diff --git a/scripts/contour_centroid.py b/scripts/contour_centroid.py
old mode 100644
new mode 100755
index 4dd7f6b5652ecb127a7621ce889d5f2191cfeaed..d4bdd75127432b33107f8603f717d026c80a8540
--- a/scripts/contour_centroid.py
+++ b/scripts/contour_centroid.py
@@ -4,55 +4,66 @@
from obj_recogkinect import *
import cv2
import numpy as np
+from collections import Counter
from matplotlib import pyplot as plt
-class CentroidContour():
-
- def __init__(self):
-
- self.image = cv2.imread('/home/maitreyee/IMG_20171011_162319075.jpg')
-
- def contourXO(self,contours):
- #import the image from obj_recogkinect.py
- gray = cv2.cvtColor(self.image , cv2.COLOR_BGR2GRAY)
- #Find out threshold to use for finding contours
- ret, thresh = cv2.threshold(gray , 127,255,cv2.THRESH_BINARY)
- #find contours and hierarchy of contours, here we use cv2 parameter to find out all the possible contours
- im2, contours, hierarchy = cv2.findContours(thresh , cv2.RETR_TREE , cv2.CHAIN_APPROX_TC89_L1)
- #draw the contours, it will be in array form
- cv2.drawContours(self.image , contours , -1 , (0, 255, 0) , 5)
- #show the contour with the image
- cv2.imshow('Contours',self.image)
- k = cv2.waitKey(0) & 0xFF
- if k==27:#wait for esc key to destroy all windows
- cv2.destroyAllWindows()
- #here we find out solidity of all the contours and loop through a list of contours to classify X and O into different categories.
- for (i,c) in enumerate(contours):
- area = cv2.contourArea(c)
- (x, y, w, h) = cv2.boundingRect(c)
- hull = cv2.convexHull(c)
- hullArea = cv2.contourArea(hull)
- solidity = float(area) / hullArea
- char = '?'
- if solidity > 0.9:
- char = "O"
- elif solidity > 0.5:
- char = "X"
- if char != "?":
- cv2.drawContours(self.image ,[c] ,-1 , (0,255,0) , 5)
- cv2.putText(self.image , char , (x, y - 10) , cv2.FONT_HERSHEY_COMPLEX, 1.25, (0, 255, 0), 5)
- return contours[0]
- #For the available contours we find their entre points and print those centre points which will be in an array format
- def detectCentroids(self):
- centres = []
- cnts = self.contourXO()
- ctr = np.array(cnts).reshape((-1, 1, 2)).astype(np.int32)
- for c in cnts:
- m = cv2.moments(c)
- cx = int(m["m10"] / m["m00"])
- cy = int(m["m01"] / m["m00"])
- cv2.drawContours(self.image , [ctr] , -1 , (0, 255, 0) , 2)
- cv2.circle(self.image , (cx, cy) , 7 , (255, 255, 255) , -1)
- cv2.putText(self.image, "center", (cx - 20, cy - 20) , cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 255, 255), 2)
- cv2.imshow("Image", self.image)
- cv2.waitKey(0)
+
+img1 = cv2.imread('/home/maitreyee/Desktop/board.jpg')
+img = cv2.resize(img1, (640, 480), interpolation=cv2.INTER_CUBIC)
+gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
+cimg = cv2.cvtColor(gray, cv2.COLOR_GRAY2BGR)
+hsv1 = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
+blur = cv2.GaussianBlur(gray, (17, 17), 0)
+(ret, thresh) = cv2.threshold(blur, 100, 250, cv2.THRESH_BINARY)
+(im2, contours, hierarchy) = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
+ratio = img.shape[0] / float(img.shape[0])
+circles = cv2.HoughCircles(gray, cv2.HOUGH_GRADIENT, 1, 20,
+ param1=620, param2=10, minRadius=39, maxRadius=42)
+circles = np.uint16(np.around(circles))
+
+for c in contours:
+ shape = "unidentified"
+ peri = cv2.arcLength(c, True)
+ approx = cv2.approxPolyDP(c, 0.04 * peri, True)
+ # if the shape has 4 vertices, it is either a square or
+ # a rectangle
+ if len(approx) == 4:
+ # compute the bounding box of the contour and use the
+ # bounding box to compute the aspect ratio
+
+ (x, y, w, h) = cv2.boundingRect(approx)
+ ar = w / float(h)
+
+ M = cv2.moments(c)
+ cX = int((M["m10"] / M["m00"]) * ratio)
+ cY = int((M["m01"] / M["m00"]) * ratio)
+ mean = cv2.mean((cX, cY), mask=None)
+ c = c.astype("float")
+ c *= ratio
+ c = c.astype("int")
+ cv2.drawContours(img, [c], -1, (0, 255, 0), 2)
+ cv2.circle(img, (cX, cY), 7, (255, 255, 255), -1)
+
+ # a square will have an aspect ratio that is approximately
+ # equal to one, otherwise, the shape is a rectangle
+ shape = "square" if ar >= 0.95 and ar <= 1.05 else "rectangle"
+ for i in circles[0, :]:
+ # draw the center of the circle§
+ cv2.circle(cimg, (i[0], i[1]), i[2], (0, 255, 0), 2)
+ cv2.circle(cimg, (i[0], i[1]), 2, (0, 0, 255), 3)
+
+ lower = np.array([1, 25, 25])
+ upper = np.array([10, 255, 255])
+ mask = cv2.inRange(hsv1, lower, upper)
+ output = cv2.bitwise_and(img, img, mask=mask)
+
+ # Threshold the HSV image to get only red colors
+
+ print mean
+ cv2.imshow(np.hstack([hsv1,output]))
+ cv2.imshow('contours',img)
+ cv2.waitKey(0)
+ cv2.destroyAllWindows()
+plt.imshow(cimg)
+plt.show()
+
diff --git a/scripts/obj_recogkinect.py b/scripts/obj_recogkinect.py
index 587aafd7028773f6089285b07c47f4cb7f9bd907..7e1615b1e725a2292dd3f9581cfe0cdd8e306662 100755
--- a/scripts/obj_recogkinect.py
+++ b/scripts/obj_recogkinect.py
@@ -8,7 +8,7 @@ import cv2
#from std_msgs.msg import String
from sensor_msgs.msg import Image
#ROS Image message to OpenCV2 image converter
-import cv_bridge import CvBridge, CvBridgeError
+from cv_bridge import CvBridge, CvBridgeError
import sys