机器学习 - 图像识别

图像识别

OpenCV基础

OpenCV是一个开源的计算机视觉库。提供了很多图像处理常用的工具。

案例：

import numpy as np
import cv2 as cv
# 读取图片并显示
original = cv.imread('../data/forest.jpg')
cv.imshow('Original', original)
# 显示图片某个颜色通道的图像
blue = np.zeros_like(original)
blue[:, :, 0] = original[:, :, 0]  # 0 - 蓝色通道
cv.imshow('Blue', blue)
green = np.zeros_like(original)
green[:, :, 1] = original[:, :, 1]  # 1 - 绿色通道
cv.imshow('Green', green)
red = np.zeros_like(original)
red[:, :, 2] = original[:, :, 2]  # 2 - 红色通道
cv.imshow('Red', red)
# 图像裁剪
h, w = original.shape[:2]
l, t = int(w / 4), int(h / 4)
r, b = int(w * 3 / 4), int(h * 3 / 4)
cropped = original[t:b, l:r]
cv.imshow('Cropped', cropped)
#图像缩放 interpolation=线型插值
scaled1 = cv.resize(original, (int(w / 4), int(h / 4)),
    interpolation=cv.INTER_LINEAR)
cv.imshow('Scaled1', scaled1)
scaled2 = cv.resize(
    scaled1, None, fx=4, fy=4,
    interpolation=cv.INTER_LINEAR)
cv.imshow('Scaled2', scaled2)
cv.waitKey()
# 图像文件保存
cv.imwrite('../../data/blue.jpg', blue)
cv.imwrite('../../data/green.jpg', green)
cv.imwrite('../../data/red.jpg', red)
cv.imwrite('../../data/cropped.jpg', cropped)
cv.imwrite('../../data/scaled1.jpg', scaled1)
cv.imwrite('../../data/scaled2.jpg', scaled2)

边缘检测

物体的边缘检测是物体识别常用的手段。边缘检测常用亮度梯度方法。通过识别亮度梯度变化最大的像素点从而检测出物体的边缘。

常用边缘检测算法相关API：

# 索贝尔边缘识别
# cv.CV_64F：卷积运算使用数据类型为64位浮点型（保证微分的精度）
# 1：水平方向索贝尔偏微分
# 0：垂直方向索贝尔偏微分
# ksize：卷积核为5*5的方阵
cv.Sobel(original, cv.CV_64F, 1, 0, ksize=5)
# 拉普拉斯边缘识别
cv.Laplacian(original, cv.CV_64F)
# Canny边缘识别
# 50:水平方向阈值  240:垂直方向阈值
cv.Canny(original, 50, 240)

案例：

import cv2 as cv

original = cv.imread( '../data/chair.jpg', cv.IMREAD_GRAYSCALE)
cv.imshow('Original', original)
hsobel = cv.Sobel(original, cv.CV_64F, 1, 0, ksize=5)
cv.imshow('H-Sobel', hsobel)
vsobel = cv.Sobel(original, cv.CV_64F, 0, 1, ksize=5)
cv.imshow('V-Sobel', vsobel)
sobel = cv.Sobel(original, cv.CV_64F, 1, 1, ksize=5)
cv.imshow('Sobel', sobel)
laplacian = cv.Laplacian(original, cv.CV_64F)
cv.imshow('Laplacian', laplacian)
canny = cv.Canny(original, 50, 240)
cv.imshow('Canny', canny)
cv.waitKey()

亮度提升

OpenCV提供了直方图均衡化的方式实现亮度提升，更有利于边缘识别与物体识别模型的训练。

OpenCV直方图均衡化相关API：

# 彩色图转为灰度图
gray = cv.cvtColor(original, cv.COLOR_BGR2GRAY)
# 直方图均衡化
equalized_gray = cv.equalizeHist(gray)

案例：

import cv2 as cv

original = cv.imread('../../data/sunrise.jpg')
cv.imshow('Original', original)
gray = cv.cvtColor(original, cv.COLOR_BGR2GRAY)
cv.imshow('Gray', gray)
equalized_gray = cv.equalizeHist(gray)
cv.imshow('Equalized Gray', equalized_gray)
# YUV：亮度，色度，饱和度
yuv = cv.cvtColor(original, cv.COLOR_BGR2YUV)
yuv[..., 0] = cv.equalizeHist(yuv[..., 0])
equalized_color = cv.cvtColor(yuv, cv.COLOR_YUV2BGR)
cv.imshow('Equalized Color', equalized_color)
cv.waitKey()

角点检测

平直棱线的交汇点（颜色梯度方向改变的像素点的位置）

OpenCV提供的角点检测相关API：

gray = cv.cvtColor(original, cv.COLOR_BGR2GRAY)
# Harris角点检测器
# 边缘水平方向、垂直方向颜色值改变超过阈值7、5时即为边缘
# 边缘线方向改变超过阈值0.04弧度即为一个角点。
corners = cv.cornerHarris(gray, 7, 5, 0.04)

案例：

import cv2 as cv

original = cv.imread('../data/box.png')
cv.imshow('Original', original)
gray = cv.cvtColor(original, cv.COLOR_BGR2GRAY)
cv.imshow('Gray', gray)
corners = cv.cornerHarris(gray, 7, 5, 0.04)
mixture = original.copy()
mixture[corners > corners.max() * 0.01] = [0, 0, 255]
cv.imshow('Corner', mixture)
cv.waitKey()

特征点检测

常用特征点检测有：STAR特征点检测 / SIFT特征点检测

特征点检测结合了边缘检测与角点检测从而识别出图形的特征点。

STAR特征点检测相关API如下：

import cv2 as cv
# 创建STAR特征点检测器
star = cv.xfeatures2d.StarDetector_create()
# 检测出gray图像所有的特征点
keypoints = star.detect(gray)
# drawKeypoints方法可以把所有的特征点绘制在mixture图像中
cv.drawKeypoints(original, keypoints, mixture,
    			 flags=cv.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)
cv.imshow('Mixture', mixture)

案例：

import cv2 as cv
original = cv.imread('../data/table.jpg')
cv.imshow('Original', original)
gray = cv.cvtColor(original, cv.COLOR_BGR2GRAY)
cv.imshow('Gray', gray)
star = cv.xfeatures2d.StarDetector_create()
keypoints = star.detect(gray)
mixture = original.copy()
cv.drawKeypoints(
    original, keypoints, mixture,
    flags=cv.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)
cv.imshow('Mixture', mixture)
cv.waitKey()

SIFT特征点检测相关API：

import cv2 as cv

# 创建SIFT特征点检测器
sift = cv.xfeatures2d.SIFT_create()
keypoints = sift.detect(gray)

案例：

import cv2 as cv

original = cv.imread('../data/table.jpg')
cv.imshow('Original', original)
gray = cv.cvtColor(original, cv.COLOR_BGR2GRAY)
cv.imshow('Gray', gray)
sift = cv.xfeatures2d.SIFT_create()
keypoints = sift.detect(gray)
mixture = original.copy()
cv.drawKeypoints(original, keypoints, mixture,
    flags=cv.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)
cv.imshow('Mixture', mixture)
cv.waitKey()

特征值矩阵

图像特征值矩阵（描述）记录了图像的特征点以及每个特征点的梯度信息，相似图像的特征值矩阵也相似。这样只要有足够多的样本，就可以基于隐马尔科夫模型进行图像内容的识别。

特征值矩阵相关API：

sift = cv.xfeatures2d.SIFT_create()
keypoints = sift.detect(gray)
_, desc = sift.compute(gray, keypoints)

案例：

import cv2 as cv

import matplotlib.pyplot as mp
original = cv.imread('../data/table.jpg')
cv.imshow('Original', original)
gray = cv.cvtColor(original, cv.COLOR_BGR2GRAY)
cv.imshow('Gray', gray)
sift = cv.xfeatures2d.SIFT_create()
keypoints = sift.detect(gray)
_, desc = sift.compute(gray, keypoints)
print(desc.shape)
mp.matshow(desc, cmap='jet', fignum='Description')
mp.title('Description', fontsize=20)
mp.xlabel('Feature', fontsize=14)
mp.ylabel('Sample', fontsize=14)
mp.tick_params(which='both', top=False, labeltop=False, labelbottom=True, labelsize=10)
mp.show()

物体识别

import os
import numpy as np
import cv2 as cv
import hmmlearn.hmm as hl

def search_files(directory):
    directory = os.path.normpath(directory)

    objects = {}
    for curdir, subdirs, files in os.walk(directory):
        for file in files:
            if(file.endswith('.jpg')):
                label = curdir.split(os.path.sep)[-1]
                if label not in objects:
                    objects[label] = []
                path = os.path.join(curdir, file)
                objects[label].append(path)
    return objects
	
#加载训练集样本数据，训练模型，模型存储
train_objects = search_files('../data/objects/training')
train_x, train_y = [], []
for label, filenames in train_objects.items():
    descs = np.array([])
    for filename in filenames:
        image = cv.imread(filename)
        gray = cv.cvtColor(image, cv.COLOR_BGR2GRAY)
        #范围缩放，使特征描述矩阵样本数量一致
        h, w = gray.shape[:2]
        f = 200 / min(h, w)
        gray = cv.resize(gray, None, fx=f, fy=f)
        sift = cv.xfeatures2d.SIFT_create()
        keypoints = sift.detect(gray)
        _, desc = sift.compute(gray, keypoints)
        if len(descs) == 0:
            descs = desc
        else:
            descs = np.append(descs, desc, axis=0)
    train_x.append(descs)
    train_y.append(label)
models = {}
for descs, label in zip(train_x, train_y):
    model = hl.GaussianHMM(n_components=4, covariance_type='diag', n_iter=100)
    models[label] = model.fit(descs)


#测试模型
test_objects = search_files('../data/objects/testing')
test_x, test_y = [], []
for label, filenames in test_objects.items():
    descs = np.array([])
    for filename in filenames:
        image = cv.imread(filename)
        gray = cv.cvtColor(image, cv.COLOR_BGR2GRAY)
        sift = cv.xfeatures2d.SIFT_create()
        keypoints = sift.detect(gray)
        _, desc = sift.compute(gray, keypoints)
        if len(descs) == 0:
            descs = desc
        else:
            descs = np.append(descs, desc, axis=0)
    test_x.append(descs)
    test_y.append(label)

# 遍历所有测试样本  使用model匹配测试样本查看每个模型的匹配分数
for descs, test_label in zip(test_x, test_y):
    for pred_label, model in models.items():
        score = model.score(descs)
        print(test_label, '->', pred_label, score)