圖片去摩爾紋簡(jiǎn)述實(shí)現(xiàn)python代碼示例

更新時(shí)間：2023年02月24日 16:22:23 作者：愉快的李長(zhǎng)安

這篇文章主要為大家介紹了圖片去摩爾紋簡(jiǎn)述實(shí)現(xiàn)的python代碼示例，有需要的朋友可以借鑒參考下，希望能夠有所幫助，祝大家多多進(jìn)步，早日升職加薪

1、前言

當(dāng)感光元件像素的空間頻率與影像中條紋的空間頻率接近時(shí)，可能產(chǎn)生一種新的波浪形的干擾圖案，即所謂的摩爾紋。傳感器的網(wǎng)格狀紋理構(gòu)成了一個(gè)這樣的圖案。當(dāng)圖案中的細(xì)條狀結(jié)構(gòu)與傳感器的結(jié)構(gòu)以小角度交叉時(shí)，這種效應(yīng)也會(huì)在圖像中產(chǎn)生明顯的干擾。這種現(xiàn)象在一些細(xì)密紋理情況下，比如時(shí)尚攝影中的布料上，非常普遍。這種摩爾紋可能通過(guò)亮度也可能通過(guò)顏色來(lái)展現(xiàn)。但是在這里，僅針對(duì)在翻拍過(guò)程中產(chǎn)生的圖像摩爾紋進(jìn)行處理。

翻拍即從計(jì)算機(jī)屏幕上捕獲圖片，或?qū)χ聊慌臄z圖片；該方式會(huì)在圖片上產(chǎn)生摩爾紋現(xiàn)象

論文主要處理思路

對(duì)原圖作Haar變換得到四個(gè)下采樣特征圖（原圖下二采樣cA、Horizontal橫向高頻cH、Vertical縱向高頻cV、Diagonal斜向高頻cD）
然后分別利用四個(gè)獨(dú)立的CNN對(duì)四個(gè)下采樣特征圖卷積池化，提取特征信息
原文隨后對(duì)三個(gè)高頻信息卷積池化后的結(jié)果的每個(gè)channel、每個(gè)像素點(diǎn)比對(duì)，取max
將上一步得到的結(jié)果和cA卷積池化后的結(jié)果作笛卡爾積

論文地址

2、網(wǎng)絡(luò)結(jié)構(gòu)復(fù)現(xiàn)

如下圖所示，本項(xiàng)目復(fù)現(xiàn)了論文的圖像去摩爾紋方法，并對(duì)數(shù)據(jù)處理部分進(jìn)行了修改，并且網(wǎng)絡(luò)結(jié)構(gòu)上也參考了源碼中的結(jié)構(gòu)，對(duì)圖片產(chǎn)生四個(gè)下采樣特征圖，而不是論文中的三個(gè)，具體處理方式大家可以參考一下網(wǎng)絡(luò)結(jié)構(gòu)。

import math
import paddle
import paddle.nn as nn
import paddle.nn.functional as F
# import pywt
from paddle.nn import Linear, Dropout, ReLU
from paddle.nn import Conv2D, MaxPool2D
class mcnn(nn.Layer):
    def __init__(self, num_classes=1000):
        super(mcnn, self).__init__()
        self.num_classes = num_classes
        self._conv1_LL = Conv2D(3,32,7,stride=2,padding=1,)      
        # self.bn1_LL = nn.BatchNorm2D(128)
        self._conv1_LH = Conv2D(3,32,7,stride=2,padding=1,)  
        # self.bn1_LH = nn.BatchNorm2D(256)
        self._conv1_HL = Conv2D(3,32,7,stride=2,padding=1,)
        # self.bn1_HL = nn.BatchNorm2D(512)
        self._conv1_HH = Conv2D(3,32,7,stride=2,padding=1,)
        # self.bn1_HH = nn.BatchNorm2D(256)
        self.pool_1_LL = nn.MaxPool2D(kernel_size=2,stride=2, padding=0)
        self.pool_1_LH = nn.MaxPool2D(kernel_size=2,stride=2, padding=0)
        self.pool_1_HL = nn.MaxPool2D(kernel_size=2,stride=2, padding=0)
        self.pool_1_HH = nn.MaxPool2D(kernel_size=2,stride=2, padding=0)
        self._conv2 = Conv2D(32,16,3,stride=2,padding=1,)
        self.pool_2 = nn.MaxPool2D(kernel_size=2,stride=2, padding=0)
        self.dropout2 = Dropout(p=0.5)
        self._conv3 = Conv2D(16,32,3,stride=2,padding=1,)
        self.pool_3 = nn.MaxPool2D(kernel_size=2,stride=2, padding=0)
        self._conv4 = Conv2D(32,32,3,stride=2,padding=1,)
        self.pool_4 = nn.MaxPool2D(kernel_size=2,stride=2, padding=0)
        self.dropout4 = Dropout(p=0.5)
        # self.bn1_HH = nn.BatchNorm1D(256)
        self._fc1 = Linear(in_features=64,out_features=num_classes)
        self.dropout5 = Dropout(p=0.5)
        self._fc2 = Linear(in_features=2,out_features=num_classes)
    def forward(self, inputs1, inputs2, inputs3, inputs4):
        x1_LL = self._conv1_LL(inputs1)
        x1_LL = F.relu(x1_LL)
        x1_LH = self._conv1_LH(inputs2)
        x1_LH = F.relu(x1_LH)
        x1_HL = self._conv1_HL(inputs3)
        x1_HL = F.relu(x1_HL)
        x1_HH = self._conv1_HH(inputs4)
        x1_HH = F.relu(x1_HH)
        pool_x1_LL = self.pool_1_LL(x1_LL)
        pool_x1_LH = self.pool_1_LH(x1_LH)
        pool_x1_HL = self.pool_1_HL(x1_HL)
        pool_x1_HH = self.pool_1_HH(x1_HH)
        temp = paddle.maximum(pool_x1_LH, pool_x1_HL)
        avg_LH_HL_HH = paddle.maximum(temp, pool_x1_HH)
        inp_merged = paddle.multiply(pool_x1_LL, avg_LH_HL_HH)
        x2 = self._conv2(inp_merged)
        x2 = F.relu(x2)
        x2 = self.pool_2(x2)
        x2 = self.dropout2(x2)
        x3 = self._conv3(x2)
        x3 = F.relu(x3)
        x3 = self.pool_3(x3)
        x4 = self._conv4(x3)
        x4 = F.relu(x4)
        x4 = self.pool_4(x4)
        x4 = self.dropout4(x4)
        x4 = paddle.flatten(x4, start_axis=1, stop_axis=-1)
        x5 = self._fc1(x4)
        x5 = self.dropout5(x5)
        out = self._fc2(x5)
        return out
model_res = mcnn(num_classes=2)
paddle.summary(model_res,[(1,3,512,384),(1,3,512,384),(1,3,512,384),(1,3,512,384)])

---------------------------------------------------------------------------
 Layer (type)       Input Shape          Output Shape         Param #    
===========================================================================
   Conv2D-1      [[1, 3, 512, 384]]   [1, 32, 254, 190]        4,736     
   Conv2D-2      [[1, 3, 512, 384]]   [1, 32, 254, 190]        4,736     
   Conv2D-3      [[1, 3, 512, 384]]   [1, 32, 254, 190]        4,736     
   Conv2D-4      [[1, 3, 512, 384]]   [1, 32, 254, 190]        4,736     
  MaxPool2D-1   [[1, 32, 254, 190]]    [1, 32, 127, 95]          0       
  MaxPool2D-2   [[1, 32, 254, 190]]    [1, 32, 127, 95]          0       
  MaxPool2D-3   [[1, 32, 254, 190]]    [1, 32, 127, 95]          0       
  MaxPool2D-4   [[1, 32, 254, 190]]    [1, 32, 127, 95]          0       
   Conv2D-5      [[1, 32, 127, 95]]    [1, 16, 64, 48]         4,624     
  MaxPool2D-5    [[1, 16, 64, 48]]     [1, 16, 32, 24]           0       
   Dropout-1     [[1, 16, 32, 24]]     [1, 16, 32, 24]           0       
   Conv2D-6      [[1, 16, 32, 24]]     [1, 32, 16, 12]         4,640     
  MaxPool2D-6    [[1, 32, 16, 12]]      [1, 32, 8, 6]            0       
   Conv2D-7       [[1, 32, 8, 6]]       [1, 32, 4, 3]          9,248     
  MaxPool2D-7     [[1, 32, 4, 3]]       [1, 32, 2, 1]            0       
   Dropout-2      [[1, 32, 2, 1]]       [1, 32, 2, 1]            0       
   Linear-1          [[1, 64]]              [1, 2]              130      
   Dropout-3          [[1, 2]]              [1, 2]               0       
   Linear-2           [[1, 2]]              [1, 2]               6       
===========================================================================
Total params: 37,592
Trainable params: 37,592
Non-trainable params: 0
---------------------------------------------------------------------------
Input size (MB): 9.00
Forward/backward pass size (MB): 59.54
Params size (MB): 0.14
Estimated Total Size (MB): 68.68
---------------------------------------------------------------------------
{'total_params': 37592, 'trainable_params': 37592}

3、數(shù)據(jù)預(yù)處理

與源代碼不同的是，本項(xiàng)目將圖像的小波分解部分集成在了數(shù)據(jù)讀取部分，即改為了線上進(jìn)行小波分解，而不是源代碼中的線下進(jìn)行小波分解并且保存圖片。首先，定義小波分解的函數(shù)

!pip install PyWavelets

import numpy as np
import pywt
def splitFreqBands(img, levRows, levCols):
    halfRow = int(levRows/2)
    halfCol = int(levCols/2)
    LL = img[0:halfRow, 0:halfCol]
    LH = img[0:halfRow, halfCol:levCols]
    HL = img[halfRow:levRows, 0:halfCol]
    HH = img[halfRow:levRows, halfCol:levCols]
    return LL, LH, HL, HH
def haarDWT1D(data, length):
    avg0 = 0.5;
    avg1 = 0.5;
    dif0 = 0.5;
    dif1 = -0.5;
    temp = np.empty_like(data)
    # temp = temp.astype(float)
    temp = temp.astype(np.uint8)
    h = int(length/2)
    for i in range(h):
        k = i*2
        temp[i] = data[k] * avg0 + data[k + 1] * avg1;
        temp[i + h] = data[k] * dif0 + data[k + 1] * dif1;
    data[:] = temp
# computes the homography coefficients for PIL.Image.transform using point correspondences
def fwdHaarDWT2D(img):
    img = np.array(img)
    levRows = img.shape[0];
    levCols = img.shape[1];
    # img = img.astype(float)
    img = img.astype(np.uint8)
    for i in range(levRows):
        row = img[i,:]
        haarDWT1D(row, levCols)
        img[i,:] = row
    for j in range(levCols):
        col = img[:,j]
        haarDWT1D(col, levRows)
        img[:,j] = col
    return splitFreqBands(img, levRows, levCols)

!cd "data/data188843/" &amp;&amp; unzip -q 'total_images.zip'

import os 
recapture_keys = [ 'ValidationMoire']
original_keys = ['ValidationClear']
def get_image_label_from_folder_name(folder_name):
    """
    :param folder_name:
    :return:
    """
    for key in original_keys:
        if key in folder_name:
            return 'original'
    for key in recapture_keys:
        if key in folder_name:
            return 'recapture'
    return 'unclear'
label_name2label_id = {
    'original': 0,
    'recapture': 1,}
src_image_dir = "data/data188843/total_images"
dst_file = "data/data188843/total_images/train.txt"
image_folder = [file for file in os.listdir(src_image_dir)]
print(image_folder)
image_anno_list = []
for folder in image_folder:
    label_name = get_image_label_from_folder_name(folder)
    # label_id = label_name2label_id.get(label_name, 0)
    label_id = label_name2label_id[label_name]
    folder_path = os.path.join(src_image_dir, folder)
    image_file_list = [file for file in os.listdir(folder_path) if
                        file.endswith('.jpg') or file.endswith('.jpeg') or
                        file.endswith('.JPG') or file.endswith('.JPEG') or file.endswith('.png')]
    for image_file in image_file_list:
        # if need_root_dir:
        #     image_path = os.path.join(folder_path, image_file)
        # else:
        image_path = image_file
        image_anno_list.append(folder +"/"+image_path +"\t"+ str(label_id) + '\n')
dst_path = os.path.dirname(src_image_dir)
if not os.path.exists(dst_path):
    os.makedirs(dst_path)
with open(dst_file, 'w') as fd:
    fd.writelines(image_anno_list)

import paddle
import numpy as np
import pandas as pd
import PIL.Image as Image
from paddle.vision import transforms
# from haar2D import fwdHaarDWT2D
paddle.disable_static()
# 定義數(shù)據(jù)預(yù)處理
data_transforms = transforms.Compose([
    transforms.Resize(size=(448,448)),
    transforms.ToTensor(), # transpose操作 + (img / 255)
    # transforms.Normalize(      # 減均值 除標(biāo)準(zhǔn)差
    #     mean=[0.31169346, 0.25506335, 0.12432463],        
    #     std=[0.34042713, 0.29819837, 0.1375536])
    #計(jì)算過(guò)程：output[channel] = (input[channel] - mean[channel]) / std[channel]
])
# 構(gòu)建Dataset
class MyDataset(paddle.io.Dataset):
    """
    步驟一：繼承paddle.io.Dataset類
    """
    def __init__(self, train_img_list, val_img_list, train_label_list, val_label_list, mode='train', ):
        """
        步驟二：實(shí)現(xiàn)構(gòu)造函數(shù)，定義數(shù)據(jù)讀取方式，劃分訓(xùn)練和測(cè)試數(shù)據(jù)集
        """
        super(MyDataset, self).__init__()
        self.img = []
        self.label = []
        # 借助pandas讀csv的庫(kù)
        self.train_images = train_img_list
        self.test_images = val_img_list
        self.train_label = train_label_list
        self.test_label = val_label_list
        if mode == 'train':
            # 讀train_images的數(shù)據(jù)
            for img,la in zip(self.train_images, self.train_label):
                self.img.append('/home/aistudio/data/data188843/total_images/'+img)
                self.label.append(paddle.to_tensor(int(la), dtype='int64'))
        else:
            # 讀test_images的數(shù)據(jù)
            for img,la in zip(self.test_images, self.test_label):
                self.img.append('/home/aistudio/data/data188843/total_images/'+img)
                self.label.append(paddle.to_tensor(int(la), dtype='int64'))
    def load_img(self, image_path):
        # 實(shí)際使用時(shí)使用Pillow相關(guān)庫(kù)進(jìn)行圖片讀取即可，這里我們對(duì)數(shù)據(jù)先做個(gè)模擬
        image = Image.open(image_path).convert('RGB')
        # image = data_transforms(image)
        return image
    def __getitem__(self, index):
        """
        步驟三：實(shí)現(xiàn)__getitem__方法，定義指定index時(shí)如何獲取數(shù)據(jù)，并返回單條數(shù)據(jù)（訓(xùn)練數(shù)據(jù)，對(duì)應(yīng)的標(biāo)簽）
        """
        image = self.load_img(self.img[index])
        LL, LH, HL, HH = fwdHaarDWT2D(image)
        label = self.label[index]
        # print(LL.shape)
        # print(LH.shape)
        # print(HL.shape)
        # print(HH.shape)
        LL = data_transforms(LL)
        LH = data_transforms(LH)
        HL = data_transforms(HL)
        HH = data_transforms(HH)
        print(type(LL))
        print(LL.dtype)
        return LL, LH, HL, HH, np.array(label, dtype='int64')
    def __len__(self):
        """
        步驟四：實(shí)現(xiàn)__len__方法，返回?cái)?shù)據(jù)集總數(shù)目
        """
        return len(self.img)
image_file_txt = '/home/aistudio/data/data188843/total_images/train.txt'
with open(image_file_txt) as fd:
    lines = fd.readlines()
train_img_list = list()
train_label_list = list()
for line in lines:
    split_list = line.strip().split()
    image_name, label_id = split_list
    train_img_list.append(image_name)
    train_label_list.append(label_id)
# print(train_img_list)
# print(train_label_list)
# 測(cè)試定義的數(shù)據(jù)集
train_dataset = MyDataset(mode='train',train_label_list=train_label_list,  train_img_list=train_img_list, val_img_list=train_img_list, val_label_list=train_label_list)
# test_dataset = MyDataset(mode='test')
# 構(gòu)建訓(xùn)練集數(shù)據(jù)加載器
train_loader = paddle.io.DataLoader(train_dataset, batch_size=2, shuffle=True)
# 構(gòu)建測(cè)試集數(shù)據(jù)加載器
valid_loader = paddle.io.DataLoader(train_dataset, batch_size=2, shuffle=True)
print('=============train dataset=============')
for LL, LH, HL, HH, label in train_dataset:
    print('label: {}'.format(label))
    break

4、模型訓(xùn)練

model2 = paddle.Model(model_res)
model2.prepare(optimizer=paddle.optimizer.Adam(parameters=model2.parameters()),
              loss=nn.CrossEntropyLoss(),
              metrics=paddle.metric.Accuracy())
model2.fit(train_loader,
        valid_loader,
        epochs=5,
        verbose=1,
        )

總結(jié)

本項(xiàng)目主要介紹了如何使用卷積神經(jīng)網(wǎng)絡(luò)去檢測(cè)翻拍圖片，主要為摩爾紋圖片；其主要?jiǎng)?chuàng)新點(diǎn)在于網(wǎng)絡(luò)結(jié)構(gòu)上，將圖片的高低頻信息分開處理。

在本項(xiàng)目中，CNN 僅使用 1 級(jí)小波分解進(jìn)行訓(xùn)練。可以探索對(duì)多級(jí)小波分解網(wǎng)絡(luò)精度的影響。 CNN 模型可以用更多更難的例子和更深的網(wǎng)絡(luò)進(jìn)行訓(xùn)練，更多關(guān)于python 圖片去摩爾紋的資料請(qǐng)關(guān)注腳本之家其它相關(guān)文章！

您可能感興趣的文章: