Question

我有以下使用hilbert变换进行的峰检测，该峰获取信号的包络，然后从其中检测出峰。

我想从峰1到峰2，从峰2到峰3，从峰3到峰4切掉那些峰，依此类推。

这是示例图片：

那是过程的结果

那是我的代码：

import cv2
import numpy as np
from PIL import Image
from scipy import signal
from math import factorial
from matplotlib import pyplot as plt
from scipy.signal import savgol_filter
import scipy.signal.signaltools as sigtool
from sklearn.preprocessing import normalize
from scipy.signal import find_peaks, peak_widths, find_peaks_cwt
from scipy.signal import argrelextrema


# ---------------------------------------Functions---------------------------------------------------#


def normalize(v):
    norm = np.linalg.norm(v)
    if norm == 0:
        return v
    return v / norm


'''
reduces the photo to a vector representing its pixel freuqeuncy at each column 
'''


def image_reduce(img):
    col_counts = cv2.reduce(img, 0, cv2.REDUCE_SUM, dtype=cv2.CV_32SC1)
    column = col_counts.flatten().tolist()
    # print("Column counts:\n\n", column)
    return column


def histogram_plot(convluted_word, peaks, fit):
    plt.plot(convluted_word)
    plt.plot(fit, 'r')
    plt.plot(peaks, fit[peaks], "x")
    plt.show()




# ---------------------------------------Main Code Flow---------------------------------------------------#
# ---------------------------an example on how to use this package----------------------------------------#

def slice_digits(image_name):
    img = cv2.imread(image_name, 0)

    column_frequency = image_reduce(cv2.bitwise_not(img))
    column_frequency = normalize(column_frequency)

    env = np.abs(sigtool.hilbert(column_frequency))

    square_sig = (env > 0.1)
    square_sig = square_sig.astype(float)
    square_sig = np.divide(square_sig, 15.0)
    square_sig = np.where((column_frequency > 0), 0.1, 0)

    peaks, _ = find_peaks(env > 0.1)
    plt.plot(env)
    plt.scatter(peaks, env[peaks],  s = 50, c = 'r')

    edges = np.nonzero(np.diff(square_sig))[0]
    plt.scatter(edges, env[edges], c = 'g')
    plt.show()
    all_slices = []
    for i in range(len(peaks) - 1):
        x0, x1 = peaks[i:i + 2]
        image_slice = img[x0:x1]
        # Now do something with the slice, e.g.
        cv2.imshow("slice",image_slice)

        all_slices.append(image_slice)

    # used for debugging
    #histogram_plot(column_frequency, peaks, square_sig)

    # segements the picture
    #listt, image_final = char_slicer(edges, img)
    plt.show()

    # display result
    #return image_final


if __name__ == '__main__':
    image = r"c:\ahmed\doc.png"
    res_image = slice_digits(image)

我想要的是这样的

desired

Answer 1

要从列表中peaks中的坐标中切出图像，可以使用：

all_slices = []
for i in range(len(peaks)-1):
    x0, x1 = peaks[i:i+2]
    image_slice = img[:, x0:x1]
    # Now do something with the slice, e.g. 
    all_slices.append(image_slice)

对于您的具体情况，完整列表为

import cv2
import numpy as np
import matplotlib.pyplot as plt
import scipy.signal.signaltools as sigtool
from scipy.signal import find_peaks, peak_widths, find_peaks_cwt


def image_reduce(img):
    col_counts = cv2.reduce(img, 0, cv2.REDUCE_SUM, dtype=cv2.CV_32SC1)
    column = col_counts.flatten().tolist()
    # print("Column counts:\n\n", column)
    return column


def normalize(v):
    norm = np.linalg.norm(v)
    if norm == 0:
        return v
    return v / norm


def slice_digits(image_name):
    img = cv2.imread(image_name, 0)

    column_frequency = image_reduce(cv2.bitwise_not(img))
    column_frequency = normalize(column_frequency)

    env = np.abs(sigtool.hilbert(column_frequency))

    square_sig = (env > 0.1)
    square_sig = square_sig.astype(float)
    square_sig = np.divide(square_sig, 15.0)
    square_sig = np.where((column_frequency > 0), 0.1, 0)

    peaks, _ = find_peaks(env > 0.1)
    plt.plot(env)
    plt.scatter(peaks, env[peaks],  s=50, c='r')

    edges = np.nonzero(np.diff(square_sig))[0]
    plt.scatter(edges, env[edges], c='g')

    all_slices = []
    for i in range(len(peaks) - 1):
        x0, x1 = peaks[i:i + 2]
        image_slice = img[:, x0:x1]

        print("coords:", x0, x1)
        # Now do something with the slice, e.g.
        all_slices.append(image_slice)
        plt.figure("Slice %d)" % i)
        plt.imshow(image_slice)

    plt.show()


if __name__ == '__main__':
    image = r"c:\ahmed\doc.png"
    res_image = slice_digits(image)

根据峰切片图像

1 个答案: