圖片去摩爾紋簡述實現python代碼示例
1、前言
當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，可能產生一種新的波浪形的幹擾圖案，即所謂的摩爾紋。傳感器的網格狀紋理構成瞭一個這樣的圖案。當圖案中的細條狀結構與傳感器的結構以小角度交叉時，這種效應也會在圖像中產生明顯的幹擾。這種現象在一些細密紋理情況下，比如時尚攝影中的佈料上，非常普遍。這種摩爾紋可能通過亮度也可能通過顏色來展現。但是在這裡，僅針對在翻拍過程中產生的圖像摩爾紋進行處理。
翻拍即從計算機屏幕上捕獲圖片，或對著屏幕拍攝圖片；該方式會在圖片上產生摩爾紋現象
論文主要處理思路
- 對原圖作Haar變換得到四個下采樣特征圖（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）
- 然後分別利用四個獨立的CNN對四個下采樣特征圖卷積池化，提取特征信息
- 原文隨後對三個高頻信息卷積池化後的結果的每個channel、每個像素點比對，取max
- 將上一步得到的結果和cA卷積池化後的結果作笛卡爾積
論文地址
2、網絡結構復現
如下圖所示，本項目復現瞭論文的圖像去摩爾紋方法，並對數據處理部分進行瞭修改，並且網絡結構上也參考瞭源碼中的結構，對圖片產生四個下采樣特征圖，而不是論文中的三個，具體處理方式大傢可以參考一下網絡結構。
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、數據預處理
與源代碼不同的是，本項目將圖像的小波分解部分集成在瞭數據讀取部分，即改為瞭線上進行小波分解，而不是源代碼中的線下進行小波分解並且保存圖片。首先，定義小波分解的函數
!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/" && 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()
# 定義數據預處理
data_transforms = transforms.Compose([
transforms.Resize(size=(448,448)),
transforms.ToTensor(), # transpose操作 + (img / 255)
# transforms.Normalize( # 減均值 除標準差
# mean=[0.31169346, 0.25506335, 0.12432463],
# std=[0.34042713, 0.29819837, 0.1375536])
#計算過程：output[channel] = (input[channel] - mean[channel]) / std[channel]
])
# 構建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：實現構造函數，定義數據讀取方式，劃分訓練和測試數據集
"""
super(MyDataset, self).__init__()
self.img = []
self.label = []
# 借助pandas讀csv的庫
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的數據
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的數據
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):
# 實際使用時使用Pillow相關庫進行圖片讀取即可，這裡我們對數據先做個模擬
image = Image.open(image_path).convert('RGB')
# image = data_transforms(image)
return image
def __getitem__(self, index):
"""
步驟三：實現__getitem__方法，定義指定index時如何獲取數據，並返回單條數據（訓練數據，對應的標簽）
"""
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：實現__len__方法，返回數據集總數目
"""
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)
# 測試定義的數據集
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')
# 構建訓練集數據加載器
train_loader = paddle.io.DataLoader(train_dataset, batch_size=2, shuffle=True)
# 構建測試集數據加載器
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
本項目主要介紹瞭如何使用卷積神經網絡去檢測翻拍圖片，主要為摩爾紋圖片；其主要創新點在於網絡結構上，將圖片的高低頻信息分開處理。
在本項目中，CNN 僅使用 1 級小波分解進行訓練。 可以探索對多級小波分解網絡精度的影響。 CNN 模型可以用更多更難的例子和更深的網絡進行訓練，更多關於python 圖片去摩爾紋的資料請關註WalkonNet其它相關文章！
推薦閱讀：
- Pytorch深度學習之實現病蟲害圖像分類
- 超詳細PyTorch實現手寫數字識別器的示例代碼
- Python編程pytorch深度卷積神經網絡AlexNet詳解
- 淺談Pytorch 定義的網絡結構層能否重復使用
- PyTorch 遷移學習實踐(幾分鐘即可訓練好自己的模型)