Cara menggunakan kod python untuk mengalih keluar moiré daripada imej-Tutorial Python-php.cn

1. Pengenalan

Apabila frekuensi spatial piksel unsur fotosensitif hampir dengan frekuensi ruang jalur dalam imej, corak gangguan beralun baharu, yang dipanggil corak moiré, mungkin dihasilkan . Tekstur seperti grid sensor mencipta satu corak sedemikian. Jika jalur nipis dalam corak bersilang dengan struktur penderia pada sudut yang kecil, ini akan menghasilkan kesan gangguan yang ketara dalam imej. Fenomena ini sangat biasa dalam fotografi fesyen dengan tekstur halus seperti kain. Corak moiré ini mungkin muncul melalui kecerahan atau warna. Tetapi di sini, hanya imej moiré yang dihasilkan semasa pembuatan semula diproses.

Tangkap semula adalah untuk menangkap gambar dari skrin komputer, atau menangkap gambar pada skrin; Idea pemprosesan utama kertas itu

Cara menggunakan kod python untuk mengalih keluar moiré daripada imej

Lakukan transformasi Haar pada imej asal untuk mendapatkan empat peta ciri sampel turun (dua sampel cA, cH frekuensi tinggi mendatar mendatar, Menegak frekuensi tinggi menegak di bawah imej asal) cV, CD frekuensi tinggi serong pepenjuru)

2 ; Seperti yang ditunjukkan dalam rajah di bawah, projek ini menghasilkan semula kaedah demoir imej kertas, dan mengubah suai bahagian pemprosesan data Struktur rangkaian juga merujuk kepada struktur dalam kod sumber untuk menghasilkan empat peta ciri pensampelan untuk imej. , bukannya tiga dalam kertas, anda boleh merujuk kepada struktur rangkaian untuk kaedah pemprosesan tertentu.

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)])

Salin selepas log masuk

---------------------------------------------------------------------------
 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
---------------------------------------------------------------------------
{&#39;total_params&#39;: 37592, &#39;trainable_params&#39;: 37592}

Salin selepas log masuk

3. Prapemprosesan data

Berbeza daripada kod sumber, projek ini menyepadukan bahagian penguraian wavelet ke dalam data bahagian bacaan ditukar untuk melakukan penguraian wavelet dalam talian dan bukannya melakukan penguraian wavelet di luar talian dalam kod sumber dan menyimpan imej. Pertama, takrifkan fungsi penguraian wavelet

!pip install PyWavelets

Salin selepas log masuk

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)

Salin selepas log masuk

!cd "data/data188843/" && unzip -q &#39;total_images.zip&#39;

Salin selepas log masuk

import os 
recapture_keys = [ &#39;ValidationMoire&#39;]
original_keys = [&#39;ValidationClear&#39;]
def get_image_label_from_folder_name(folder_name):
    """
    :param folder_name:
    :return:
    """
    for key in original_keys:
        if key in folder_name:
            return &#39;original&#39;
    for key in recapture_keys:
        if key in folder_name:
            return &#39;recapture&#39;
    return &#39;unclear&#39;
label_name2label_id = {
    &#39;original&#39;: 0,
    &#39;recapture&#39;: 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(&#39;.jpg&#39;) or file.endswith(&#39;.jpeg&#39;) or
                        file.endswith(&#39;.JPG&#39;) or file.endswith(&#39;.JPEG&#39;) or file.endswith(&#39;.png&#39;)]
    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) + &#39;\n&#39;)
dst_path = os.path.dirname(src_image_dir)
if not os.path.exists(dst_path):
    os.makedirs(dst_path)
with open(dst_file, &#39;w&#39;) as fd:
    fd.writelines(image_anno_list)

Salin selepas log masuk

4 Latihan model

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()
# 定义数据预处理
data_transforms = transforms.Compose([
    transforms.Resize(size=(448,448)),
    transforms.ToTensor(), # transpose操作 + (img / 255)
    # transforms.Normalize(      # 减均值 除标准差
    #     mean=[0.31169346, 0.25506335, 0.12432463],        
    #     std=[0.34042713, 0.29819837, 0.1375536])
    #计算过程：output[channel] = (input[channel] - mean[channel]) / std[channel]
])
# 构建Dataset
class MyDataset(paddle.io.Dataset):
    """
    步骤一：继承paddle.io.Dataset类
    """
    def __init__(self, train_img_list, val_img_list, train_label_list, val_label_list, mode=&#39;train&#39;, ):
        """
        步骤二：实现构造函数，定义数据读取方式，划分训练和测试数据集
        """
        super(MyDataset, self).__init__()
        self.img = []
        self.label = []
        # 借助pandas读csv的库
        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 == &#39;train&#39;:
            # 读train_images的数据
            for img,la in zip(self.train_images, self.train_label):
                self.img.append(&#39;/home/aistudio/data/data188843/total_images/&#39;+img)
                self.label.append(paddle.to_tensor(int(la), dtype=&#39;int64&#39;))
        else:
            # 读test_images的数据
            for img,la in zip(self.test_images, self.test_label):
                self.img.append(&#39;/home/aistudio/data/data188843/total_images/&#39;+img)
                self.label.append(paddle.to_tensor(int(la), dtype=&#39;int64&#39;))
    def load_img(self, image_path):
        # 实际使用时使用Pillow相关库进行图片读取即可，这里我们对数据先做个模拟
        image = Image.open(image_path).convert(&#39;RGB&#39;)
        # image = data_transforms(image)
        return image
    def __getitem__(self, index):
        """
        步骤三：实现__getitem__方法，定义指定index时如何获取数据，并返回单条数据（训练数据，对应的标签）
        """
        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=&#39;int64&#39;)
    def __len__(self):
        """
        步骤四：实现__len__方法，返回数据集总数目
        """
        return len(self.img)
image_file_txt = &#39;/home/aistudio/data/data188843/total_images/train.txt&#39;
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)
# 测试定义的数据集
train_dataset = MyDataset(mode=&#39;train&#39;,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=&#39;test&#39;)
# 构建训练集数据加载器
train_loader = paddle.io.DataLoader(train_dataset, batch_size=2, shuffle=True)
# 构建测试集数据加载器
valid_loader = paddle.io.DataLoader(train_dataset, batch_size=2, shuffle=True)
print(&#39;=============train dataset=============&#39;)
for LL, LH, HL, HH, label in train_dataset:
    print(&#39;label: {}&#39;.format(label))
    break

Salin selepas log masuk

Atas ialah kandungan terperinci Cara menggunakan kod python untuk mengalih keluar moiré daripada imej. Untuk maklumat lanjut, sila ikut artikel berkaitan lain di laman web China PHP!