Python+OpenCV：Feature Matching + Homography to find Objects

ゝ一纸荒年。 2022-12-24 00:45 98阅读 0赞

## Python+OpenCV：Feature Matching + Homography to find Objects ##

####################################################################################################
    # 图像特征匹配(Feature Matching with Homography)
    def lmc_cv_image_feature_matching_homography():
        """
            函数功能: 图像特征匹配(Feature Matching with FLANN)。
        """
    
        # 读取图像
        image1 = lmc_cv.imread('D:/99-Research/Python/Image/Brochure01.jpg', lmc_cv.IMREAD_GRAYSCALE)
        image2 = lmc_cv.imread('D:/99-Research/Python/Image/Brochure02.jpg', lmc_cv.IMREAD_GRAYSCALE)
    
        # Initiate SIFT detector
        min_match_count = 10
        sift = lmc_cv.SIFT_create()
    
        # find the keypoints and descriptors with SIFT
        keypoints1, descriptors1 = sift.detectAndCompute(image1, None)
        keypoints2, descriptors2 = sift.detectAndCompute(image2, None)
        flann_index_kdtree = 1
        index_params = dict(algorithm=flann_index_kdtree, trees=5)
        search_params = dict(checks=50)
        flann = lmc_cv.FlannBasedMatcher(index_params, search_params)
        matches = flann.knnMatch(descriptors1, descriptors2, k=2)
        # store all the good matches as per Lowe's ratio test.
        good = []
        for m, n in matches:
            if m.distance < 0.7 * n.distance:
                good.append(m)
    
        if len(good) > min_match_count:
            src_pts = np.float32([keypoints1[m.queryIdx].pt for m in good]).reshape(-1, 1, 2)
            dst_pts = np.float32([keypoints2[m.trainIdx].pt for m in good]).reshape(-1, 1, 2)
            m, mask = lmc_cv.findHomography(src_pts, dst_pts, lmc_cv.RANSAC, 5.0)
            matches_mask = mask.ravel().tolist()
            h, w = image1.shape
            pts = np.float32([[0, 0], [0, h - 1], [w - 1, h - 1], [w - 1, 0]]).reshape(-1, 1, 2)
            dst = lmc_cv.perspectiveTransform(pts, m)
            img2 = lmc_cv.polylines(image2, [np.int32(dst)], True, 255, 3, lmc_cv.LINE_AA)
        else:
            print("Not enough matches are found - {}/{}".format(len(good), MIN_MATCH_COUNT))
            matches_mask = None
    
        draw_params = dict(matchColor=(0, 255, 0),  # draw matches in green color
                           singlePointColor=None,
                           matchesMask=matches_mask,  # draw only inliers
                           flags=2)
        # cv.drawMatchesKnn expects list of lists as matches.
        result_image = lmc_cv.drawMatches(image1, keypoints1, image2, keypoints2, good, None, **draw_params)
    
        # 显示图像
        pyplot.figure('Feature Matching with FLANN and Homography')
        pyplot.subplot(1, 1, 1)
        pyplot.imshow(result_image, 'gray')
        pyplot.title('Feature Matching with FLANN and Homography')
        pyplot.xticks([])
        pyplot.yticks([])
    
        # 根据用户输入保存图像
        if ord("q") == (lmc_cv.waitKey(0) & 0xFF):
            # 销毁窗口
            pyplot.close('all')
        return

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2xpdWJpbmc4NjA5_size_16_color_FFFFFF_t_70][]

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2xpdWJpbmc4NjA5_size_16_color_FFFFFF_t_70]: /images/20221120/592a9fa901f84153a7158a4c40be183f.png