hog特徵提取-python實現

【轉載自 https://blog.csdn.net/ppp8300885/article/details/71078555】

所有代碼：

import cv2
import numpy as np
import math
import matplotlib.pyplot as plt


class Hog_descriptor():
    def __init__(self, img, cell_size=16, bin_size=8):
        self.img = img
        self.img = np.sqrt(img / np.max(img))
        self.img = img * 255
        self.cell_size = cell_size
        self.bin_size = bin_size
        self.angle_unit = 360 / self.bin_size
        assert type(self.bin_size) == int, "bin_size should be integer,"
        assert type(self.cell_size) == int, "cell_size should be integer,"
        assert type(self.angle_unit) == int, "bin_size should be divisible by 360"

    def extract(self):
        height, width = self.img.shape
        gradient_magnitude, gradient_angle = self.global_gradient()
        gradient_magnitude = abs(gradient_magnitude)
        cell_gradient_vector = np.zeros((height / self.cell_size, width / self.cell_size, self.bin_size))
        for i in range(cell_gradient_vector.shape[0]):
            for j in range(cell_gradient_vector.shape[1]):
                cell_magnitude = gradient_magnitude[i * self.cell_size:(i + 1) * self.cell_size,
                                 j * self.cell_size:(j + 1) * self.cell_size]
                cell_angle = gradient_angle[i * self.cell_size:(i + 1) * self.cell_size,
                             j * self.cell_size:(j + 1) * self.cell_size]
                cell_gradient_vector[i][j] = self.cell_gradient(cell_magnitude, cell_angle)

        hog_image = self.render_gradient(np.zeros([height, width]), cell_gradient_vector)
        hog_vector = []
        for i in range(cell_gradient_vector.shape[0] - 1):
            for j in range(cell_gradient_vector.shape[1] - 1):
                block_vector = []
                block_vector.extend(cell_gradient_vector[i][j])
                block_vector.extend(cell_gradient_vector[i][j + 1])
                block_vector.extend(cell_gradient_vector[i + 1][j])
                block_vector.extend(cell_gradient_vector[i + 1][j + 1])
                mag = lambda vector: math.sqrt(sum(i ** 2 for i in vector))
                magnitude = mag(block_vector)
                if magnitude != 0:
                    normalize = lambda block_vector, magnitude: [element / magnitude for element in block_vector]
                    block_vector = normalize(block_vector, magnitude)
                hog_vector.append(block_vector)
        return hog_vector, hog_image

    def global_gradient(self):
        gradient_values_x = cv2.Sobel(self.img, cv2.CV_64F, 1, 0, ksize=5)
        gradient_values_y = cv2.Sobel(self.img, cv2.CV_64F, 0, 1, ksize=5)
        gradient_magnitude = cv2.addWeighted(gradient_values_x, 0.5, gradient_values_y, 0.5, 0)
        gradient_angle = cv2.phase(gradient_values_x, gradient_values_y, angleInDegrees=True)
        return gradient_magnitude, gradient_angle

    def cell_gradient(self, cell_magnitude, cell_angle):
        orientation_centers = [0] * self.bin_size
        for i in range(cell_magnitude.shape[0]):
            for j in range(cell_magnitude.shape[1]):
                gradient_strength = cell_magnitude[i][j]
                gradient_angle = cell_angle[i][j]
                min_angle, max_angle, mod = self.get_closest_bins(gradient_angle)
                orientation_centers[min_angle] += (gradient_strength * (1 - (mod / self.angle_unit)))
                orientation_centers[max_angle] += (gradient_strength * (mod / self.angle_unit))
        return orientation_centers

    def get_closest_bins(self, gradient_angle):
        idx = int(gradient_angle / self.angle_unit)
        mod = gradient_angle % self.angle_unit
        return idx, (idx + 1) % self.bin_size, mod

    def render_gradient(self, image, cell_gradient):
        cell_width = self.cell_size / 2
        max_mag = np.array(cell_gradient).max()
        for x in range(cell_gradient.shape[0]):
            for y in range(cell_gradient.shape[1]):
                cell_grad = cell_gradient[x][y]
                cell_grad /= max_mag
                angle = 0
                angle_gap = self.angle_unit
                for magnitude in cell_grad:
                    angle_radian = math.radians(angle)
                    x1 = int(x * self.cell_size + magnitude * cell_width * math.cos(angle_radian))
                    y1 = int(y * self.cell_size + magnitude * cell_width * math.sin(angle_radian))
                    x2 = int(x * self.cell_size - magnitude * cell_width * math.cos(angle_radian))
                    y2 = int(y * self.cell_size - magnitude * cell_width * math.sin(angle_radian))
                    cv2.line(image, (y1, x1), (y2, x2), int(255 * math.sqrt(magnitude)))
                    angle += angle_gap
        return image

img = cv2.imread('person_037.png', cv2.IMREAD_GRAYSCALE)
hog = Hog_descriptor(img, cell_size=8, bin_size=8)
vector, image = hog.extract()
print np.array(vector).shape
plt.imshow(image, cmap=plt.cm.gray)
plt.show()

5. 結果分析
本文最終單幅圖像HOG特徵的求取平均時間爲1.8秒，相比最第一版本所需的5.4秒有個長足的改進。
相比初期的版本hog梯度特徵圖

 

可見最終版本中

 

可以更加有效的區分梯度顯示邊緣。這是由於對各個像素的梯度進行了全局歸一化，而且在描繪梯度方向時加入了梯度量級的非線性映射，使得梯度方向產生明顯的深淺和長度差別，更易於區分邊緣，凸顯明顯的梯度變化。

此外在輸入圖像時，採用Gamma校訂對輸入圖像進行顏色空間的標準化可以抑制噪聲，使得產生的邊緣更加明顯，清晰。

此外改變cell的大小和直方圖方向通道的效果以下：
cell_size = 10 即 16*16個像素

 

能夠看出增大cell的size獲得的特徵圖更加註重基本輪廓和邊緣，而忽略一些細節，某種程度上下降了噪聲。

當通道數目爲16個方向

 

梯度特徵圖像的細節變得更加明顯，方向更多。

6. 在人臉識別，物體檢測中的應用在提取完圖像的HOG特徵以後，能夠使用SVM進行分類訓練，能完成行人檢測等任務。