如何解决HOG手写数字识别不起作用
我正在读一本OpenCV书中有关手写数字识别的一章，尽管我仔细阅读了一下，但我认为一切都得到了正确处理，但出现了错误public async Task<TestTable[]> GetAllEmployees()
{
IQueryable<TestTable> query = _context.TestTable;
return await query.ToArrayAsync();
}
。我尝试用Google搜索答案，似乎很多其他人遇到了非常相似的问题，但没有提供真正的答案。
任何人都可以阐明为什么此Expected 2D array,got 1D array instead方法不返回2D数组吗？我正在阅读一些文档，显然它默认情况下会返回一个平面1D数组，所以我不知道为什么这个feature.hog()方法抱怨为什么期望使用2D数组。再说一遍，我想读的这本书是我想在2015年发行的，所以也许有什么变化吗？
这是我要运行的文件：
classify.py
model.predict()这是为此编写的自定义生猪模块：
hog.py
# -*- coding: utf-8 -*-
"""
Created on Tue Nov 3 13:01:39 2020
@author: User
"""
from __future__ import print_function
from sklearn.externals import joblib
from pyimagesearch.hog import HOG
from pyimagesearch import dataset
import argparse
import mahotas
import cv2
ap = argparse.ArgumentParser()
ap.add_argument('-m','--model',required=True,help='Path to model')
ap.add_argument('-i','--image',help='Path to image')
args=vars(ap.parse_args())
model = joblib.load(args['model'])
hog = HOG(orientations=18,pixelsPerCell=(10,10),cellsPerBlock=(1,1),normalize=True)
image = cv2.imread(args["image"])
gray = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
blurred = cv2.GaussianBlur(gray,(5,5),0)
edged = cv2.Canny(blurred,30,150)
(_,cnts,_) = cv2.findContours(edged.copy(),cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)
cnts = sorted([(c,cv2.boundingRect(c)[0]) for c in cnts],key=lambda x: x[1])
for (c,_) in cnts:
(x,y,w,h) = cv2.boundingRect(c)
if w >= 7 and h>= 20:
roi = gray[y:y+h,x:x+w]
thresh = roi.copy()
T = mahotas.thresholding.otsu(roi)
thresh[thresh > T] = 255
thresh = cv2.bitwise_not(thresh)
thresh = dataset.deskew(thresh,72)
thresh = dataset.center_extent(thresh,(72,72))
cv2.imshow("thresh",thresh)
hist = hog.describe(thresh)
digit = model.predict(hist)[0] #this is where it errors
print("I think that number is: {}".format(digit))
cv2.rectangle(image,(x,y),(x+w,y+h),(0,255,0),1)
cv2.putText(image,str(digit),(x-10,y-10),cv2.FONT_HERSHEY_SIMPLEX,1.2,2)
cv2.imshow("image",image)
cv2.waitKey(0)
这是为此产生“训练模型”的原因：
train.py
# -*- coding: utf-8 -*-
"""
Created on Tue Nov 3 11:22:38 2020
@author: User
"""
from skimage import feature
class HOG:
def __init__(self,orientations=9,pixelsPerCell=(14,14),normalize=False):
self.orientations = orientations
self.pixelsPerCell = pixelsPerCell
self.cellsPerBlock = cellsPerBlock
self.normalize = normalize
def describe(self,image):
'''
(2017-11-28) Update for skimage: In scikit-image==0.12,the
normalise parameter has been updated to transform_sqrt . The
transform_sqrt performs the exact same operation,only with a
different name. If you’re using an older version of scikit-image
(again,before the v0.12 release),then you’ll want to change
transform_sqrt to normalise . In scikit-image==0.15 the default
value of block_norm="L1" has been deprecated and changed to
block_norm="L2-Hys" . Therefore,for this lesson we’ll explicitly
specify block_norm="L1" . Doing this will avoid it switching to
"L2-Hys" with version updates without us knowing (and yielding
incorrect car logo identification results). You can read about L1 and
L2 norms here:
https://gurus.pyimagesearch.com/lesson-sample-histogram-of-oriented-gradients-and-car-logo-recognition/#tour_modal
'''
hist = feature.hog(image,orientations=self.orientations,pixels_per_cell=self.pixelsPerCell,cells_per_block=self.cellsPerBlock,transform_sqrt =self.normalize,block_norm="L1")
return hist
dataset.py
# -*- coding: utf-8 -*-
"""
Created on Tue Nov 3 11:57:26 2020
@author: User
"""
from sklearn.externals import joblib
from sklearn.svm import LinearSVC
from pyimagesearch.hog import HOG
from pyimagesearch import dataset
import argparse
ap = argparse.ArgumentParser()
ap.add_argument('-d','--dataset',help='Path to dataset')
ap.add_argument('-m',help='path to where model will be stored')
args=vars(ap.parse_args())
(digits,target) = dataset.load_digits(args['dataset'])
data = []
hog = HOG(orientations=9,normalize=True)
for image in digits:
image = dataset.deskew(image,20)
image = dataset.center_extent(image,(20,20))
hist = hog.describe(image)
data.append(hist)
model = LinearSVC(random_state=42)
model.fit(data,target)
joblib.dump(model,args['model'])
，如果需要的话，请使用此自定义# -*- coding: utf-8 -*-
"""
Created on Tue Nov 3 11:35:04 2020
@author: User
"""
from . import imutils
import numpy as np
import mahotas
import cv2
def load_digits(datasetPath):
data = np.genfromtxt(datasetPath,delimiter=',',dtype='uint8')
target = data[:,0]
data = data[:,1:].reshape(data.shape[0],28,28)
return (data,target)
def deskew(image,width):
(h,w) = image.shape[:2]
moments = cv2.moments(image)
skew = moments['mu11'] / moments['mu02']
M = np.float32([
[1,skew,-0.5 * w * skew],[0,1,0]])
image = cv2.warpAffine(image,M,(w,h),flags = cv2.WARP_INVERSE_MAP | cv2.INTER_LINEAR)
image = imutils.resize(image,width=width)
return image
def center_extent(image,size):
(eW,eH) = size
if image.shape[1] > image.shape[0]:
image = imutils.resize(image,width=eW)
else:
image = imutils.resize(image,height=eH)
extent = np.zeros((eH,eW),dtype = 'uint8')
offsetX = (eW - image.shape[1]) // 2
offsetY = (eH - image.shape[0]) // 2
extent[offsetY:offsetY + image.shape[0],offsetX:offsetX + image.shape[1]] = image
CM = mahotas.center_of_mass(extent)
(cY,cX) = np.round(CM).astype('int32')
(dX,dY) = ((size[0] // 2) - cX,(size[1] // 2) - cY)
M = np.float32([[1,dX],dY]])
extent = cv2.warpAffine(extent,size)
return extent
模块
imutils.py
imutils并且我正在使用此数据found here (the train.csv file)，并且通过此脚本将其减少为5000行：
# -*- coding: utf-8 -*-
"""
Created on Tue Sep 29 16:27:16 2020
@author: User
"""
import numpy as np
import cv2
def translate(image,x,y):
M = np.float32([[1,x],y]])
shifted = cv2.warpAffine(image,(image.shape[1],image.shape[0]))
return shifted
def rotate(image,angle,center=None,scale=1.0):
(h,w) = image.shape[:2]
if not center:
center = (w // 2,h // 2)
M = cv2.getRotationMatrix2D(center,scale)
rotated = cv2.warpAffine(image,h))
return rotated
def resize(image,width=None,height=None,inter=cv2.INTER_AREA):
dim = None
(h,w) = image.shape[:2]
if width is None and height is None:
return image
if width is None:
r = height / float(h)
dim = (int(w*r),height)
else:
r = width / float(w)
dim = (width,int(h*r))
resized = cv2.resize(image,dim,interpolation = inter)
return resized
解决方法
我已经想通了一段时间，但现在有机会发帖，所以我想分享我的发现。
我认为当我试图“重塑”数组时，我实际上是在重塑错误的数组，这就是为什么它一直给我一个错误。
所以我想将我拥有的一维数组转换为二维数组，我选择了这一行：digit = model.predict(hist)[0]
并将其更改为：digit = model.predict(hist.reshape(1,-1))[0]
版权声明：本文内容由互联网用户自发贡献，该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容， 请发送邮件至 dio@foxmail.com 举报，一经查实，本站将立刻删除。
