Derick's profile - activity

I'm using a logitech web cam to do real time object detection in Ubuntu 16.04. I wish to rotate the output of the video

OMG. The problem now is I maintain somebody code wrote before and enhance it. Not enough time for me to re-write the w

How to rotate captured video from camera I have OpenCV project using C language. I wish to rotate the captured video fr

opencv_traincascade insufficient count of sample in vec file I have 20 positive images and 750 negative images. I gener

opencv_traincascade insufficient count of sample in vec file I have 20 positive images and 750 negative images. I gener

opencv_traincascade insufficient count of sample in vec file I have 20 positive images and 750 negative images. I gener

even I turn ON the CUDA during install OpenCV3.3, it still will not using GPU?

I have try to train my classifier using opencv_traincascade in my machine. When run it, it utilize 100% of my CPU but not use my GPU. I have install OpenCV 3.x in my Ubuntu 16.04. And I have GeForece GTX 1080 Ti/PCIe/SSE2. I success install the driver with CUDA 8.0. How I can use the GPU instead of using CPU? I use below script to train the module in terminal

opnencv_traincascade -data data -vec positives.vec -bg bg.txt -numPos 37000 -numNeg 756 -numStage 20 -w 20 -h 20

Any configuration I need to set to use the GPU?

how opencv_traincascade can using GPU I have try to train my classifier using opencv_traincascade in my machine. When ru

@berak, I have go through the tutorial "Creating your own Haar Cascade OpenCV Python Tutorial" and train my own cascade

Hi, I'm new in deep learning with open cv with python. I'm confuse whether opencv_traincascade is a image classifier algorithm or just a function? We need to train it? When using it, we need supply the path of a xml file which contains all the image dataset. This xml file also need train by ourself? I'm confuse whether we need train the xml file or we need train the opencv_traincascade? I read a book about k-NN classifier algorithm and the book mention we need to train the k-NN classifier. I'm confuse, why we need to train the algorithm but not the xml file?

Is opencv_traincascade a image classification algorithhm Hi, I'm new in deep learning with open cv with python. I'm con

I has raspberry pi 3 with raspbian jessie installed. Open CV3 and python 3.0 also installed. I get a python sample code which detect the face. I need write text on the screen but it's not write on it. I need write text once instead of repeated on top of each faces. Below is the code

import cv2
import sys
from tkinter import *
from tkinter import messagebox

faceCascade =  cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
video_capture = cv2.VideoCapture(0)
video_capture.set(3,500)
video_capture.set(4,300)
video_capture.set(12, 0.1)

frameWidth = int(video_capture.get(cv2.CAP_PROP_FRAME_WIDTH))
frameHeight = int(video_capture.get(cv2.CAP_PROP_FRAME_HEIGHT))

while True:
   ret, frame = video_capture.read()
   gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)

faces = faceCascade.detectMultiScale(
gray,
scaleFactor=1.1,
minNeighbors=5,
minSize=(30, 30),
flags=cv2.CASCADE_SCALE_IMAGE

)

# Draw a rectangle around the faces
for (x, y, w, h) in faces:
cv2.rectangle(frame, (x, y), (x+w, y+h), (0, 255, 0), 2)
#cv2.putText(frame, 'How are you', (x - 1, y - 1), cv2.FONT_HERSHEY_PLAIN,2,(0, 255, 0)) 
#if the puttext at here, it will write the text on top of each face detected.  But I just need the text appear once.

# Display the resulting frame
cv2.imshow('Video', frame)


if len(faces) > 0:
    cv2.putText(img = frame, text = 'How are you', org = (int(frameWidth/2 - 20),int(frameHeight/2)), fontFace = cv2.FONT_HERSHEY_DUPLEX, fontScale = 3, 
                color = (0, 255, 0))
#print(int(frameWidth/2 - 20),int(frameHeight/2))
#print('Found ' + str(len(faces)) + ' face(s)')

if cv2.waitKey(1) & 0xFF == ord('q'):
    break

# When everything is done, release the capture
video_capture.release()
cv2.destroyAllWindows()