2013-07-09 05:52:26 -0600 | asked a question | Problem with opencv_haartraining: correct use of image Hi my name is andrea and I'm trying to use opencv_haartraining. I cut 150 images of a particular eyeglass frame. For make this I photographed putting it behind a sheet of white paper and cutting exactly the region of eyeglasses. next I have past the region cut on a white background. Next I have generate 7000 samples with createsamples and I have set it with bg 256 so the write backgroud is take as trasparent. Finished it I have generated the cascade with haartraining, but the xml generated recognizes a lot false-positive. I assumed that setting the white to transparent the image were considered positive only in regions with different colors. my assumption is correct or I need positive images without "holes"? For greater clarification on what the concept will bring a clearer example. If I wanted to recognize a cross using the above technique. the program would recognize only one or because you have to pass a rectangular region it would recognize the cross with the background of bg in the rectangular area given him? |
2013-06-08 08:29:23 -0600 | commented answer | VideoCapture crashes on Samsung Galaxy S4 (Android 4.2.3) thanks for all. I have resolved the problem. I have change all call to videocamputer with call to CameraBridgeViewBase and now the app run in all android device with androind 4.0.3 how minimal sistem. thanks so much for the support |
2013-06-07 07:40:07 -0600 | commented answer | VideoCapture crashes on Samsung Galaxy S4 (Android 4.2.3) yes I'm sure I have the last version and for more security I have installed the library(or driver I don't know the correct type) for my arm. |
2013-06-07 04:15:43 -0600 | asked a question | VideoCapture crashes on Samsung Galaxy S4 (Android 4.2.3) I have Run the program of Roman for eyes and face detection. This program uses Speaking with Roman he has noted in the log an another and more specific error: therefore I think that the error due to OpenCV library which don't support the camera of Samsung S4. My opinion is supported from my second test on Samsung S2 with android 4.1.2 where the program runs perfectly |