opencv级联分类器未检测到开放式手掌 [英] opencv cascade classifier no open palm detected

问题描述

我有以下代码可以检测img.jpg中的开放手掌：
 
＃！/ usr / bin / env python 
＃ -  *  - 编码：utf-8  -  *  -  
 import cv2 
 import glob 
 
 
 #somehow如果路径没有以\ n结尾它会引发另一个错误
 classifier = cv2.CascadeClassifier（path / to / classifier.xml \ n）
r = classifier.detectMultiScale（cv2.cvtColor（img，cv2.CV_8U））
 print r 
 cv2.rectangle（img，r [0]，r [1]，（0,0,255））
 cv2.imshow（result，img）
 cv2.waitKey（1000）
 classifier.xml是由类似于
 
i =path / to / positives / images的脚本生成的。
 cd $ i 
 #list of positive images 
找到。 -name'*' -  exec identify -format'％i 1 0 0％w％h'\ {\} \; > ls.txt 
 opencv_createsamples -vec $（pwd）/coll.vec -info ls.txt \ 
 -bg negatives / ls.txt -w 24 -h 24 -num 1550 
 mkdir path / to / classifiers＃我们放置分类器的目录
 
 opencv_traincascade -data path / to / classifiers\ 
 -bg negatives / ls.txt -vec coll.vec  - featureType LBP \ 
 -w 24 -h 24 -numPos 1300 -minHitRate 0.99 \ 
 -precalcValBufSize 4096 -precalcIdxBufSize 4096 
但是当我执行python脚本时它给了我以下输出
 
（）
回溯（最近一次调用最后一次）：
文件test1.py，第13行，< module> 
 cv2.rectangle（img，r [0]，r [1]，（0,0,255））
 IndexError：元组索引超出范围
如何以及在哪里做错了？

解决方案

i
#list的正面图像
find。 -name'*' - exec identify -format'％i 1 0 0％w％h'\ {\} \; > ls.txt
opencv_createsamples -vec

（pwd）/coll.vec -info ls.txt \
-bg negatives / ls.txt -w 24 -h 24 -num 1550
mkdir路径/到/分类器＃我们放置分类器的目录

opencv_traincascade -data path / to / classifiers\
-bg negatives /ls.txt-vec coll.vec -featureType LBP \
-w 24 -h 24 -numPos 1300 -minHitRate 0.99 \
-precalcValBufSize 4096 -precalcIdxBufSize 4096
但是当我执行时它为我提供了以下输出的python脚本

（）
Traceback（最近一次调用最后一次）：
文件test1.py，第13行，在< module>中
cv2.rectangle（img，r [0]，r [1]，（0,0,255））
IndexError：元组索引超出范围
如何以及在哪里做错了？

I have the following code which should detect a open palm in img.jpg:

    #!/usr/bin/env python
    # -*- coding: utf-8 -*-
    import cv2
    import glob
    

    #somehow if the path doesn't end in \n it will raise another error
    classifier=cv2.CascadeClassifier("path/to/classifier.xml\n")
    r=classifier.detectMultiScale(cv2.cvtColor(img,cv2.CV_8U))
    print r
    cv2.rectangle(img,r[0],r[1],(0,0,255))
    cv2.imshow("result",img)
    cv2.waitKey(1000)
classifier.xml is generated by a script similar to

    i="path/to/positives/images"
    cd $i
    #list of the positive images
    find . -name '*' -exec identify -format '%i 1 0 0 %w %h' \{\} \; >ls.txt
    opencv_createsamples -vec $(pwd)/coll.vec -info ls.txt \
        -bg negatives/ls.txt -w 24 -h 24 -num 1550
    mkdir path/to/classifiers #the directory where we put the classifiers

    opencv_traincascade -data path/to/classifiers\
        -bg negatives/ls.txt -vec coll.vec -featureType LBP \
        -w 24 -h 24 -numPos 1300 -minHitRate 0.99 \
        -precalcValBufSize 4096 -precalcIdxBufSize 4096
But when I execute the python script it gives me the following output
 
    ()
    Traceback (most recent call last):
      File "test1.py", line 13, in <module>
        cv2.rectangle(img,r[0],r[1],(0,0,255))
    IndexError: tuple index out of range
How and where did I do wrong?

解决方案

i #list of the positive images find . -name '*' -exec identify -format '%i 1 0 0 %w %h' \{\} \; >ls.txt opencv_createsamples -vec

(pwd)/coll.vec -info ls.txt \ -bg negatives/ls.txt -w 24 -h 24 -num 1550 mkdir path/to/classifiers #the directory where we put the classifiers opencv_traincascade -data path/to/classifiers\ -bg negatives/ls.txt -vec coll.vec -featureType LBP \ -w 24 -h 24 -numPos 1300 -minHitRate 0.99 \ -precalcValBufSize 4096 -precalcIdxBufSize 4096 But when I execute the python script it gives me the following output () Traceback (most recent call last): File "test1.py", line 13, in <module> cv2.rectangle(img,r[0],r[1],(0,0,255)) IndexError: tuple index out of range How and where did I do wrong?

这篇关于opencv级联分类器未检测到开放式手掌的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！