cascade-classifier

问题 I want to try create my own .xml file for my graduation project with this reference. But I have a problem which stage 6 doesn't work.It gives error such as: Traceback (most recent call last): File "./tools/mergevec.py", line 170, in <module> merge_vec_files(vec_directory, output_filename) File "./tools/mergevec.py", line 120, in merge_vec_files val = struct.unpack('<iihh', content[:12]) TypeError: a bytes-like object is required, not 'str' I have found a solution which says find 0 size vector

问题 I want to try create my own .xml file for my graduation project with this reference. But I have a problem which stage 6 doesn't work.It gives error such as: Traceback (most recent call last): File "./tools/mergevec.py", line 170, in <module> merge_vec_files(vec_directory, output_filename) File "./tools/mergevec.py", line 120, in merge_vec_files val = struct.unpack('<iihh', content[:12]) TypeError: a bytes-like object is required, not 'str' I have found a solution which says find 0 size vector

问题 I need to detect people in real time using OpenCV Cascades. Currently I am using the trained cascade files which comes with OpenCV but later I will train my own LBP Cascades to achieve more speed. I do have a question. what are the ways to speed up the detection of cascades? For an example, have a look at this video. It is really fast, uses Haar cascades and nice. what kind of things I can do to achieve this speed, specially for a real time application? any tricks and hacks? 回答1: I'm not sure

问题 I am using OpenCv 2.4.10 . I have recently tried to create my own cascade classifier to detect robotino; I have 240 negative samples and 650 positive samples. But I am getting confused in the values I should give to the opencv_traincascade . numNeg : states the number of negative samples used in each stage. How should I calculate this parameter? numStage : How should I tell the number of stages wanted ? 回答1: A few points to consider: numNeg can be all the negative samples you have, however

问题 My webcam takes images. But opencv gender classification needs the images to be of the same size of that of the images used to train. So I need my webcam images to be 300x300 where the face in the webcam images would fit the resolution 300x300. I have identified the face in the webcam image using opencv face cascade classifiers. But how can I crop that face to fit in the size of 300x300? Please help with some code lines as I am new to opencv. 回答1: Here a small sample that will help you to

问题 I'm trying to run create samples on Ubuntu 16.04 with OpenCV, and I keep coming across this error when it runs. I have about 1960 negative images that I'm trying to generate sample images from. What i'm running in the terminal is: opencv_createsamples -img pipe1.jpg -bg bg.txt -info info/info.lst -pngoutput info -maxxangle 5 -maxyangle 5 -maxzangle 5 -num 1950 and and abbreviated output is: Open background image: neg/930.jpg Open background image: neg/11.jpg Open background image: neg/332.jpg

问题 I'm working on objects detection with cascade classifier on OpenCV 3.1 and VC++ 2015. I want to force the cascade to detect only one object for each image and I want to get its accuracy score. For that, I tried to use the undocumented prototype of the method CascadeClassifier::detectMultiScale with reject levels. The documented version works good. But the version with reject levels still executing for a long time without giving any result. this is my source code below. #include "stdafx.h"

问题 I'm working on objects detection with cascade classifier on OpenCV 3.1 and VC++ 2015. I want to force the cascade to detect only one object for each image and I want to get its accuracy score. For that, I tried to use the undocumented prototype of the method CascadeClassifier::detectMultiScale with reject levels. The documented version works good. But the version with reject levels still executing for a long time without giving any result. this is my source code below. #include "stdafx.h"

问题 What are the recommended parameters for CascadeClassifier::detectMultiScale() and depending on which factors I should change default parameters? void CascadeClassifier::detectMultiScale( const Mat& image, vector<Rect>& objects, double scaleFactor=1.1, int minNeighbors=3, int flags=0, Size minSize=Size(), Size maxSize=Size() ) 回答1: Amongst these parameters, you need to pay more attention to four of them: scaleFactor – Parameter specifying how much the image size is reduced at each image scale.

问题 I trained my pc with opencv_traincascade all one day long to detect 2€ coins using more than 6000 positive images similar to the following: Now, I have just tried to run a simple OpenCV program to see the results and to check the file cascade.xml . The final result is very disappointing: There are many points on the coin but there are also many other points on the background. Could it be a problem with my positive images used for training? Or maybe, am I using the detectMultiScale() with