Question

借助我之前在堆栈溢出时所做的其他问题，我已经实现了这段代码，该代码可以检测图像中的文档（在这种情况下为ID卡），然后根据需要执行其旋转和透视校正。 / p>

它做了所有事情，但是最终处理的图像质量下降/丧失了能量，并且字母看起来比原始字母更窄（我不知道），并且重要的是不要发生这种情况，因为我想使用图像来执行OCR。

我将提供一张图片用作测试，出于明显的原因，我画了一些信息，但检查了剩余的文字，看来很奇怪。

代码：

import cv2
import numpy as np

def order_corner_points(corners):
    # Separate corners into individual points
    # Index 0 - top-right
    #       1 - top-left
    #       2 - bottom-left
    #       3 - bottom-right
    corners = [(corner[0][0], corner[0][1]) for corner in corners]
    top_r, top_l, bottom_l, bottom_r = corners[0], corners[1], corners[2], corners[3]
    return (top_l, top_r, bottom_r, bottom_l)

def perspective_transform(image, corners):
    # Order points in clockwise order
    ordered_corners = order_corner_points(corners)
    top_l, top_r, bottom_r, bottom_l = ordered_corners

    # Determine width of new image which is the max distance between 
    # (bottom right and bottom left) or (top right and top left) x-coordinates
    width_A = np.sqrt(((bottom_r[0] - bottom_l[0]) ** 2) + ((bottom_r[1] - bottom_l[1]) ** 2))
    width_B = np.sqrt(((top_r[0] - top_l[0]) ** 2) + ((top_r[1] - top_l[1]) ** 2))
    width = max(int(width_A), int(width_B))

    # Determine height of new image which is the max distance between 
    # (top right and bottom right) or (top left and bottom left) y-coordinates
    height_A = np.sqrt(((top_r[0] - bottom_r[0]) ** 2) + ((top_r[1] - bottom_r[1]) ** 2))
    height_B = np.sqrt(((top_l[0] - bottom_l[0]) ** 2) + ((top_l[1] - bottom_l[1]) ** 2))
    height = max(int(height_A), int(height_B))

    # Construct new points to obtain top-down view of image in 
    # top_r, top_l, bottom_l, bottom_r order
    dimensions = np.array([[0, 0], [width - 1, 0], [width - 1, height - 1], 
                    [0, height - 1]], dtype = "float32")

    # Convert to Numpy format
    ordered_corners = np.array(ordered_corners, dtype="float32")

    # Find perspective transform matrix
    matrix = cv2.getPerspectiveTransform(ordered_corners, dimensions)

    # Return the transformed image
    return cv2.warpPerspective(image, matrix, (width, height), cv2.INTER_MAX)

def get_image_width_height(image):
    image_width = image.shape[1]  # current image's width
    image_height = image.shape[0]  # current image's height
    return image_width, image_height

def calculate_scaled_dimension(scale, image):
    image_width, image_height = get_image_width_height(image)
    ratio_of_new_with_to_old = scale / image_width
    dimension = (scale, int(image_height * ratio_of_new_with_to_old))
    return dimension

def scale_image(image, size):
    image_resized_scaled = cv2.resize(
        image,
        calculate_scaled_dimension(
            size,
            image
        ),
        interpolation=cv2.INTER_AREA
    )
    return image_resized_scaled

def rotate_image(image, angle):
    # Grab the dimensions of the image and then determine the center
    (h, w) = image.shape[:2]
    (cX, cY) = (w / 2, h / 2)

    # grab the rotation matrix (applying the negative of the
    # angle to rotate clockwise), then grab the sine and cosine
    # (i.e., the rotation components of the matrix)
    M = cv2.getRotationMatrix2D((cX, cY), -angle, 1.0)
    cos = np.abs(M[0, 0])
    sin = np.abs(M[0, 1])

    # Compute the new bounding dimensions of the image
    nW = int((h * sin) + (w * cos))
    nH = int((h * cos) + (w * sin))

    # Adjust the rotation matrix to take into account translation
    M[0, 2] += (nW / 2) - cX
    M[1, 2] += (nH / 2) - cY

    # Perform the actual rotation and return the image
    return cv2.warpAffine(image, M, (nW, nH))

image = cv2.imread('images/cc_test_img2.jpg')
original_image = image.copy()

image = scale_image(image, 500)

# convert the image to grayscale, blur it, and find edges in the image
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
gray = cv2.bilateralFilter(gray, 11, 17, 17)
edged = cv2.Canny(gray, 30, 200)

cv2.imshow('edged', edged)
cv2.waitKey()

cnts = cv2.findContours(edged.copy(), cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
cnts = sorted(cnts, key = cv2.contourArea, reverse = True)[:10]
screen_cnt = None

# loop over our contours
for c in cnts:
    # approximate the contour
    peri = cv2.arcLength(c, True)
    approx = cv2.approxPolyDP(c, 0.015 * peri, True)

    if len(approx) == 4:
        screen_cnt = approx
        transformed = perspective_transform(image, screen_cnt)
        break

# Draw ROI
cv2.drawContours(image, [screen_cnt], -1, (0, 255, 0), 1)

(h, w) = transformed.shape[:2]

if (h > w):
    rotated = rotate_image(transformed, 90)
else:
    rotated = transformed

cv2.imshow("image", original_image)
cv2.imshow("ROI", image)
cv2.imshow("transformed", transformed)
cv2.imshow("rotated", rotated)
cv2.waitKey(0)

要测试的图像

Python warpPerspective（）失去质量，图像失去正确的比率/潜力

0 个答案: