python

关注公众号 jb51net

关闭
首页 > 脚本专栏 > python > Python图像获取patch

Python实现随机从图像中获取多个patch

作者:拜阳

经常有一些图像任务需要从一张大图中截取固定大小的patch来进行训练。本文就来和大家聊聊如何用Python实现随机从图像中获取多个patch,感兴趣的可以了解一下

经常有一些图像任务需要从一张大图中截取固定大小的patch来进行训练。这里面常常存在下面几个问题:

基于以上问题,我们可以使用下面的策略从图像中获取位置随机的多个patch:

下面是实现代码和例子:

注意下面代码只是获取了patch的bounding box,并没有把patch截取出来。

# -*- coding: utf-8 -*-
import cv2
import numpy as np


def get_random_patch_bboxes(image, bbox_size, stride, jitter, roi_bbox=None):
    """
    Generate random patch bounding boxes for a image around ROI region

    Parameters
    ----------
    image: image data read by opencv, shape is [H, W, C]
    bbox_size: size of patch bbox, one digit or a list/tuple containing two
        digits, defined by (width, height)
    stride: stride between adjacent bboxes (before jitter), one digit or a
        list/tuple containing two digits, defined by (x, y)
    jitter: jitter size for evenly distributed bboxes, one digit or a
        list/tuple containing two digits, defined by (x, y)
    roi_bbox: roi region, defined by [xmin, ymin, xmax, ymax], default is whole
        image region

    Returns
    -------
    patch_bboxes: randomly distributed patch bounding boxes, n x 4 numpy array.
        Each bounding box is defined by [xmin, ymin, xmax, ymax]
    """
    height, width = image.shape[:2]
    bbox_size = _process_geometry_param(bbox_size, min_value=1)
    stride = _process_geometry_param(stride, min_value=1)
    jitter = _process_geometry_param(jitter, min_value=0)

    if bbox_size[0] > width or bbox_size[1] > height:
        raise ValueError('box_size must be <= image size')

    if roi_bbox is None:
        roi_bbox = [0, 0, width, height]

    # tl is for top-left, br is for bottom-right
    tl_x, tl_y = _get_top_left_points(roi_bbox, bbox_size, stride, jitter)
    br_x = tl_x + bbox_size[0]
    br_y = tl_y + bbox_size[1]

    # shrink bottom-right points to avoid exceeding image border
    br_x[br_x > width] = width
    br_y[br_y > height] = height
    # shrink top-left points to avoid exceeding image border
    tl_x = br_x - bbox_size[0]
    tl_y = br_y - bbox_size[1]
    tl_x[tl_x < 0] = 0
    tl_y[tl_y < 0] = 0
    # compute bottom-right points again
    br_x = tl_x + bbox_size[0]
    br_y = tl_y + bbox_size[1]

    patch_bboxes = np.concatenate((tl_x, tl_y, br_x, br_y), axis=1)
    return patch_bboxes


def _process_geometry_param(param, min_value):
    """
    Process and check param, which must be one digit or a list/tuple containing
    two digits, and its value must be >= min_value

    Parameters
    ----------
    param: parameter to be processed
    min_value: min value for param

    Returns
    -------
    param: param after processing
    """
    if isinstance(param, (int, float)) or \
            isinstance(param, np.ndarray) and param.size == 1:
        param = int(np.round(param))
        param = [param, param]
    else:
        if len(param) != 2:
            raise ValueError('param must be one digit or two digits')
        param = [int(np.round(param[0])), int(np.round(param[1]))]

    # check data range using min_value
    if not (param[0] >= min_value and param[1] >= min_value):
        raise ValueError('param must be >= min_value (%d)' % min_value)
    return param


def _get_top_left_points(roi_bbox, bbox_size, stride, jitter):
    """
    Generate top-left points for bounding boxes

    Parameters
    ----------
    roi_bbox: roi region, defined by [xmin, ymin, xmax, ymax]
    bbox_size: size of patch bbox, a list/tuple containing two digits, defined
        by (width, height)
    stride: stride between adjacent bboxes (before jitter), a list/tuple
        containing two digits, defined by (x, y)
    jitter: jitter size for evenly distributed bboxes, a list/tuple containing
        two digits, defined by (x, y)

    Returns
    -------
    tl_x: x coordinates of top-left points, n x 1 numpy array
    tl_y: y coordinates of top-left points, n x 1 numpy array
    """
    xmin, ymin, xmax, ymax = roi_bbox
    roi_width = xmax - xmin
    roi_height = ymax - ymin

    # get the offset between the first top-left point of patch box and the
    # top-left point of roi_bbox
    offset_x = np.arange(0, roi_width, stride[0])[-1] + bbox_size[0]
    offset_y = np.arange(0, roi_height, stride[1])[-1] + bbox_size[1]
    offset_x = (offset_x - roi_width) // 2
    offset_y = (offset_y - roi_height) // 2

    # get the coordinates of all top-left points
    tl_x = np.arange(xmin, xmax, stride[0]) - offset_x
    tl_y = np.arange(ymin, ymax, stride[1]) - offset_y
    tl_x, tl_y = np.meshgrid(tl_x, tl_y)
    tl_x = np.reshape(tl_x, [-1, 1])
    tl_y = np.reshape(tl_y, [-1, 1])

    # jitter the coordinates of all top-left points
    tl_x += np.random.randint(-jitter[0], jitter[0] + 1, size=tl_x.shape)
    tl_y += np.random.randint(-jitter[1], jitter[1] + 1, size=tl_y.shape)
    return tl_x, tl_y


if __name__ == '__main__':
    image = cv2.imread('1.bmp')
    patch_bboxes = get_random_patch_bboxes(
        image,
        bbox_size=[64, 96],
        stride=[128, 128],
        jitter=[32, 32],
        roi_bbox=[500, 200, 1500, 800])

    colors = [
        (255, 0, 0),
        (0, 255, 0),
        (0, 0, 255),
        (255, 255, 0),
        (255, 0, 255),
        (0, 255, 255)]
    color_idx = 0

    for bbox in patch_bboxes:
        color_idx = color_idx % 6
        pt1 = (bbox[0], bbox[1])
        pt2 = (bbox[2], bbox[3])
        cv2.rectangle(image, pt1, pt2, color=colors[color_idx], thickness=2)
        color_idx += 1

    cv2.namedWindow('image', 0)
    cv2.imshow('image', image)
    cv2.waitKey(0)
    cv2.destroyAllWindows()
    cv2.imwrite('image.png', image)

在实际应用中可以进一步增加一些简单的功能:

1.根据位置增加一些过滤功能。比如说太靠近边缘的给剔除掉,有些算法可能有比较严重的边缘效应,所以此时我们可能不太想要边缘的数据加入训练

2.也可以根据某些简单的算法策略进行过滤。比如在超分辨率这样的任务中,我们可能一般不太关心面积非常大的平坦区域,比如纯色墙面,大片天空等,此时可以使用方差进行过滤

3.设置最多保留数目。有时候原图像的大小可能有很大差异,此时利用上述方法得到的patch数量也就随之有很大的差异,然而为了保持训练数据的均衡性,我们可以设置最多保留数目,为了确保覆盖程度,一般需要在截取之前对patch进行shuffle,或者计算stride

以上就是Python实现随机从图像中获取多个patch的详细内容,更多关于Python图像获取patch的资料请关注脚本之家其它相关文章!

您可能感兴趣的文章:
阅读全文