爲什麼FindContours在opencv中的功能在圖像中找到兩個輪廓而不是一個輪廓？

Question

輸入圖像 - http://i.imgur.com/sLoqh.png 輸出圖像的繪製的輪廓的凸包 - http://i.imgur.com/AaNJY.png

還就如何得到一個輪廓任何幫助將非常感激？

Answer 1

訣竅來檢索圖像作爲一個輪廓似乎與Canny被處理圖像執行cvFindContours之前。

IplImage* src = cvLoadImage(argv[1], CV_LOAD_IMAGE_GRAYSCALE); 

IplImage* cc_img = cvCreateImage(cvGetSize(src), src->depth, 3); 
cvSetZero(cc_img); 
CvScalar(ext_color); 

CvMemStorage *mem; 
mem = cvCreateMemStorage(0); 
CvSeq *contours = 0; 

// edges returned by Canny might have small gaps between them, which causes some problems during contour detection 
// Simplest way to solve this s to "dilate" the image. 
cvCanny(src, src, 10, 50, 3); 
cvShowImage("Tutorial", src); 
cvWaitKey(0); 

int n = cvFindContours(src, mem, &contours, sizeof(CvContour), CV_RETR_CCOMP, CV_CHAIN_APPROX_SIMPLE, cvPoint(0,0)); 

CvSeq* ptr = 0; 
for (ptr = contours; ptr != NULL; ptr = ptr->h_next) 
{ 
    ext_color = CV_RGB(rand()&255, rand()&255, rand()&255); //randomly coloring different contours 
    cvDrawContours(cc_img, ptr, ext_color, CV_RGB(0,0,0), -1, CV_FILLED, 8, cvPoint(0,0)); 
} 

cvNamedWindow("Tutorial"); 
cvShowImage("Tutorial", cc_img); 
//cvSaveImage("out.png", cc_img); 

cvWaitKey(0); 

輸出：