将KNN训练从Opencv 3转换为2

Question

我正在阅读使用Opencv训练KNN的教程。代码是为Opencv 3编写的，但我需要在Opencv 2中使用它。最初的训练是：

cv2.ml.KNearest_create().train(npaFlattenedImages, cv2.ml.ROW_SAMPLE, npaClassifications)

我试着使用这个：

cv2.KNearest().train(npaFlattenedImages, cv2.CV_ROW_SAMPLE, npaClassifications)

但错误是：

Unsupported index array data type (it should be 8uC1, 8sC1 or 32sC1) in function cvPreprocessIndexArray

完整的代码在这里：https://github.com/MicrocontrollersAndMore/OpenCV_3_KNN_Character_Recognition_Python/blob/master/TrainAndTest.py

Answer 1

下面是让我在OpenCV 2.4.13上使用full code的一些更改：

60c60
<     kNearest = cv2.ml.KNearest_create()                   # instantiate KNN object
---
>     kNearest = cv2.KNearest()                   # instantiate KNN object
62c62
<     kNearest.train(npaFlattenedImages, cv2.ml.ROW_SAMPLE, npaClassifications)
---
>     kNearest.train(npaFlattenedImages, npaClassifications)
85c85
<     imgContours, npaContours, npaHierarchy = cv2.findContours(imgThreshCopy,             # input image, make sure to use a copy since the function will modify this image in the course of finding contours
---
>     npaContours, npaHierarchy = cv2.findContours(imgThreshCopy,             # input image, make sure to use a copy since the function will modify this image in the course of finding contours
125c125
<         retval, npaResults, neigh_resp, dists = kNearest.findNearest(npaROIResized, k = 1)     # call KNN function find_nearest
---
>         retval, npaResults, neigh_resp, dists = kNearest.find_nearest(npaROIResized, k = 1)     # call KNN function find_nearest

Answer 2

• 与一般的CvStatModel::train()不同，cv2.KNearest.train()没有第二个可选参数int tflag，文档上说：“只支持CV_ROW_SAMPLE数据布局”。因此，尝试使用sampleIdx.

作为下一个参数的函数

• 导致了错误消息(顺便说一下，隐秘的助记符是OpenCV data types

​

修复此问题后的其他错误：

• cv2.findCountours()只返回两个值: anyway).
• KNearest.findNearest() (你不需要第三个值，KNearest.find_nearest().

是→ contours, hierarchy，imgContours

现在的结果是：

​

​

Ulrich Stern already did me a favor to provide a raw diff。