HOG图像特征提取及其SK-imgae实现

2020-03-02  本文已影响0人  风风荷举

前言

hog(image, orientations=9, pixels_per_cell=(8, 8), cells_per_block=(3, 3),
        block_norm='L2-Hys', visualize=False, transform_sqrt=False,
        feature_vector=True, multichannel=None)

图像标准化

在这一步，我们的主要目的是为了预处理图像，减少光照等带来的影响。
f(I) = I^{ \gamma }

if transform_sqrt:
    image = np.sqrt(image)

图像平滑

梯度计算

G_{y}(x, y)=I(x, y+1)-I(x, y-1)

横纵梯度表示 
    if image.dtype.kind == 'u':
        # convert uint image to float
        # to avoid problems with subtracting unsigned numbers
        image = image.astype('float')

    if multichannel:
        g_row_by_ch = np.empty_like(image, dtype=np.double)
        g_col_by_ch = np.empty_like(image, dtype=np.double)
        g_magn = np.empty_like(image, dtype=np.double)

        for idx_ch in range(image.shape[2]):
            g_row_by_ch[:, :, idx_ch], g_col_by_ch[:, :, idx_ch] = \
                _hog_channel_gradient(image[:, :, idx_ch])
            g_magn[:, :, idx_ch] = np.hypot(g_row_by_ch[:, :, idx_ch],
                                            g_col_by_ch[:, :, idx_ch])

        # For each pixel select the channel with the highest gradient magnitude
        idcs_max = g_magn.argmax(axis=2)
        rr, cc = np.meshgrid(np.arange(image.shape[0]),
                             np.arange(image.shape[1]),
                             indexing='ij',
                             sparse=True)
        g_row = g_row_by_ch[rr, cc, idcs_max]
        g_col = g_col_by_ch[rr, cc, idcs_max]
    else:
        g_row, g_col = _hog_channel_gradient(image)

def _hog_channel_gradient(channel):
    """Compute unnormalized gradient image along `row` and `col` axes.

    Parameters
    ----------
    channel : (M, N) ndarray
        Grayscale image or one of image channel.

    Returns
    -------
    g_row, g_col : channel gradient along `row` and `col` axes correspondingly.
    """
    g_row = np.empty(channel.shape, dtype=np.double)
    g_row[0, :] = 0
    g_row[-1, :] = 0
    g_row[1:-1, :] = channel[2:, :] - channel[:-2, :]
    g_col = np.empty(channel.shape, dtype=np.double)
    g_col[:, 0] = 0
    g_col[:, -1] = 0
    g_col[:, 1:-1] = channel[:, 2:] - channel[:, :-2]

    return g_row, g_col

We evaluated two variants of the C-HOG geometry, ones with a single circular central cell (similar to the GLOH feature), and ones whose cen-tralcellis divided into angular sectors as in shape contexts.We present results only for the circular-centrevariants, as these have fewer spatial cells than the divided centre ones and give the same per-formance in practice.

orientation选取为8举例 C-HOG示意图，ppc=cpb=(4, 4) 
s_row, s_col = image.shape[:2]
    c_row, c_col = pixels_per_cell
    b_row, b_col = cells_per_block

    n_cells_row = int(s_row // c_row)  # number of cells along row-axis
    n_cells_col = int(s_col // c_col)  # number of cells along col-axis

    # compute orientations integral images
    orientation_histogram = np.zeros((n_cells_row, n_cells_col, orientations))

    _hoghistogram.hog_histograms(g_col, g_row, c_col, c_row, s_col, s_row,
                                 n_cells_col, n_cells_row,
                                 orientations, orientation_histogram)

    # now compute the histogram for each cell
    hog_image = None

    if visualize:
        from .. import draw

        radius = min(c_row, c_col) // 2 - 1
        orientations_arr = np.arange(orientations)
        # set dr_arr, dc_arr to correspond to midpoints of orientation bins
        orientation_bin_midpoints = (
            np.pi * (orientations_arr + .5) / orientations)
        dr_arr = radius * np.sin(orientation_bin_midpoints)
        dc_arr = radius * np.cos(orientation_bin_midpoints)
        hog_image = np.zeros((s_row, s_col), dtype=float)
        for r in range(n_cells_row):
            for c in range(n_cells_col):
                for o, dr, dc in zip(orientations_arr, dr_arr, dc_arr):
                    centre = tuple([r * c_row + c_row // 2,
                                    c * c_col + c_col // 2])
                    rr, cc = draw.line(int(centre[0] - dc),
                                       int(centre[1] + dr),
                                       int(centre[0] + dc),
                                       int(centre[1] - dr))
                    hog_image[rr, cc] += orientation_histogram[r, c, o]

归一化

def _hog_normalize_block(block, method, eps=1e-5):
    if method == 'L1':
        out = block / (np.sum(np.abs(block)) + eps)
    elif method == 'L1-sqrt':
        out = np.sqrt(block / (np.sum(np.abs(block)) + eps))
    elif method == 'L2':
        out = block / np.sqrt(np.sum(block ** 2) + eps ** 2)
    elif method == 'L2-Hys':
        out = block / np.sqrt(np.sum(block ** 2) + eps ** 2)
        out = np.minimum(out, 0.2)
        out = out / np.sqrt(np.sum(out ** 2) + eps ** 2)
    else:
        raise ValueError('Selected block normalization method is invalid.')

    return out

    n_blocks_row = (n_cells_row - b_row) + 1
    n_blocks_col = (n_cells_col - b_col) + 1
    normalized_blocks = np.zeros((n_blocks_row, n_blocks_col,
                                  b_row, b_col, orientations))

    for r in range(n_blocks_row):
        for c in range(n_blocks_col):
            block = orientation_histogram[r:r + b_row, c:c + b_col, :]
            normalized_blocks[r, c, :] = \
                _hog_normalize_block(block, method=block_norm)

参考文章

上一篇 下一篇

猜你喜欢

热点阅读