Determine the age of the tree by the number of circles
Hello! Can i determine the age of the tree by the number of circles?
Hello! Can i determine the age of the tree by the number of circles?
Merry Christmas. Here's your present... The ring count that I get is 70. Make sure to mark my answer as correct, if you find that it works for you. :)
Here is a cropped version of your input image, which contains only the necessary data:
Here is the C++ code to count the rings:
#include <opencv2/opencv.hpp>
using namespace cv;
#pragma comment(lib, "opencv_world340.lib")
#include <iostream>
using namespace std;
int main(void)
{
Mat frame = imread("rings_slice.png");
if (frame.empty())
{
cout << "Error loading image file" << endl;
return -1;
}
cvtColor(frame, frame, CV_BGR2GRAY);
adaptiveThreshold(frame, frame, 255, ADAPTIVE_THRESH_GAUSSIAN_C, THRESH_BINARY, 11, 2);
// Use centre column
int column_index = frame.cols / 2;
int ring_count = 0;
// Start with the second row
for (int i = 1; i < frame.rows; i++)
{
// If this pixel is white and the previous pixel is black
if (255 == frame.at<unsigned char>(i, column_index) && 0 == frame.at<unsigned char>(i - 1, column_index))
ring_count++;
}
cout << ring_count << endl;
return 1;
}
Alternatively, here is the Python code:
import numpy as np
import cv2
import sys
frame = cv2.imread("rings_slice.png")
if frame is None:
print('Error loading image')
exit()
frame = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
frame = cv2.adaptiveThreshold(frame, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 11, 2)
rows = frame.shape[0]
cols = frame.shape[1]
# Use centre column
column_index = cols / 2
ring_count = 0;
# Start with the second row
for i in range(1, rows):
# If this pixel is white and the previous pixel is black
if 255 == frame[i, column_index] and 0 == frame[i - 1, column_index]:
ring_count += 1;
print ring_count
I wrote a C++ code that scans for rings in both horizontal and vertical mode... the code selects the highest ring count:
https://github.com/sjhalayka/opencv_r...
Making the same changes to the Python code should be fairly easy.
Anyway, the code is picking up too many rings. You'll have to experiment with the threshold()
/adaptiveThreshold()
parameters for each wood type, I'd think. Have fun!
Asked: 2017-12-25 04:30:31 -0600
Seen: 1,531 times
Last updated: Dec 25 '17
How to reduce false positives for face detection
OpenCV DescriptorMatcher matches
Record/Store constant refreshing coordinates points into notepad
Conversion between IplImage and MxArray
How can solvePnPRansac be used with double values?
Combine SIFT with other method for object recognition
OpenCV Paths Headaches in Eclipse