我正在尝试使用自己的图像训练SVM并将其提供给OpenCV中的HOGDescriptor。
训练似乎进展顺利,但是当我尝试使用setSVMDetector
函数将模型提供给HOGDescriptor时,它失败了。
培训代码
Mat trainingImages = new Mat();
Mat trainingLables = new Mat();
String personsPath = "C:\INRIAPerson\\INRIAPerson\\96X160H96\\Train\\pos";
for (File file : new File(personsPath).listFiles()) {
if(file.isFile()){
Mat img = Imgcodecs.imread(file.getPath());
Mat newImg = new Mat();
Imgproc.cvtColor(img, newImg, Imgproc.COLOR_BGR2GRAY);
newImg = newImg.reshape(1,1);
trainingImages.push_back(newImg);
trainingLables.push_back(Mat.ones(new Size(1,1), CvType.CV_32SC1));
}
}
String nonPersonsPath = "C:\\NRIAPerson\\INRIAPerson\\train_64x128_H96\\neg";
for (File file : new File(nonPersonsPath).listFiles()) {
if(file.isFile()){
Mat img = Imgcodecs.imread(file.getPath());
Mat newImg = new Mat();
Imgproc.cvtColor(img, newImg, Imgproc.COLOR_BGR2GRAY);
Imgproc.resize(newImg, newImg, new Size(160 , 96));
newImg = newImg.reshape(1,1);
trainingImages.push_back(newImg);
trainingLables.push_back(Mat.zeros(new Size(1,1), CvType.CV_32SC1));
}
}
trainingImages.convertTo(trainingImages, CvType.CV_32FC1);
SVM trainer = SVM.create();
trainer.setKernel(SVM.LINEAR);
trainer.train(trainingImages, Ml.ROW_SAMPLE, trainingLables);
HOGDescriptor hog = new HOGDescriptor(new Size(160, 96), new Size(8,8), new Size(4,4), new Size(4,4), 9);
Mat supportVector = trainer.getSupportVectors();
hog.setSVMDetector(supportVector);
错误消息
libpng warning: iCCP: known incorrect sRGB profile
libpng warning: iCCP: known incorrect sRGB profile
libpng warning: iCCP: known incorrect sRGB profile
libpng warning: iCCP: known incorrect sRGB profile
libpng warning: iCCP: known incorrect sRGB profile
libpng warning: iCCP: known incorrect sRGB profile
libpng warning: iCCP: known incorrect sRGB profile
libpng warning: iCCP: known incorrect sRGB profile
libpng warning: iCCP: known incorrect sRGB profile
libpng warning: iCCP: known incorrect sRGB profile
libpng warning: iCCP: known incorrect sRGB profile
libpng warning: iCCP: known incorrect sRGB profile
libpng warning: iCCP: known incorrect sRGB profile
libpng warning: iCCP: known incorrect sRGB profile
libpng warning: iCCP: known incorrect sRGB profile
libpng warning: iCCP: known incorrect sRGB profile
libpng warning: iCCP: known incorrect sRGB profile
libpng warning: iCCP: known incorrect sRGB profile
libpng warning: iCCP: known incorrect sRGB profile
libpng warning: iCCP: known incorrect sRGB profile
libpng warning: iCCP: known incorrect sRGB profile
libpng warning: iCCP: known incorrect sRGB profile
libpng warning: iCCP: known incorrect sRGB profile
libpng warning: iCCP: known incorrect sRGB profile
libpng warning: iCCP: known incorrect sRGB profile
OpenCV Error: Assertion failed (checkDetectorSize()) in cv::HOGDescriptor::setSVMDetector, file C:\builds\master_PackSlaveAddon-win64-vc12-static\opencv\modules\objdetect\src\hog.cpp, line 117
Exception in thread "main" CvException [org.opencv.core.CvException: cv::Exception: C:\builds\master_PackSlaveAddon-win64-vc12-static\opencv\modules\objdetect\src\hog.cpp:117: error: (-215) checkDetectorSize() in function cv::HOGDescriptor::setSVMDetector
]
at org.opencv.objdetect.HOGDescriptor.setSVMDetector_0(Native Method)
at org.opencv.objdetect.HOGDescriptor.setSVMDetector(HOGDescriptor.java:302)
at feature.extraction.App.main(App.java:86)
我不知道libpng警告是否与它有关。 如果有人有这个想法,这让我发疯了吗?
答案 0 :(得分:1)
我明白了。我做错了几件事
<package>
features
添加到supportvector 首先我创建了一个-rho
。使用2d float array
类中的compute
函数使用图像的功能填充它。用阵列训练SVM。培训结束后,我使用HOGDescriptor
函数获取getDecisionFunction
并将其附加到rho
。