# opencv traincascade haar and lbp my training parameters > Opencv train cascade haar and lbp training Opencv train cascade script parameter examples for Windows. - Canonical URL: https://www.funvisiontutorials.com/blog/opencv-traincascade-haar-lbp-training-parameters/ - Author: Vladimir Kucera - Published: 2016-12-13 - Updated: 2023-09-13 - Topics: Object detection, Installing & building OpenCV Opencv train cascade haar and lbp training Opencv train cascade script parameter examples for Windows. Traincascade utility is easy to use for training HAAR-like and LBP-like cascade for opencv detect multiscale by CascadeClassifier. On this blog, you can find several examples of how to detect something by the HAAR and LBP cascade. ## [Image: Opencv LBP detection] ### Opencv traincascade examples I am using this parameter. You can start where you just ended before. This makes sense. Train for 5 stages and test. If the results with a higher threshold make sense. Train again with the same script and increase numStages. After some time training is much and much slower and test before you run the training for a long time. This is my script.. If you have any opencv\_traincascade.exe -data v -vec vec.vec -bg bg.dat -numPos 300 -numNeg 300 -numStages 10 -numThreads 2 -stageType BOOST -featureType LBP -w 32 -h 64 -minHitRate 0.995 -maxFalseAlarmRate 0.42 -maxDepth 1 -maxWeakCount 100 opencv\_traincascade.exe -data vv -vec vec.vec -bg bg.dat -numPos 540 -numNeg 800 -numStages 8 -numThreads 4 -stageType BOOST -featureType LBP -w 32 -h 64 -minHitRate 0.9995 -maxFalseAlarmRate 0.32 -maxDepth 5 -maxWeakCount 120 opencv\_traincascade.exe -data cascade -vec vec.vec -bg bg.dat -numPos 680 -numNeg 800 -numStages 10 numThreads 4 -stageType BOOST -featureType LBP -w 32 -h 64 -minHitRate 0.999995 -maxFalseAlarmRate 0.42 -maxDepth 10 -maxWeakCount 120 -mode ALL ### opencv traincascade documentation description Later abou this.. Complex staff. Just try example if you have some datasets prepared or know the how to prepare vector\_file and background file for training. Usage: opencv\_traincascade.exe -data <cascade\_dir\_name> -vec <vec\_file\_name> -bg <background\_file\_name> \[-numPos <number\_of\_positive\_samples = 2000>\] \[-numNeg <number\_of\_negative\_samples = 1000>\] \[-numStages <number\_of\_stages = 20>\] \[-precalcValBufSize <precalculated\_vals\_buffer\_size\_in\_Mb = 1024>\] \[-precalcIdxBufSize <precalculated\_idxs\_buffer\_size\_in\_Mb = 1024>\] \[-baseFormatSave\] \[-numThreads <max\_number\_of\_threads = 9>\] \[-acceptanceRatioBreakValue <value> = -1>\] \--cascadeParams-- \[-stageType <BOOST(default)>\] \[-featureType <{HAAR(default), LBP, HOG}>\] \[-w <sampleWidth = 24>\] \[-h <sampleHeight = 24>\] \--boostParams-- \[-bt <{DAB, RAB, LB, GAB(default)}>\] \[-minHitRate <min\_hit\_rate> = 0.995>\] \[-maxFalseAlarmRate <max\_false\_alarm\_rate = 0.5>\] \[-weightTrimRate <weight\_trim\_rate = 0.95>\] \[-maxDepth <max\_depth\_of\_weak\_tree = 1>\] \[-maxWeakCount <max\_weak\_tree\_count = 100>\] \--haarFeatureParams-- \[-mode <BASIC(default) | CORE | ALL \--lbpFeatureParams-- \--HOGFeatureParams--