techlearner's profile - activity

I am working on a vein pattern recognition project based on SURF algorithm and euclidean distance. I have completed my program to find the maximum and minimum distance between vein features and find a match exactly when there is an identical image. i.e max and min distance between two images is zero. In this case, how would I find my FAR and FRR. Will it be 0% or am I missing a big concept here?

Even if there is a slight variation it wouldn't match in which case, I guess I need to have a threshold value to compare to. I have calculate the max and min distance between all combination of images with the same hand, with different hands. In this case, how do I computer the FAR and FRR. This is my first biometrics project and it would be helpful if I am directed to any resource that would help me in this. Thank you.

Kindly help me out.

@martin :Thank you so much, that did the trick!

Thank you for the reply. I corrected those and I still get the same result. The problem is, the images are not being searched in the directory specified by dir. Instead it searches the image in the default directory where OpenCV is installed.

I am working on Image matching program, it captures image from IR camera stores it in one directory. A database of images exist in a different directory. I get an unexpected result while executing. I somehow realize that it's because I'm messing with different directories and something basic. Any help in getting around the mistake? Here's a snippet of the code.

Code:

VideoCapture cap(0);    
Mat frame;
Mat src, dst, tmp,img_3,img_4;

filename3 = (char *)malloc(sizeof(char));
printf("\n-------------------------------------------------\n");
printf("\nOne to Many Image matching with SURF Algorithm.\n");
printf("\n-------------------------------------------------\n");

//Get the Vein image from Webcam that needs to be compared with the database.
// The below function gets frame and saves it in /home/srikbaba/opencv/veins
veincnt = captureVein(veincnt, cap);
if(veincnt == -1)
     cout << "A problem has occured" << endl;
printf("\nPlease enter the filename of saved image with the extension.\n");
scanf("%s",filename3);
//Scan the directory for images.
DIR *dir;
struct dirent *ent;
clock_t tstart1 = clock(); //start clock function, do something!!!!
if ((dir = opendir ("/home/srikbaba/images")) != NULL) 
{
    /* print all the files and directories within directory */
    while ((ent = readdir (dir)) != NULL) 
    {
        if(ent->d_type!= DT_DIR)
        {
            //Print the images
            printf ("%s\n", ent->d_name);
            //Store the Filename
            img_db = ent->d_name;
            //Open each file name as Mat identifier and loop the process
            img_3 = imread (filename3, IMREAD_GRAYSCALE);

//Filename3 is saved in /home/srikbaba/opencv/veins --> different directory
// I feel this is the problem
                img_4 = imread (img_db, IMREAD_GRAYSCALE);
                if( !img_3.data)
                {
                    std::cout<< " --(!) Invalid filename or file not found! " << std::endl;
                    return -1;
                }

Because of this I always get --(!) Invalid filename or file not found message. Is there a way I can compare one image from a directory and another image from a different directory? I hope what I asked is not confusing. Kindly help.

Working on Opencv - C++ on Ubuntu 12.04 LTS

0 down vote favorite

I want to extract the vein patterns from the attached images. I am trying to code to Vein pattern recognition system. I tried the Canny Edge Detector for getting the edges of the veins but somehow they are not very clear. Any improvisations or other techniques would be greatly appreciated. For information, I am trying to write a C++ Code in OpenCV on Ubuntu.

Source ROI Canny

Hello,

I am working on opencv code written in C++ on Ubuntu that can match vein patterns. I have captured 4 vein images. In my program, I would like to capture a new image from the IR camera and compare it with the files in the images directory. I am planning to use fuzzy C clustering algorithm for my matching. I have created a user menu in which one option is comparing my algorithm with FLANN, SIFT, etc. This comparison is based on the time taken. How do you calculate the time taken for computation?

I am completely new to Fuzzy clustering and any tutorials/Sample codes that might help is greatly appreciated.

Also, can you please suggest how to go about comparing a file captured from camera to a file in directory in linux?