feature detection using lineair classification

src/features_detection/recognizer.py → src/features_detection/background_remove.py

 import numpy as np
 import cv2
-import argparse
-from detect_shapes import detecting
 
 def getSobel (channel):
 
@@ -36,96 +34,14 @@ def findSignificantContours (img, sobel_8u):
     significant.sort(key=lambda x: x[1])
     return [x[0] for x in significant];
 
-def getColor(colorValues, colorNames, maxValue):
-    for i, item in enumerate(colorValues):
-        if(item == maxValue):
-            return colorNames[i]
-
-def getCroppedImage(image):
-    
-#    im1 = cv2.imread(image)
-#image1 = imread("/path/to/image1")
-#image2 = imread("/path/to/image2")
-#    image3 = im1 - im
-
-    img = image #cv2.imread(image)
-     # Crop from x, y, w, h -> 100, 200, 300, 400
-    # NOTE: its img[y: y + h, x: x + w] and *not* img[x: x + w, y: y + h]
-
-
-    crop_img = img[300:550, 300:550]
-    #cv2.imshow("cropped", crop_img)
-    cv2.imwrite("result.jpg", crop_img)
-    #cv2.waitKey(0)
-#    cv2.imshow('frame',img)
-#    cv2.waitKey(0)
-    return crop_img
-#    gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
-#    ret, thresh = cv2.threshold(gray,0,255,cv2.THRESH_BINARY_INV+cv2.THRESH_OTSU)
-
-#    kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE,(3,3))
-#    fgbg = cv2.createBackgroundSubtractorGMG()
-
-#    fgmask = fgbg.apply(im1)
-#    fgmask = cv2.morphologyEx(fgmask, cv2.MORPH_OPEN, kernel)
-
-#    cv2.imshow('frame',fgmask)
-
-#    cv2.imshow("Image", img)
-#    cv2.waitKey(0)
-
-#    imgray = cv2.cvtColor(im,cv2.COLOR_BGR2GRAY)
-#    ret,thresh = cv2.threshold(imgray,127,255,0)
-#    contours, hierarchy, _ = cv2.findContours(thresh,cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)
-
-#    ctr = np.array(contours).reshape((-1,1,2)).astype(np.int32)
-
-#    cv2.drawContours(im1, [ctr], 0, (0,255,0), -1)
-#    cv2.imwrite("result.jpg", im1)
-#    cv2.waitKey(0)
-
-def getNegative(img):
-    background = cv2.imread('background.jpg')
-    background = background[300:550, 300:550]
-    img = cv2.absdiff(background,img)
-    return img
-
-
-def getFeatures (image):
-
-    size = shape = color = ""
-
-    copy = image
-    
-    img = getCroppedImage(image)
-    img = getNegative(img)
-    
-    # find object
-    detection = detecting(img)
+def segment (img):
     
-    shape = detection[0]
-    
-    if(detection[2] > 7000):
-        size = "BIG"
-    elif(detection[2] > 5000):
-        size = "MEDIUM"
-    else:
-        size = "SMALL"
-
-
-    img = getCroppedImage(copy)
-    
-    
-#    img = cv2.imread(path)
-
-#    getObjectFromImage('background.jpg', path)
-
     blurred = cv2.GaussianBlur(img, (5, 5), 0) # Remove noise
 
     # Edge operator
     sobel = np.max( np.array([ getSobel(blurred[:,:, 0]), getSobel(blurred[:,:, 1]), getSobel(blurred[:,:, 2]) ]), axis=0 )
 
-
+    # Noise reduction trick, from http://sourceforge.net/p/octave/image/ci/default/tree/inst/edge.m#l182
     mean = np.median(sobel)
 
     # Zero any values less than mean. This reduces a lot of noise.
@@ -138,77 +54,22 @@ def getFeatures (image):
 
     # Find contours
     significant = findSignificantContours(img, sobel_8u)
-#    print("significant: ", significant)
-#    print("cnts: ", [shape[1]])
+
     # Mask
     mask = sobel.copy()
     mask[mask > 0] = 0
-    cv2.fillPoly(mask, [detection[1]], 255)
+    cv2.fillPoly(mask, significant, 255)
     # Invert mask
     mask = np.logical_not(mask)
 
     #Finally remove the background
     img[mask] = 0;
-
+    return img
 #    fname = path.split('/')[-1]
-#    cv2.imwrite('output/' + fname, img);
-
-    
-
-#cv2.imshow("Image", img)
-#    cv2.waitKey(0)
-
-    # construct the argument parse and parse the arguments
-    ap = argparse.ArgumentParser()
-    ap.add_argument("-i", "--image", help = "path to the image")
-    args = vars(ap.parse_args())
-
-    # load the image
-    image =  img # cv2.imread(args["image"])
-    
-    
-    
-    
-    # define the list of boundaries
-    # BGR
-    boundaries = [
-	([0, 0, 140], [140, 140, 255]), #red
-	([140, 0, 0], [255, 140, 140]),  #blue
-	([0, 140, 0], [140, 255, 140]), #green
-	([103, 86, 65], [145, 133, 128]) #grey
-    ]
-
-    colorValues = []
-
-    # loop over the boundaries
-    for (lower, upper) in boundaries:
-        # create NumPy arrays from the boundaries
-	lower = np.array(lower, dtype = "uint8")
-	upper = np.array(upper, dtype = "uint8")
-
-	# find the colors within the specified boundaries and apply
-	# the mask
-	mask = cv2.inRange(image, lower, upper)
-        #print(cl.label(image, mask))
-
-        # save the values
-        colorValues.append(np.count_nonzero(mask))
-
-        #print(np.count_nonzero(mask))
-	output = cv2.bitwise_and(image, image, mask = mask)
-        
-	# show the images
-    #cv2.imshow("images", np.hstack([image, output]))
-    #cv2.waitKey(0)
-
-    color = getColor(colorValues, ['RED', 'BLUE', 'GREEN', 'GREY'], max(colorValues))
-
-    return {'shape': shape, 'color': color, 'size': size}
-
-
-
-image = cv2.imread('sphere3.jpg')
-print(getFeatures(image))
-
+#    cv2.imshow('output', img)
+#    cv2.key
+#    cv2.imwrite('output/' + fname, img)
+#    print (path)
 
 
+#segment('original-small.jpg')