我會使用水平和垂直投影來首先將圖像分割成線,然後將每一行分割成更小的切片(例如單詞)。
首先將圖像轉換爲灰度,然後對其進行反轉,以便間隙包含零和任何文本/圖形都不爲零。
img = cv2.imread('article.png', cv2.IMREAD_COLOR)
img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
img_gray_inverted = 255 - img_gray
計算水平投影 - 意味着每行強度,使用cv2.reduce
,並將其平坦化,以線性陣列。
row_means = cv2.reduce(img_gray_inverted, 1, cv2.REDUCE_AVG, dtype=cv2.CV_32F).flatten()
現在找到所有連續間隙的行範圍。您可以使用this answer中提供的功能。
row_gaps = zero_runs(row_means)
最後計算出差距的中點,我們將用它來裁剪圖像。
row_cutpoints = (row_gaps[:,0] + row_gaps[:,1] - 1)/2
你最終是這樣的情況(差距是粉紅色,紅色的分割點):
下一步將處理每個標識線。
bounding_boxes = []
for n,(start,end) in enumerate(zip(row_cutpoints, row_cutpoints[1:])):
line = img[start:end]
line_gray_inverted = img_gray_inverted[start:end]
計算垂直投影(每列的平均強度),找到差距和切點。此外,計算間隙大小,以便過濾出單個字母之間的小間隙。
column_means = cv2.reduce(line_gray_inverted, 0, cv2.REDUCE_AVG, dtype=cv2.CV_32F).flatten()
column_gaps = zero_runs(column_means)
column_gap_sizes = column_gaps[:,1] - column_gaps[:,0]
column_cutpoints = (column_gaps[:,0] + column_gaps[:,1] - 1)/2
過濾分界點。
filtered_cutpoints = column_cutpoints[column_gap_sizes > 5]
並創建每個段的邊界框列表。
for xstart,xend in zip(filtered_cutpoints, filtered_cutpoints[1:]):
bounding_boxes.append(((xstart, start), (xend, end)))
現在你最終像這樣(再次差距是粉紅色,紅色的分割點):
現在你可以削減了圖像。我只是想象中的邊界框:
完整的腳本:
import cv2
import numpy as np
import matplotlib.pyplot as plt
from matplotlib import gridspec
def plot_horizontal_projection(file_name, img, projection):
fig = plt.figure(1, figsize=(12,16))
gs = gridspec.GridSpec(1, 2, width_ratios=[3,1])
ax = plt.subplot(gs[0])
im = ax.imshow(img, interpolation='nearest', aspect='auto')
ax.grid(which='major', alpha=0.5)
ax = plt.subplot(gs[1])
ax.plot(projection, np.arange(img.shape[0]), 'm')
ax.grid(which='major', alpha=0.5)
plt.xlim([0.0, 255.0])
plt.ylim([-0.5, img.shape[0] - 0.5])
ax.invert_yaxis()
fig.suptitle("FOO", fontsize=16)
gs.tight_layout(fig, rect=[0, 0.03, 1, 0.97])
fig.set_dpi(200)
fig.savefig(file_name, bbox_inches='tight', dpi=fig.dpi)
plt.clf()
def plot_vertical_projection(file_name, img, projection):
fig = plt.figure(2, figsize=(12, 4))
gs = gridspec.GridSpec(2, 1, height_ratios=[1,5])
ax = plt.subplot(gs[0])
im = ax.imshow(img, interpolation='nearest', aspect='auto')
ax.grid(which='major', alpha=0.5)
ax = plt.subplot(gs[1])
ax.plot(np.arange(img.shape[1]), projection, 'm')
ax.grid(which='major', alpha=0.5)
plt.xlim([-0.5, img.shape[1] - 0.5])
plt.ylim([0.0, 255.0])
fig.suptitle("FOO", fontsize=16)
gs.tight_layout(fig, rect=[0, 0.03, 1, 0.97])
fig.set_dpi(200)
fig.savefig(file_name, bbox_inches='tight', dpi=fig.dpi)
plt.clf()
def visualize_hp(file_name, img, row_means, row_cutpoints):
row_highlight = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
row_highlight[row_means == 0, :, :] = [255,191,191]
row_highlight[row_cutpoints, :, :] = [255,0,0]
plot_horizontal_projection(file_name, row_highlight, row_means)
def visualize_vp(file_name, img, column_means, column_cutpoints):
col_highlight = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
col_highlight[:, column_means == 0, :] = [255,191,191]
col_highlight[:, column_cutpoints, :] = [255,0,0]
plot_vertical_projection(file_name, col_highlight, column_means)
# From https://stackoverflow.com/a/24892274/3962537
def zero_runs(a):
# Create an array that is 1 where a is 0, and pad each end with an extra 0.
iszero = np.concatenate(([0], np.equal(a, 0).view(np.int8), [0]))
absdiff = np.abs(np.diff(iszero))
# Runs start and end where absdiff is 1.
ranges = np.where(absdiff == 1)[0].reshape(-1, 2)
return ranges
img = cv2.imread('article.png', cv2.IMREAD_COLOR)
img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
img_gray_inverted = 255 - img_gray
row_means = cv2.reduce(img_gray_inverted, 1, cv2.REDUCE_AVG, dtype=cv2.CV_32F).flatten()
row_gaps = zero_runs(row_means)
row_cutpoints = (row_gaps[:,0] + row_gaps[:,1] - 1)/2
visualize_hp("article_hp.png", img, row_means, row_cutpoints)
bounding_boxes = []
for n,(start,end) in enumerate(zip(row_cutpoints, row_cutpoints[1:])):
line = img[start:end]
line_gray_inverted = img_gray_inverted[start:end]
column_means = cv2.reduce(line_gray_inverted, 0, cv2.REDUCE_AVG, dtype=cv2.CV_32F).flatten()
column_gaps = zero_runs(column_means)
column_gap_sizes = column_gaps[:,1] - column_gaps[:,0]
column_cutpoints = (column_gaps[:,0] + column_gaps[:,1] - 1)/2
filtered_cutpoints = column_cutpoints[column_gap_sizes > 5]
for xstart,xend in zip(filtered_cutpoints, filtered_cutpoints[1:]):
bounding_boxes.append(((xstart, start), (xend, end)))
visualize_vp("article_vp_%02d.png" % n, line, column_means, filtered_cutpoints)
result = img.copy()
for bounding_box in bounding_boxes:
cv2.rectangle(result, bounding_box[0], bounding_box[1], (255,0,0), 2)
cv2.imwrite("article_boxes.png", result)
垂直和水平投影。首先將整個圖像分割成行,然後將每行分割成列。 –
謝謝丹。我明白了。你會用什麼工具進行垂直和水平投影?它可以自動化嗎?它可以檢測行和列嗎? – enzolito
你所做的是基本上計算每行的平均強度(例如,使用'cv2.reduce'),用它來確定行之間的白色間隙,找出間隙的中點,用它們作爲切點來生成一組圖像, –