Chochstr's profile - activity

What is the number mean for the Confidence? for example: Eigen_model->predict(face_resized, Eigen_Predict, Eigen_Confidence); and i have the same for LBPH and Fisher algorithms.

I would like to know this to get more accurate predictions because each algorithm is giving me different predictions and none are the correct predictions either.

also here is my project with full code on github.com https://github.com/Chochstr/OpenCVapp/

Here is my code on github I would like to improve my results of face detection as well as improving my face recognition. Any help will be really helpful. Thanks.

https://github.com/Chochstr/OpenCV_FaceDetection

I have updated my code a little can you assist me in improving my face recognizer I seem to be getting bad predictions still maybe we can chat through google or or something else?

i sent my update not much changes, also please look in another location in my github files OpenCV_Image and toward the bottom.

i'm detecting faces with detectmultiscale with lbpcascade_frontalface.xml and lbp_cascade.detectMultiScale(gray, faces2, 3, 1, 0|CASCADE_DO_CANNY_PRUNING,Size(30,30)); then looping and making the prediction but i get the wrong prediction. i have applied the equalizeHist as mentioned above. my images are 112 x 92 same as the at&t database but using png as you mentioned above.

I don't know how to implement singleScale into my code, also i don't think i want to use this because i will not know in a video capture the scale of the persons face. its uncontrolled.

I guess i don't know how to fix my code according to what you said because its not working can you take a look at my code on github at this url

https://github.com/Chochstr/OpenCV_FaceDetection.git

also with the comments above make sure if your in windows the read file is in a encoding of UTF-8 or it will be finding garbage

I'm using Fisher-faces and I would like to combined with Eigenvalues face recognition to have a more accurate prediction how would i do this? I keep getting false predictions. When I train my face recognition what is best in pictures sizes of images and file types? I would to be able to recognize my class mates when they walk into a room so the computer greets them as they walk in.

thanks

I'm using haar_cascade classifier frontal face to detect if a face is looking at the video camera, its not fast, but i would like to speed this process up. How would I do this?

I'm using detectmultiscale which seems to be where its slowing down.

Perfect! Thanks. I checked the path I was pulling in the read_csv function and the first path was garbage because of something. still not sure what, but I erased the garbage data from the first path and now all is well and I have passed this line of code.

I have tried to follow the tutorial but when i run my code i get an error which says

"OpenCV Error: Unsupported format or combination of formats In the (Fisherfaces method all input samples (training images) must be of equal size! Expected 0 pixels, but was 10304 pixels.) in unknown function, file ...facerec.cpp line 455"

This is thrown on line containing model->train(images, labels);

I'm using this code here.