, image[y:y + windowSize[1], x:x + windowSize[0]])

if __name__ == '__main__':
    image = cv2.imread('./image/cat2.jpg')  
    # METHOD #2: Resizing + Gaussian smoothing.
    for (i, resized) in enumerate(pyramid_gaussian(image, downscale=2)):
        # if the image is too small, break from the loop
        if resized.shape[0] < 30 or resized.shape[1] < 30:
            break
        # show the resized image
        WinName = "Layer {}".format(i + 1)
        cv2.imshow(WinName, resized)
        cv2.waitKey(10)
        resized = resized*255
        cv2.imwrite('./'+WinName+'.jpg',resized)

效果

参考

【1】Sliding Windows for Object Detection with Python and OpenCV - PyImageSearch
http://www.pyimagesearch.com/2015/03/23/sliding-windows-for-object-detection-with-python-and-opencv/?replytocom=322532
【2】My imutils package: A series of OpenCV convenience functions - PyImageSearch
http://www.pyimagesearch.com/2015/02/02/just-open-sourced-personal-imutils-package-series-opencv-convenience-functions/
【3】《SVM物体分类和定位检测》 - Hans的成长记录 - CSDN博客
http://blog.csdn.net/renhanchi/article/category/7007663