在Android上运行基于TensorFlow Lite训练的二维码检测模型

二维码定位可以使用传统的图形学或者机器学习。那么哪种在手机上运行的效率更高？我们可以动手实验下。

使用TensorFlow Lite训练二维码检测模型

训练图集来自于boofcv.org。为了方便，我整理之后放到了GitHub仓库里。

下载二维码图集：

git clone https://github.com/yushulx/barcode-qrcode-images.git

创建一个切分数据集的Python脚本partition_dataset.py：

""" usage: partition_dataset.py [-h] [-i IMAGEDIR] [-o OUTPUTDIR] [-r RATIO] [-x]
Partition dataset of images into training and testing sets
optional arguments:
  -h, --help            show this help message and exit
  -i IMAGEDIR, --imageDir IMAGEDIR
                        Path to the folder where the image dataset is stored. If not specified, the CWD will be used.
  -o OUTPUTDIR, --outputDir OUTPUTDIR
                        Path to the output folder where the train and test dirs should be created. Defaults to the same directory as IMAGEDIR.
  -r RATIO, --ratio RATIO
                        The ratio of the number of test images over the total number of images. The default is 0.1.
  -x, --xml             Set this flag if you want the xml annotation files to be processed and copied over.
"""
import os
import re
from shutil import copyfile
import argparse
import math
import random
import cv2

def png2jpg(source, filename):
    if filename[-4:] == '.png':
        filepath = os.path.join(source, filename)
        img = cv2.imread(filepath)
        filepath = filepath[:-4] + '.jpg'
        filename = filename[:-4] + '.jpg'
        cv2.imwrite(filepath, img)
        print(filepath)

    return filename

def iterate_dir(source, dest, ratio, copy_xml):
    source = source.replace('\\', '/')
    dest = dest.replace('\\', '/')
    train_dir = os.path.join(dest, 'train')
    test_dir = os.path.join(dest, 'test')

    if not os.path.exists(train_dir):
        os.makedirs(train_dir)
    if not os.path.exists(test_dir):
        os.makedirs(test_dir)

    images = [f for f in os.listdir(source)
              if re.search(r'([a-zA-Z0-9\s_\\.\-\(\):])+(?i)(.jpg|.jpeg|.png)$', f)]

    num_images = len(images)
    num_test_images = math.ceil(ratio*num_images)

    for i in range(num_test_images):
        idx = random.randint(0, len(images)-1)
        filename = images[idx]
        filename = png2jpg(source, filename)
        copyfile(os.path.join(source, filename),
                 os.path.join(test_dir, filename))
        if copy_xml:
            xml_filename = os.path.splitext(filename)[0]+'.xml'
            copyfile(os.path.join(source, xml_filename),
                     os.path.join(test_dir,xml_filename))
        images.remove(images[idx])

    for filename in images:
        filename = png2jpg(source, filename)
        copyfile(os.path.join(source, filename),
                 os.path.join(train_dir, filename))
        if copy_xml:
            xml_filename = os.path.splitext(fil