Question

Tensorflow的

tf.image.decode_jpeg()函数为scipy.misc.imread()图像提供了与jpg不同的数值结果。虽然图像看起来很相似，但像素值却不同。

import numpy as np
import scipy
import tensorflow as tf
import matplotlib.pyplot as plt
def minimal_example():
    def _bytes_feature(value):
        return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))

    tffilename = 'astronaut.tfrecords'
    writer = tf.python_io.TFRecordWriter(tffilename)
    #image_source = 'https://upload.wikimedia.org/wikipedia/commons/8/88/Astronaut-EVA.jpg'
    image_path = 'astronaut.jpg'
    image_file = open(image_path,'rb')
    image = image_file.read()
    image_scipy = scipy.misc.imread(image_path)
    example = tf.train.Example(features=tf.train.Features(feature={'image':_bytes_feature(image)}))
    writer.write(example.SerializeToString())
    writer.close()

    record_iterator = tf.python_io.tf_record_iterator(path=tffilename)
    example = tf.train.Example()
    example.ParseFromString(next(record_iterator))
    image = example.features.feature['image'].bytes_list.value[0]
    image_tf = tf.image.decode_jpeg(image).eval(session=tf.Session())
    fig = plt.figure()
    ax1 = fig.add_subplot(121)
    ax2 = fig.add_subplot(122)
    ax1.imshow(image_scipy)
    ax2.imshow(image_tf)
    print('Reconstruction Error', np.sum(np.abs(image_tf - image_scipy)))
    plt.show()

结果：

Reconstruction Error 3420883624

这是一个错误还是我做错了什么？

Answer 1

差异是由于Tensorflow使用的不准确但默认的默认离散余弦变换而引起的

根据Source code

// TensorFlow选择的jpeg解码默认值为IFAST，牺牲

//速度的图像质量。

flags_.dct_method = JDCT_IFAST;

为了获得准确的解码，可以设置属性dct_method = 'INTEGER_ACCURATE'，如下面的示例所示

def minimal_example():
    #image_source = 'https://upload.wikimedia.org/wikipedia/commons/8/88/Astronaut-EVA.jpg'
    image_path = 'astronaut.jpg'
    image_file = open(image_path,'rb')
    image_raw = image_file.read()
    image_scipy = scipy.misc.imread(image_path)
    image_tf = tf.image.decode_jpeg(image_raw).eval(session=tf.Session())
    image_tf_accurate = tf.image.decode_jpeg(image_raw,dct_method="INTEGER_ACCURATE").eval(session=tf.Session())
    print('Error For Default: ', np.sum(np.abs(image_tf - image_scipy)))
    print('Error For Accurate: ', np.sum(np.abs(image_tf_accurate - image_scipy)))
    #Error For Default:  3420883624
    #Error For Accurate:  0

Answer 2

The JPEG standard does not require bit-to-bit identical decoding。因此，不同的实现之间会有一些变化。

但是，它仍然需要

每个像素组件的最大差异为1比特。

因此两个输出不应该超过一个。正确？

print('max diff: ', np.max(np.abs(image_tf.astype(float) - image_scipy.astype(float))))
# max diff:  17.0

哎呀，至少有一个实现不符合标准...

为什么tensorflow解码jpeg图像与scipy imread不同？

2 个答案: