byoon's profile - activity

Do facial landmark detectors work across different languages? Hi everyone, I am currently using a dlib facial landmark d

I am currently running OpenCV version 3.4.4 on Python 3.7.1 and designed a program that utilizes the eye haar cascade classifiers. The program runs fine but often misinterprets the center lower lip or one of the nostrils as a false eye. Is this a problem with the cascade I am using? Are there ways to limit my program to only the two most prominent eye features?

Here is an example:

While on the subject of Haar Cascades, when using the detectMultiScale function to find the position of the face, I noticed that when the face is moved upwards, the y-value actually decreases. Why might that be the case?

Any and all help is appreciated, B

Haar Cascades: Limiting detectMultiScale to just one set of facial features? I am currently running OpenCV version 3.4.4

I am following a basic tutorial on image morphology from this website here. Currently running OpenCV version 3.1.0 on Microsoft Visual Studio 2017. I was able to input my own image by adding the image path to the debugging command arguments. However, this line confused me:

cv::CommandLineParser parser(argc, argv, "{help h||}{ @image | ../data/baboon.jpg | }");

I sort of understand where argc and argv came from, but what is the third input? The image they were trying to display in the sample code was a baboon, so the last part is the image path, but what are the first two parts? And why the brackets? After that line was this statement:

std::string filename = parser.get<std::string>("@image");

The filename variable was then used to open a file using the imread function, but what does that line actually do? Any help is appreciated, thanks in advance, B

What is the third argument in CommandLineParser parser() function? I am following a basic tutorial on image morphology f

Finding an OpenCV debug file I am a high school programmer little to no experience programming outside of Python IDLE. I