python opencv通過4坐標剪裁圖片

Posted on by

本文主要介紹瞭python opencv通過4坐標剪裁圖片，分享給大傢，具體如下：

效果展示,

在這裡插入圖片描述

裁剪出的單詞圖像(如下)

請添加圖片描述
請添加圖片描述
請添加圖片描述
請添加圖片描述
請添加圖片描述
請添加圖片描述
請添加圖片描述

這裡程序我是用在paddleOCR裡面,通過識別模型將識別出的圖根據程序提供的坐標(即四個頂點的值)進行摳圖的程序(上面的our和and就是扣的圖),並進行瞭封裝,相同格式的在這個基礎上改就是瞭

[[[368.0, 380.0], [437.0, 380.0], [437.0, 395.0], [368.0, 395.0]], [[496.0, 376.0], [539.0, 378.0], [538.0, 397.0], [495.0, 395.0]], [[466.0, 379.0], [498.0, 379.0], [498.0, 395.0], [466.0, 395.0]], [[438.0, 379
.0], [466.0, 379.0], [466.0, 395.0], [438.0, 395.0]], ]

從程序得到的數據格式大概長上面的樣子,由多個四個坐標一組的數據(如下)組成,即下面的[368.0, 380.0]為要裁剪圖片左上角坐標,[437.0, 380.0]為要裁剪圖片右上角坐標,[437.0, 395.0]為要裁剪圖片右下角坐標,[368.0, 395.0]為要裁剪圖片左下角坐標.

[[368.0, 380.0], [437.0, 380.0], [437.0, 395.0], [368.0, 395.0]]

而這裡剪裁圖片使用的是opencv(由於參數的原因沒有設置角度的話就隻能裁剪出平行的矩形,如果需要裁減出不與矩形圖片編譯平行的圖片的話,參考這個博客進行進一步的改進點擊進入)

裁剪部分主要是根據下面這一行代碼進行的,這裡要記住(我被這裡坑瞭一下午),
參數 tr[1]:左上角或右上角的縱坐標值
參數bl[1]:左下角或右下角的縱坐標值
參數tl[0]:左上角或左下角的橫坐標值
參數br[0]:右上角或右下角的橫坐標值

 crop = img[int(tr[1]):int(bl[1]), int(tl[0]):int(br[0]) ]

在這裡插入圖片描述

總的程序代碼如下

import numpy as np
import cv2


def np_list_int(tb):
    tb_2 = tb.tolist() #將np轉換為列表
    return tb_2


def shot(img, dt_boxes):#應用於predict_det.py中,通過dt_boxes中獲得的四個坐標點,裁剪出圖像
    dt_boxes = np_list_int(dt_boxes)
    boxes_len = len(dt_boxes)
    num = 0
    while 1:
        if (num < boxes_len):
            box = dt_boxes[num]
            tl = box[0]
            tr = box[1]
            br = box[2]
            bl = box[3]
            print("打印轉換成功數據num =" + str(num))
            print("tl:" + str(tl), "tr:" + str(tr), "br:" + str(br), "bl:" + str(bl))
            print(tr[1],bl[1], tl[0],br[0])


            crop = img[int(tr[1]):int(bl[1]), int(tl[0]):int(br[0]) ]

            
            # crop = img[27:45, 67:119] #測試
            # crop = img[380:395, 368:119]

            cv2.imwrite("K:/paddleOCR/PaddleOCR/screenshot/a/" + str(num) + ".jpg", crop)

            num = num + 1
        else:
            break


def shot1(img_path,tl, tr, br, bl,i):
    tl = np_list_int(tl)
    tr = np_list_int(tr)
    br = np_list_int(br)
    bl = np_list_int(bl)

    print("打印轉換成功數據")
    print("tl:"+str(tl),"tr:" + str(tr), "br:" + str(br), "bl:"+ str(bl))

    img = cv2.imread(img_path)
    crop = img[tr[1]:bl[1], tl[0]:br[0]]

    # crop = img[27:45, 67:119]

    cv2.imwrite("K:/paddleOCR/PaddleOCR/screenshot/shot/" + str(i) + ".jpg", crop)

# tl1 = np.array([67,27])
# tl2= np.array([119,27])
# tl3 = np.array([119,45])
# tl4 = np.array([67,45])
# shot("K:\paddleOCR\PaddleOCR\screenshot\zong.jpg",tl1, tl2 ,tl3 , tl4 , 0)

特別註意對np類型轉換成列表,以及crop = img[tr[1]:bl[1], tl[0]:br[0]]的中參數的位置,

實例

用瞭兩種方法保存圖片，opencv和Image，實踐證明opencv非常快

from PIL import Image
import os
import cv2
import time
import matplotlib.pyplot as plt
def label2picture(cropImg,framenum,tracker):
    pathnew ="E:\\img2\\"
    # cv2.imshow("image", cropImg)
    # cv2.waitKey(1)
    if (os.path.exists(pathnew + tracker)):
        cv2.imwrite(pathnew + tracker+'\\'+framenum + '.jpg', cropImg,[int(cv2.IMWRITE_JPEG_QUALITY), 100])
 
    else:
        os.makedirs(pathnew + tracker)
        cv2.imwrite(pathnew + tracker+'\\'+framenum + '.jpg', cropImg,[int(cv2.IMWRITE_JPEG_QUALITY), 100])
 
f = open("E:\\hypotheses.txt","r")
lines = f.readlines()
for line in lines:
    li  = line.split(',')
    print(li[0],li[1],li[2],li[3],li[4],li[5])
    filename = li[0]+'.jpg'
    img = cv2.imread("E:\\DeeCamp\\img1\\" + filename)
    crop_img = img[int(li[3][:-3]):(int(li[3][:-3]) + int(li[5][:-3])),
               int(li[2][:-3]):(int(li[2][:-3]) + int(li[4][:-3]))]
    # print(int(li[2][:-3]),int(li[3][:-3]),int(li[4][:-3]),int(li[5][:-3]))
    label2picture(crop_img, li[0], li[1])
# #
# x,y,w,h = 87,158,109,222
# img = cv2.imread("E:\\DeeCamp\\img1\\1606.jpg")
# # print(img.shape)
# crop = img[y:(h+y),x:(w+x)]
# cv2.imshow("image", crop)
# cv2.waitKey(0)
# img = Image.open("E:\\DeeCamp\\img1\\3217.jpg")
#
# cropImg = img.crop((x,y,x+w,y+h))
# cropImg.show()
    # img = Image.open("E:\\deep_sort-master\\MOT16\\train\\try1\\img1\\"+filename)
    # print(int(li[2][:-3]),(int(li[2][:-3])+int(li[4][:-3])), int(li[3][:-3]),(int(li[3][:-3])+int(li[5][:-3])))
 
    # #裁切圖片
    # # cropImg = img.crop(region)
    # # cropImg.show()
    # framenum ,tracker= li[0],li[1]
    # pathnew = 'E:\\DeeCamp\\deecamp項目\\deep_sort-master\\crop_picture\\'
    # if (os.path.exists(pathnew + tracker)):
    #     # 保存裁切後的圖片
    #     plt.imshow(cropImg)
    #     plt.savefig(pathnew + tracker+'\\'+framenum + '.jpg')
    # else:
    #     os.makedirs(pathnew + tracker)
    #     plt.imshow(cropImg)
    #     plt.savefig(pathnew + tracker+'\\'+framenum + '.jpg')

到此這篇關於python opencv通過4坐標剪裁圖片的文章就介紹到這瞭,更多相關opencv 剪裁圖片內容請搜索WalkonNet以前的文章或繼續瀏覽下面的相關文章希望大傢以後多多支持WalkonNet！

推薦閱讀：