首页 \ 问答 \ 为MNIST OCR预处理图像(Preprocessing an image for MNIST OCR)

为MNIST OCR预处理图像(Preprocessing an image for MNIST OCR)

我正忙于在python中使用OCR应用程序来读取数字。 我正在使用OpenCV查找图像上的轮廓,裁剪它,然后将图像预处理为28x28以获取MNIST数据集。 我的图像不是方形的,所以当我调整图像大小时,我似乎失去了很多质量。 我可以尝试任何提示或建议吗?

这是原始图像

这是在编辑之后

这应该是它的质量

我尝试过http://opencv-python-tutroals.readthedocs.io/en/latest/py_tutorials/py_imgproc/py_morphological_ops/py_morphological_ops.html中的一些技巧,比如Dilation和Opening。 但它并没有让它变得更好,只会让它变得模糊......

这是我使用的代码(找到轮廓,裁剪它,调整它,然后阈值,然后我居中)

import numpy as np
import cv2
import imutils
import scipy
from imutils.perspective import four_point_transform
from scipy import ndimage

images = np.zeros((4, 784))
correct_vals = np.zeros((4, 10))

i = 0


def getBestShift(img):
    cy, cx = ndimage.measurements.center_of_mass(img)

    rows, cols = img.shape
    shiftx = np.round(cols / 2.0 - cx).astype(int)
    shifty = np.round(rows / 2.0 - cy).astype(int)

    return shiftx, shifty


def shift(img, sx, sy):
    rows, cols = img.shape
    M = np.float32([[1, 0, sx], [0, 1, sy]])
    shifted = cv2.warpAffine(img, M, (cols, rows))
    return shifted


for no in [1, 3, 4, 5]:
    image = cv2.imread("images/" + str(no) + ".jpg")
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    blurred = cv2.GaussianBlur(gray, (5, 5), 0)
    edged = cv2.Canny(blurred, 50, 200, 255)

    cnts = cv2.findContours(edged.copy(), cv2.RETR_EXTERNAL,
                            cv2.CHAIN_APPROX_SIMPLE)
    cnts = cnts[0] if imutils.is_cv2() else cnts[1]
    cnts = sorted(cnts, key=cv2.contourArea, reverse=True)
    displayCnt = None

    for c in cnts:
        # approximate the contour
        peri = cv2.arcLength(c, True)
        approx = cv2.approxPolyDP(c, 0.02 * peri, True)

        # if the contour has four vertices, then we have found
        # the thermostat display
        if len(approx) == 4:
            displayCnt = approx
            break

    warped = four_point_transform(gray, displayCnt.reshape(4, 2))
    gray = cv2.resize(255 - warped, (28, 28))
    (thresh, gray) = cv2.threshold(gray, 128, 255, cv2.THRESH_BINARY |     cv2.THRESH_OTSU)


    while np.sum(gray[0]) == 0:
        gray = gray[1:]

    while np.sum(gray[:, 0]) == 0:
        gray = np.delete(gray, 0, 1)

    while np.sum(gray[-1]) == 0:
        gray = gray[:-1]

    while np.sum(gray[:, -1]) == 0:
        gray = np.delete(gray, -1, 1)

    rows, cols = gray.shape

    if rows > cols:
        factor = 20.0 / rows
        rows = 20
        cols = int(round(cols * factor))
        gray = cv2.resize(gray, (cols, rows))

    else:
        factor = 20.0 / cols
        cols = 20
        rows = int(round(rows * factor))
        gray = cv2.resize(gray, (cols, rows))

    colsPadding = (int(np.math.ceil((28 - cols) / 2.0)), int(np.math.floor((28 - cols) / 2.0)))
    rowsPadding = (int(np.math.ceil((28 - rows) / 2.0)), int(np.math.floor((28 - rows) / 2.0)))
    gray = np.lib.pad(gray, (rowsPadding, colsPadding), 'constant')

    shiftx, shifty = getBestShift(gray)
    shifted = shift(gray, shiftx, shifty)
    gray = shifted

    cv2.imwrite("processed/" + str(no) + ".png", gray)
    cv2.imshow("imgs", gray)
    cv2.waitKey(0)

I'm busy with an OCR application in python to read digits. I'm using OpenCV to find the contours on an image, crop it, and then preprocess the image to 28x28 for the MNIST dataset. My images are not square, so I seem to lose a lot of quality when I resize the image. Any tips or suggestions I could try?

This is the original image

This is after editing it

And this is the quality it should be

I've tried some tricks from http://opencv-python-tutroals.readthedocs.io/en/latest/py_tutorials/py_imgproc/py_morphological_ops/py_morphological_ops.html , like Dilation and Opening. But it doesnt make it better, it only makes it vague...

This it the code im using (find contour,crop it, resize it, then threshold, and then i center it)

import numpy as np
import cv2
import imutils
import scipy
from imutils.perspective import four_point_transform
from scipy import ndimage

images = np.zeros((4, 784))
correct_vals = np.zeros((4, 10))

i = 0


def getBestShift(img):
    cy, cx = ndimage.measurements.center_of_mass(img)

    rows, cols = img.shape
    shiftx = np.round(cols / 2.0 - cx).astype(int)
    shifty = np.round(rows / 2.0 - cy).astype(int)

    return shiftx, shifty


def shift(img, sx, sy):
    rows, cols = img.shape
    M = np.float32([[1, 0, sx], [0, 1, sy]])
    shifted = cv2.warpAffine(img, M, (cols, rows))
    return shifted


for no in [1, 3, 4, 5]:
    image = cv2.imread("images/" + str(no) + ".jpg")
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    blurred = cv2.GaussianBlur(gray, (5, 5), 0)
    edged = cv2.Canny(blurred, 50, 200, 255)

    cnts = cv2.findContours(edged.copy(), cv2.RETR_EXTERNAL,
                            cv2.CHAIN_APPROX_SIMPLE)
    cnts = cnts[0] if imutils.is_cv2() else cnts[1]
    cnts = sorted(cnts, key=cv2.contourArea, reverse=True)
    displayCnt = None

    for c in cnts:
        # approximate the contour
        peri = cv2.arcLength(c, True)
        approx = cv2.approxPolyDP(c, 0.02 * peri, True)

        # if the contour has four vertices, then we have found
        # the thermostat display
        if len(approx) == 4:
            displayCnt = approx
            break

    warped = four_point_transform(gray, displayCnt.reshape(4, 2))
    gray = cv2.resize(255 - warped, (28, 28))
    (thresh, gray) = cv2.threshold(gray, 128, 255, cv2.THRESH_BINARY |     cv2.THRESH_OTSU)


    while np.sum(gray[0]) == 0:
        gray = gray[1:]

    while np.sum(gray[:, 0]) == 0:
        gray = np.delete(gray, 0, 1)

    while np.sum(gray[-1]) == 0:
        gray = gray[:-1]

    while np.sum(gray[:, -1]) == 0:
        gray = np.delete(gray, -1, 1)

    rows, cols = gray.shape

    if rows > cols:
        factor = 20.0 / rows
        rows = 20
        cols = int(round(cols * factor))
        gray = cv2.resize(gray, (cols, rows))

    else:
        factor = 20.0 / cols
        cols = 20
        rows = int(round(rows * factor))
        gray = cv2.resize(gray, (cols, rows))

    colsPadding = (int(np.math.ceil((28 - cols) / 2.0)), int(np.math.floor((28 - cols) / 2.0)))
    rowsPadding = (int(np.math.ceil((28 - rows) / 2.0)), int(np.math.floor((28 - rows) / 2.0)))
    gray = np.lib.pad(gray, (rowsPadding, colsPadding), 'constant')

    shiftx, shifty = getBestShift(gray)
    shifted = shift(gray, shiftx, shifty)
    gray = shifted

    cv2.imwrite("processed/" + str(no) + ".png", gray)
    cv2.imshow("imgs", gray)
    cv2.waitKey(0)

原文:https://stackoverflow.com/questions/49796710
更新时间:2021-07-12 20:07

最满意答案

听起来你可能正在使用自动生成的字段。 在设计视图中,单击gridview上的智能标记,然后单击“编辑列”。 然后取消选中“自动生成字段”复选框。 如果我理解正确的话,我认为这应该可以解决你的问题。


Sounds like you might be using Auto-generated fields. In design view, click the smart tag on the gridview and click "edit columns." Then uncheck the checkbox that says "Auto-generate fields." I think this should fix your problem if I am understanding you correctly.

相关问答

更多

最新问答

更多
  • 您如何使用git diff文件,并将其应用于同一存储库的副本的本地分支?(How do you take a git diff file, and apply it to a local branch that is a copy of the same repository?)
  • 将长浮点值剪切为2个小数点并复制到字符数组(Cut Long Float Value to 2 decimal points and copy to Character Array)
  • OctoberCMS侧边栏不呈现(OctoberCMS Sidebar not rendering)
  • 页面加载后对象是否有资格进行垃圾回收?(Are objects eligible for garbage collection after the page loads?)
  • codeigniter中的语言不能按预期工作(language in codeigniter doesn' t work as expected)
  • 在计算机拍照在哪里进入
  • 使用cin.get()从c ++中的输入流中丢弃不需要的字符(Using cin.get() to discard unwanted characters from the input stream in c++)
  • No for循环将在for循环中运行。(No for loop will run inside for loop. Testing for primes)
  • 单页应用程序:页面重新加载(Single Page Application: page reload)
  • 在循环中选择具有相似模式的列名称(Selecting Column Name With Similar Pattern in a Loop)
  • System.StackOverflow错误(System.StackOverflow error)
  • KnockoutJS未在嵌套模板上应用beforeRemove和afterAdd(KnockoutJS not applying beforeRemove and afterAdd on nested templates)
  • 散列包括方法和/或嵌套属性(Hash include methods and/or nested attributes)
  • android - 如何避免使用Samsung RFS文件系统延迟/冻结?(android - how to avoid lag/freezes with Samsung RFS filesystem?)
  • TensorFlow:基于索引列表创建新张量(TensorFlow: Create a new tensor based on list of indices)
  • 企业安全培训的各项内容
  • 错误:RPC失败;(error: RPC failed; curl transfer closed with outstanding read data remaining)
  • C#类名中允许哪些字符?(What characters are allowed in C# class name?)
  • NumPy:将int64值存储在np.array中并使用dtype float64并将其转换回整数是否安全?(NumPy: Is it safe to store an int64 value in an np.array with dtype float64 and later convert it back to integer?)
  • 注销后如何隐藏导航portlet?(How to hide navigation portlet after logout?)
  • 将多个行和可变行移动到列(moving multiple and variable rows to columns)
  • 提交表单时忽略基础href,而不使用Javascript(ignore base href when submitting form, without using Javascript)
  • 对setOnInfoWindowClickListener的意图(Intent on setOnInfoWindowClickListener)
  • Angular $资源不会改变方法(Angular $resource doesn't change method)
  • 在Angular 5中不是一个函数(is not a function in Angular 5)
  • 如何配置Composite C1以将.m和桌面作为同一站点提供服务(How to configure Composite C1 to serve .m and desktop as the same site)
  • 不适用:悬停在悬停时:在元素之前[复制](Don't apply :hover when hovering on :before element [duplicate])
  • 常见的python rpc和cli接口(Common python rpc and cli interface)
  • Mysql DB单个字段匹配多个其他字段(Mysql DB single field matching to multiple other fields)
  • 产品页面上的Magento Up出售对齐问题(Magento Up sell alignment issue on the products page)