python 图片滑动窗口

最新推荐文章于 2024-04-26 18:22:04 发布

weixin_34294649

最新推荐文章于 2024-04-26 18:22:04 发布

阅读量2.4k

点赞数 2

文章标签： python 人工智能

原文链接：http://www.cnblogs.com/jyxbk/p/8548022.html

版权

METHOD #1: No smooth, just scaling.

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

METHOD #2: Resizing + Gaussian smoothing.

# import the necessary packages
import helpers
from skimage.transform import pyramid_gaussian
import argparse
import cv2

# construct the argument parser and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", '--image', required=True, help="Path to the image")
ap.add_argument("-s", "--scale", type=float, default=1.5, help="scale factor size") args = vars(ap.parse_args()) # load the image image = cv2.imread(args["image"]) # METHOD #1: No smooth, just scaling. # loop over the image pyramid for (i, resized) in enumerate(helpers.pyramid(image, scale=args["scale"])): # show the resized image cv2.imshow("Layer {}".format(i + 1), resized) cv2.waitKey(0) # close all windows cv2.destroyAllWindows() # 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 cv2.imshow("Layer {}".format(i + 1), resized) cv2.waitKey(0) #Run cmd python pyramid.py --image image/cat.jpg --scale 1.5

参考

【1】Image Pyramids with python and OpenCV - PyImageSearch
http://www.pyimagesearch.com/2015/03/16/image-pyramids-with-python-and-opencv/
【2】jrosebr1/imutils: A series of convenience functions to make basic image processing operations such as translation, rotation, resizing, skeletonization, and displaying Matplotlib images easier with opencv and Python.
https://github.com/jrosebr1/imutils
【3】Histogram of Oriented Gradients and Object Detection - PyImageSearch
http://www.pyimagesearch.com/2014/11/10/histogram-oriented-gradients-object-detection/
【4】Module: transform — skimage v0.14dev docs
http://scikit-image.org/docs/dev/api/skimage.transform.html#pyramid-gaussian

上边我们介绍了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。

# 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)