2016-12-10 22:47:26 -0600 | received badge | ● Student (source) |
2016-12-10 14:25:03 -0600 | commented question | Problem with Cascade Classifier Thank you very much! I've now taken samples from a video and optimized minNeighbours and min Size. It works very well. |
2016-12-09 07:04:39 -0600 | commented question | Problem with Cascade Classifier face_cascade.detectMultiScale(frame_gray, faces, 1.1, 0, 0, cv::Size(10, 10)); |
2016-12-08 08:23:37 -0600 | asked a question | Problem with Cascade Classifier I've problems with the Cascade Classifer. I created 5000 positive samples like this: with this command: C:\OpenCV31\opencv\build\x64\vc14\bin\opencv_createsamples.exe -img C:\CreateSamples\test\image6.jpg -vec gew.vec -bg neg.txt -num 5000 -w 80 -h 80 -show -maxyangle 0.0 -maxzangle 0.0 -maxxangle 0.5 -bgcolor 0 then i trained a classifier like this: C:\OpenCV31\opencv\build\x64\vc14\bin\opencv_traincascade.exe -data NEWclassifier -vec gew.vec -bg neg.txt -numStages 15 -numPos 2500 -numNeg 1500 -w 80 -h 80 -precalcValBufSize 4048 -precalcIdxBufSize 4048 -featureType LBP and get this result: The Problem is: it detects nearly everything as an object: I used this image: and get this: I'm new with Cascade Classifier and read a lot of tutorials and samples, but i don't get my mistake. Can you help me? I call detectMultiscale like this: face_cascade.detectMultiScale(frame_gray, faces, 1.1, 0, 0, cv::Size(10, 10)); |
2016-11-24 07:05:11 -0600 | commented question | Cascade classifier doesn't detect object Okay, whren i use images wich are lager than than 100x100px it dectects an object everywhere in the image not just in the position of the object. I dont understand why. |
2016-11-24 06:20:30 -0600 | asked a question | Cascade classifier doesn't detect object Hello everyone, i've trained a Cascade classifier with opencv_traincascade.exe. In the 0-Stage it says HR 1 FA 0. But whren i use it to detect an object it doesn't detect it. I use C++ and OpenCV 3.1. The image size is 100x100px. Even if i use one of the positive images that i used for training it doesnt detect any object. Do you have any ideas what my problem could be? (more) |
2016-11-24 06:14:32 -0600 | received badge | ● Enthusiast |
2016-11-23 05:46:26 -0600 | commented question | opencv_traincascade: Calculating numstages numpos numneg I don't find my problem. I've now selected some more positives (36). But the training stops after the first stage. Even if i just do it with -numStages 2 -numPos 1 -numNeg 10. But why? After the calculation like in the link you posted, there must be enough images. |
2016-11-21 10:15:55 -0600 | received badge | ● Editor (source) |
2016-11-19 11:31:24 -0600 | asked a question | opencv_traincascade: Calculating numstages numpos numneg Hello Everyone, I'm new in to OpenCv and Cascade training. How can I calculate -numstages -numpos -numneg. My .vec file contains 6 positive Samples. And i have 129 negative Images. Can you help me with the calculation? |