如何繪制更大的邊界框和僅裁剪邊界框文本PythonOpencv

我正在使用 easyocr 來檢測影像中的文本。該方法給出了輸出邊界框。輸入影像如下所示

圖 1

圖 2

使用以下代碼獲得輸出影像。

但我想繪制一個包含所有文本的單個/更大的邊界框，并根據邊界框裁剪影像并洗掉剩余的不需要的區域或文本。

這是附加的代碼要求

pip 安裝 pytesseract

pip安裝easyocr

使用 python main.py -i image1.jpg 運行代碼

# USAGE
# python localize_text_tesseract.py --image apple_support.png
# python localize_text_tesseract.py --image apple_support.png --min-conf 50

# import the necessary packages
from pytesseract import Output
import pytesseract
import argparse
import cv2
from matplotlib import pyplot as plt
import numpy as np
import os
import easyocr
from PIL import ImageDraw, Image



def remove_lines(image):
    result = image.copy()
    gray = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
    thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV   cv2.THRESH_OTSU)[1]

    # Remove horizontal lines
    horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (40,1))
    remove_horizontal = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, horizontal_kernel, iterations=2)
    cnts = cv2.findContours(remove_horizontal, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
    cnts = cnts[0] if len(cnts) == 2 else cnts[1]
    for c in cnts:
        cv2.drawContours(result, [c], -1, (255,255,255), 5)


    # Remove vertical lines
    vertical_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1,40))
    remove_vertical = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, vertical_kernel, iterations=2)
    cnts = cv2.findContours(remove_vertical, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
    cnts = cnts[0] if len(cnts) == 2 else cnts[1]
    for c in cnts:
        cv2.drawContours(result, [c], -1, (255,255,255), 5)

    plt.imshow(result)
    plt.show()

    return result



# construct the argument parser and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", required=True,
    help="path to input image to be OCR'd")
ap.add_argument("-c", "--min-conf", type=int, default=0,
    help="mininum confidence value to filter weak text detection")
args = vars(ap.parse_args())


reader = easyocr.Reader(['ch_sim','en']) # need to run only once to load model into memory



# load the input image, convert it from BGR to RGB channel ordering,
# and use Tesseract to localize each area of text in the input image
image = cv2.imread(args["image"])
image = remove_lines(image)

results = reader.readtext(image)
#print('originalresult',results)

low_precision = []
for text in results:
    if text[2]<0.45: # precision here
        low_precision.append(text)
for i in low_precision:
    results.remove(i) # remove low precision
print(results)

#import pdb; pdb.set_trace()


image2 = Image.fromarray(image)

draw = ImageDraw.Draw(image2)
for i in range(0, len(results)):
    p0, p1, p2, p3 = results[i][0]
    draw.line([*p0, *p1, *p2, *p3, *p0], fill='red', width=1)

plt.imshow(np.asarray(image2))
plt.show()

uj5u.com熱心網友回復：

去除低精度結果后，您可以將所有有效點組合成單個二維陣列并用于cv2.boundingRect獲取邊界框。

代碼：

points = []
for result in results:
    points.extend(result[0])

rect = cv2.boundingRect(np.array(points))

x, y, w, h = rect

image2 = image.copy()
cv2.rectangle(image2, (x, y), (x   w, y   h), (255, 0, 0), 1)

plt.imshow(image2)
plt.show()

圖片：

并使用此行裁剪文本：

image_cropped = image[y:y h, x:x w]

或者如果需要更精確的裁剪：

mask = np.zeros_like(image)
# grayscale or color image
color = 255 if len(mask.shape) == 2 else mask.shape[2] * [255]
# create a mask
for result in results:
    cv2.fillConvexPoly(mask, np.array(result[0]), color)

# mask the text, and invert the mask to preserve white background
image_masked = cv2.bitwise_or(cv2.bitwise_and(image, mask), cv2.bitwise_not(mask))

image_cropped = image_masked[y:y h, x:x w]

標籤：Python opencv 图像处理 计算机视觉 opencv-contour

上一篇：使用SciKit和python檢測影像中的物件

下一篇：將影像視圖轉換為影像時質量會降低