在 Tensorflow 对象检测 API 中将图像裁剪到边界框 [英] Crop image to bounding box in Tensorflow Object Detection API

问题描述

如何在 Tensorflow 中将图像裁剪到边界框?我正在使用 Python API.

来自文档，

tf.image.crop_to_bounding_box(image, offset_height, offset_width, target_height, target_width)

<块引用>

将图像裁剪到指定的边界框.

此操作从图像中切出矩形部分.返回图像的左上角在offset_height，offset_width in image，右下角在offset_height + target_height, offset_width + target_width.

我可以在标准化坐标中获得边界框的坐标，

 ymin = box[0,i,0]xmin = 盒子[0,i,1]ymax = 盒子[0,i,2]xmax = 盒子[0,i,3]

并将这些转换为绝对坐标，

 (xminn, xmaxx, yminn, ymaxx) = (xmin * im_width, xmax * im_width, ymin * im_height, ymax * im_height)

但是我不知道如何在 crop_to_bounding_box 函数中使用这些坐标.

解决方案

由于我们认为 x 是水平的，而 y 是垂直的，下面将裁剪指定框的图像.

cropped_image = tf.image.crop_to_bounding_box(image, yminn, xminn,ymaxx - yminn，xmaxx - xminn)

How can I crop an image to the bounding box in Tensorflow? I am using the Python API.

From the documentation,

tf.image.crop_to_bounding_box(image, offset_height, offset_width, target_height, target_width)

Crops an image to a specified bounding box.

This op cuts a rectangular part out of image. The top-left corner of the returned image is at offset_height, offset_width in image, and its lower-right corner is at offset_height + target_height, offset_width + target_width.

I can get the coordinates of a bounding box in normalized coordinates as,

    ymin = boxes[0,i,0]
    xmin = boxes[0,i,1]
    ymax = boxes[0,i,2]
    xmax = boxes[0,i,3]

and convert these to absolute coordinates,

    (xminn, xmaxx, yminn, ymaxx) = (xmin * im_width, xmax * im_width, ymin * im_height, ymax * im_height)

However I cant figure out how to use these coordinates in the crop_to_bounding_box function.

解决方案

Since we consider x as horizontal and y as vertical, following would crop the image with specified box.

cropped_image = tf.image.crop_to_bounding_box(image, yminn, xminn, 
                                       ymaxx - yminn, xmaxx - xminn)

这篇关于在 Tensorflow 对象检测 API 中将图像裁剪到边界框的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！