I'm creating a object classifier in opencv python using svm. Training dataset is of 200 positive and 200 negative images. For positive images first took 200 images and cropped target object from images and resized them to (64,128) size for HOG calculation. Then for negative images, First created Pyramid of images then applied sliding window of 64X128 and then calculated HOG for positive as well all windows of negative images with labels 1 and 0. Trained svm model on hog features. I am getting error "cv2.error: OpenCV(3.4.2) C:\projects\opencv-python\opencv\modules\ml\src\svm.cpp:2010: error: (-215:Assertion failed) samples.cols == var_count && samples.type() == 5 in function 'cv::ml::SVMImpl::predict' " when i called predict function using res = svm.predict(samples[0]).ravel() method.
import cv2
import os
import time
import numpy as np
import imutils
positive_path='C:\\Users\\Admin\\3D Objects\\datqaet with hog and svm\\ROI images'
negative_path='C:\\Users\\Admin\\3D Objects\\datqaet with hog and svm\\Negative images'
def pyramid(img): #Create image Pyramid
minSize=(30, 30)
imgarr = []
while True:
scale = 2
imgarr.append(img)
w = int(img.shape[1] / scale)
img = imutils.resize(img, width=w)
if img.shape[0] < minSize[1] or img.shape[1] < minSize[0]:
break
return imgarr
def sliding_window(image, stepSize, windowSize): #Sliding window for negative images
sliding = []
for y in range(0, image.shape[0], stepSize):
for x in range(0, image.shape[1], stepSize):
sliding.append((x, y, image[y:y + windowSize[1], x:x + windowSize[0]]))
return sliding
def get_hog() :
winSize = (64,128)
blockSize = (16,16)
blockStride = (16,16)
cellSize = (8,8)
nbins = 9
derivAperture = 1
winSigma = 4.
histogramNormType = 0
L2HysThreshold = 0.2
gammaCorrection = 0
nlevels = 64
signedGradient = True
hog = cv2.HOGDescriptor(winSize,blockSize,blockStride,cellSize,nbins,derivAperture,winSigma,histogramNormType,L2HysThreshold,gammaCorrection,nlevels, signedGradient)
return hog
samples = []
labels = []
sam = []
hog = get_hog()
for filename in os.listdir(positive_path):
img = cv2.imread(os.path.join(positive_path,filename),0) #RGB image
img = cv2.resize(img,(64,128))
img = np.array(img)
hist = hog.compute(img)
hist = cv2.normalize(hist,None)
sam.append(img)
samples.append(hist)
labels.append(1)
i=0
for filename in os.listdir(negative_path):
img = cv2.imread(os.path.join(negative_path,filename),0)
(winW, winH) = (64,128)
pyr = pyramid(img)
for resized in pyr:
sliding = sliding_window(resized, stepSize=32, windowSize=(winW, winH))
for (x, y, window) in sliding:
if window.shape[0] != winH or window.shape[1] != winW:
continue
hist = hog.compute(window)
hist = cv2.normalize(hist,None)
sam.append(window)
samples.append(hist)
labels.append(0)
print(i)
i=i+1
samples = np.array(samples,dtype=np.float32)
labels = np.array(labels,dtype=int)
samples = np.squeeze(samples)
print(len(samples))
print(samples.shape)
rand = np.random.RandomState(10)
shuffle = rand.permutation(len(samples))
sam = samples[shuffle]
samples = sam[shuffle]
labels = labels[shuffle]
svm = cv2.ml.SVM_create()
svm.setKernel(cv2.ml.SVM_LINEAR)
svm.setType(cv2.ml.SVM_C_SVC)
svm.setC(2.67)
svm.setGamma(5.383)
svm_params = dict( kernel_type = cv2.ml.SVM_LINEAR,
svm_type = cv2.ml.SVM_C_SVC,
C=2.67, gamma=5.383 )
svm.train(samples,cv2.ml.ROW_SAMPLE,labels)
print("trained")
res = svm.predict(samples[0]).ravel()
print(res)
cap = cv2.VideoCapture(0)
while True:
ret, img = cap.read()
img=cv2.resize(img,(400,400))
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
(winW, winH) = (64,128)
pyr = pyramid(img)
for resized in pyr:
sliding = sliding_window(resized, stepSize=32, windowSize=(winW, winH))
for (x, y, window) in sliding:
if window.shape[0] != winH or window.shape[1] != winW:
continue
hist = hog.compute(window)
hist = cv2.normalize(hist,None)
hist = np.reshape(hist,(1,hist.shape[0]))
res = svm.predict(hist)[1].ravel()
if res == 1:
print("found")
cv2.imshow('img',img)
cv2.waitKey(10)
