gocv: how to cut out an image from blue background using opencv - opencv

I started playing with gocv. I'm trying to figure out a simple thing: how to cut out an object from an image which has a background of certain colour. In this case the object is pizza and background colour is blue.
I'm using InRange function (inRange in OpenCV) to define the upper and lower threshold for blue colour to create a mask and then CopyToWithMask function (copyTo in OpenCV) to apply the mask on the original image. I expect the result to be the blue background with the pizza cut out of it.
The code is very simple:
package main
import (
"fmt"
"os"
"gocv.io/x/gocv"
)
func main() {
imgPath := "pizza.png"
// read in an image from filesystem
img := gocv.IMRead(imgPath, gocv.IMReadColor)
if img.Empty() {
fmt.Printf("Could not read image %s\n", imgPath)
os.Exit(1)
}
// Create a copy of an image
hsvImg := img.Clone()
// Convert BGR to HSV image
gocv.CvtColor(img, hsvImg, gocv.ColorBGRToHSV)
lowerBound := gocv.NewMatFromScalar(gocv.NewScalar(110.0, 100.0, 100.0, 0.0), gocv.MatTypeCV8U)
upperBound := gocv.NewMatFromScalar(gocv.NewScalar(130.0, 255.0, 255.0, 0.0), gocv.MatTypeCV8U)
// Blue mask
mask := gocv.NewMat()
gocv.InRange(hsvImg, lowerBound, upperBound, mask)
// maskedImg: output array that has the same size and type as the input arrays.
maskedImg := gocv.NewMatWithSize(hsvImg.Rows(), hsvImg.Cols(), gocv.MatTypeCV8U)
hsvImg.CopyToWithMask(maskedImg, mask)
// save the masked image
newImg := gocv.NewMat()
// Convert back to BGR before saving
gocv.CvtColor(maskedImg, newImg, gocv.ColorHSVToBGR)
gocv.IMWrite("no_pizza.jpeg", newImg)
}
However the resulting image is basically almost completely black except for a slight hint of a pizza edge:
As for the chosen upper and lower bound of blue colours, I followed the guide mentioned in the official documentation:
blue = np.uint8([[[255, 0, 0]]])
hsv_blue = cv2.cvtColor(blue, cv2.COLOR_BGR2HSV)
print(hsv_blue)
[[[120 255 255]]]
Now you take [H-10, 100,100] and [H+10, 255, 255] as lower bound and
upper bound respectively.
I'm sure I'm missing something fundamental, but can't figure out what it is.

So I spent quite some time on this to figure out what I'm missing and finally found the answer to my question in case anyone is interested. It's now clearer to me now why this question hasn't been answered as the solution to it is rather crazy due to gocv API.
Here is the code that I had to write to get the result I'm after:
package main
import (
"fmt"
"os"
"path/filepath"
"gocv.io/x/gocv"
)
func main() {
// read image
pizzaPath := filepath.Join("pizza.png")
pizza := gocv.IMRead(pizzaPath, gocv.IMReadColor)
if pizza.Empty() {
fmt.Printf("Failed to read image: %s\n", pizzaPath)
os.Exit(1)
}
// Convert BGR to HSV image (dont modify the original)
hsvPizza := gocv.NewMat()
gocv.CvtColor(pizza, &hsvPizza, gocv.ColorBGRToHSV)
pizzaChannels, pizzaRows, pizzaCols := hsvPizza.Channels(), hsvPizza.Rows(), hsvPizza.Cols()
// define HSV color upper and lower bound ranges
lower := gocv.NewMatFromScalar(gocv.NewScalar(110.0, 50.0, 50.0, 0.0), gocv.MatTypeCV8UC3)
upper := gocv.NewMatFromScalar(gocv.NewScalar(130.0, 255.0, 255.0, 0.0), gocv.MatTypeCV8UC3)
// split HSV lower bounds into H, S, V channels
lowerChans := gocv.Split(lower)
lowerMask := gocv.NewMatWithSize(pizzaRows, pizzaCols, gocv.MatTypeCV8UC3)
lowerMaskChans := gocv.Split(lowerMask)
// split HSV lower bounds into H, S, V channels
upperChans := gocv.Split(upper)
upperMask := gocv.NewMatWithSize(pizzaRows, pizzaCols, gocv.MatTypeCV8UC3)
upperMaskChans := gocv.Split(upperMask)
// copy HSV values to upper and lower masks
for c := 0; c < pizzaChannels; c++ {
for i := 0; i < pizzaRows; i++ {
for j := 0; j < pizzaCols; j++ {
lowerMaskChans[c].SetUCharAt(i, j, lowerChans[c].GetUCharAt(0, 0))
upperMaskChans[c].SetUCharAt(i, j, upperChans[c].GetUCharAt(0, 0))
}
}
}
gocv.Merge(lowerMaskChans, &lowerMask)
gocv.Merge(upperMaskChans, &upperMask)
// global mask
mask := gocv.NewMat()
gocv.InRange(hsvPizza, lowerMask, upperMask, &mask)
// cut out pizza mask
pizzaMask := gocv.NewMat()
gocv.Merge([]gocv.Mat{mask, mask, mask}, &pizzaMask)
// cut out the pizza and convert back to BGR
gocv.BitwiseAnd(hsvPizza, pizzaMask, &hsvPizza)
gocv.CvtColor(hsvPizza, &hsvPizza, gocv.ColorHSVToBGR)
// write image to filesystem
outPizza := "no_pizza.jpeg"
if ok := gocv.IMWrite(outPizza, hsvPizza); !ok {
fmt.Printf("Failed to write image: %s\n", outPizza)
os.Exit(1)
}
// write pizza mask to filesystem
outPizzaMask := "no_pizza_mask.jpeg"
if ok := gocv.IMWrite(outPizzaMask, mask); !ok {
fmt.Printf("Failed to write image: %s\n", outPizza)
os.Exit(1)
}
}
This code produces the result I was after:
I'm also going to add another picture that shows the im
Now, let's get to code. gocv API function InRange() does not accept Scalar like OpenCV does so you have to do all that crazy image channel splitting and merging dance since you need to pass in Mats as lower and upper bounds to InRange(); these Mat masks have to have the exact number of channels as the image on which you run InRange().
This brings up another important point: when allocating the Scalars in gocv for this task, I originally used gocv.MatTypeCV8U type which represents single channel color - not enough for HSV image which has three channels -- this is fixed by using gocv.MatTypeCV8UC3 type.
If I it were possible pass in gocv.Scalars into gocv.InRange() a lot of the boiler plate code would disappear; so would all the unnecessary gocv.NewMat() allocations for splitting and reassembling the channels which are required to create lower and upper bounds channels.

inRange with the given range runs perfectly for me. I'm not familiar with Go, but here's my python code:
import numpy as py
import cv2
img = cv2.imread("pizza.png")
hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
mask = cv2.inRange(hsv, (110, 100, 100), (130, 255, 255))
inv_mask = cv2.bitwise_not(mask)
pizza = cv2.bitwise_and(img, img, mask=inv_mask)
cv2.imshow("img", img)
cv2.imshow("mask", mask)
cv2.imshow("pizza", pizza)
cv2.imshow("inv mask", inv_mask)
cv2.waitKey()
A few of notes here:
inRange returns the blue background so we need to invert it to reveal the object's mask (if you need the object).
You don't need to apply mask on hsvImg and convert to BGR, you can apply mask directly on the original image (which is BGR already).
Python does not have CopyToWithMask so I use the equivalent bitwise_and. You may check this function in Go, but I suspect there would be no differences.

Here is what I did with Python because I don't know Go...
Let me explain first.
(1) Image has been turned to gray.
(2) Applied Canny Edge
(3 - 4) Created kernel and used it to do Dilate and Close operations
(5) Found contours
(6) Created and applied mask
(7) Cropped and saved the region
Here is the code:
import cv2
import numpy as np
image = cv2.imread("image.png")
copy = image.copy()
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
cv2.imshow('Gray', gray)
cv2.waitKey(0)
edged = cv2.Canny(gray, 10, 250)
cv2.imshow('Edged', edged)
cv2.waitKey(0)
kernel = np.ones((5, 5), np.uint8)
dilation = cv2.dilate(edged, kernel, iterations=1)
cv2.imshow('Dilation', dilation)
cv2.waitKey(0)
closing = cv2.morphologyEx(dilation, cv2.MORPH_CLOSE, kernel)
cv2.imshow('Closing', closing)
cv2.waitKey(0)
# if using OpenCV 4, remove image variable from below
image, cnts, hiers = cv2.findContours(closing, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cont = cv2.drawContours(copy, cnts, -1, (0, 0, 0), 1, cv2.LINE_AA)
cv2.imshow('Contours', cont)
cv2.waitKey(0)
mask = np.zeros(cont.shape[:2], dtype="uint8") * 255
# Draw the contours on the mask
cv2.drawContours(mask, cnts, -1, (255, 255, 255), -1)
# remove the contours from the image and show the resulting images
img = cv2.bitwise_and(cont, cont, mask=mask)
cv2.imshow("Mask", img)
cv2.waitKey(0)
for c in cnts:
x, y, w, h = cv2.boundingRect(c)
if w > 50 and h > 130:
new_img = img[y:y + h, x:x + w]
cv2.imwrite('Cropped.png', new_img)
cv2.imshow("Cropped", new_img)
cv2.waitKey(0)
Hope will help more than one user.

Related

Adjusting pytesseract parameters

Note: I am migrating this question from Data Science Stack Exchange, where it received little exposure.
I am trying to implement an OCR solution to identify the numbers read from the picture of a screen.
I am adapting this pyimagesearch tutorial to my problem.
Because I am dealing with a dark background, I first invert the image, before converting it to grayscale and thresholding it:
inverted_cropped_image = cv2.bitwise_not(cropped_image)
gray = get_grayscale(inverted_cropped_image)
thresholded_image = cv2.threshold(gray, 100, 255, cv2.THRESH_BINARY)[1]
Then I call pytesseract's image_to_data function to output a dictionary containing the different text regions and their confidence intervals:
from pytesseract import Output
results = pytesseract.image_to_data(thresholded_image, output_type=Output.DICT)
Finally I iterate over results and plot them when their confidence exceeds a user defined threshold (70%). What bothers me, is that my script identifies everything in the image except the number that I would like to recognize (1227.938).
My first guess is that the image_to_data parameters are not set properly.
Checking this website, I selected a page segmentation mode (psm) of 11 (sparse text) and tried whitelisting numbers only (tessedit_char_whitelist=0123456789m.'):
results = pytesseract.image_to_data(thresholded_image, config='--psm 11 --oem 3 -c tessedit_char_whitelist=0123456789m.', output_type=Output.DICT)
Alas, this is even worse, and the script now identifies nothing at all!
Do you have any suggestion? Am I missing something obvious here?
EDIT #1:
At Ann Zen's request, here's the code used to obtain the first image:
import imutils
import cv2
import matplotlib.pyplot as plt
import numpy as np
import pytesseract
from pytesseract import Output
def get_grayscale(image):
return cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
filename = "IMAGE.JPG"
cropped_image = cv2.imread(filename)
inverted_cropped_image = cv2.bitwise_not(cropped_image)
gray = get_grayscale(inverted_cropped_image)
thresholded_image = cv2.threshold(gray, 100, 255, cv2.THRESH_BINARY)[1]
results = pytesseract.image_to_data(thresholded_image, config='--psm 11 --oem 3 -c tessedit_char_whitelist=0123456789m.', output_type=Output.DICT)
color = (255, 255, 255)
for i in range(0, len(results["text"])):
x = results["left"][i]
y = results["top"][i]
w = results["width"][i]
h = results["height"][i]
text = results["text"][i]
conf = int(results["conf"][i])
print("Confidence: {}".format(conf))
if conf > 70:
print("Confidence: {}".format(conf))
print("Text: {}".format(text))
print("")
text = "".join([c if ord(c) < 128 else "" for c in text]).strip()
cv2.rectangle(cropped_image, (x, y), (x + w, y + h), color, 2)
cv2.putText(cropped_image, text, (x, y - 10), cv2.FONT_HERSHEY_SIMPLEX,1.2, color, 3)
cv2.imshow('Image', cropped_image)
cv2.waitKey(0)
EDIT #2:
Rarely have I spent reputation points so well! All three replies posted so far helped me refine my algorithm.
First, I wrote a Tkinter program allowing me to manually crop the image around the number of interest (modifying the one found in this SO post)
Then I used Ann Zen's idea of narrowing down the search area around the fractional part. I am using her nifty process function to prepare my grayscale image for contour extraction: contours, _ = cv2.findContours(process(img_gray), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE). I am using RETR_EXTERNAL to avoid dealing with overlapping bounding rectangles.
I then sorted my contours from left to right. Bounding rectangles exceeding a user-defined threshold are associated with the integral part (white rectangles); otherwise they are associated with the fractional part (black rectangles).
I then extracted the characters using Esraa's approach i.e. applying a Gaussian blur prior to calling Tesseract. I used a much larger kernel (15x15 vs 3x3) to achieve this.
I am not out of the woods yet, but hopefully I will get better results by using Ahx's adaptive thresholding.
The Concept
As you have probably heard, pytesseract is not good at detecting text of different sizes on the same line as one piece of text. In your case, you want to detect the 1227.938, where the 1227 is much larger than the .938.
One way to go about solving this is to have the program estimate where the .938 is, and enlarge that part of the image. After that, pytesseract will have no problem in returning the text.
The Code
import cv2
import numpy as np
import pytesseract
def process(img):
img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
_, thresh = cv2.threshold(img_gray, 200, 255, cv2.THRESH_BINARY)
img_canny = cv2.Canny(thresh, 100, 100)
kernel = np.ones((3, 3))
img_dilate = cv2.dilate(img_canny, kernel, iterations=2)
return cv2.erode(img_dilate, kernel, iterations=2)
img = cv2.imread("image.png")
img_copy = img.copy()
hh = 50
contours, _ = cv2.findContours(process(img), cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
for cnt in contours:
if 20 * hh < cv2.contourArea(cnt) < 30 * hh:
x, y, w, h = cv2.boundingRect(cnt)
ww = int(hh / h * w)
src_seg = img[y: y + h, x: x + w]
dst_seg = img_copy[y: y + hh, x: x + ww]
h_seg, w_seg = dst_seg.shape[:2]
dst_seg[:] = cv2.resize(src_seg, (ww, hh))[:h_seg, :w_seg]
gray = cv2.cvtColor(img_copy, cv2.COLOR_BGR2GRAY)
_, thresh = cv2.threshold(gray, 180, 255, cv2.THRESH_BINARY)
results = pytesseract.image_to_data(thresh)
for b in map(str.split, results.splitlines()[1:]):
if len(b) == 12:
x, y, w, h = map(int, b[6: 10])
cv2.putText(img, b[11], (x, y + h + 15), cv2.FONT_HERSHEY_COMPLEX, 0.6, 0)
cv2.imshow("Result", img)
cv2.waitKey(0)
The Output
Here is the input image:
And here is the output image:
As you have said in your post, the only part you need the the decimal 1227.938. If you want to filter out the rest of the detected text, you can try tweaking some parameters. For example, replacing the 180 from _, thresh = cv2.threshold(gray, 180, 255, cv2.THRESH_BINARY) with 230 will result in the output image:
The Explanation
Import the necessary libraries:
import cv2
import numpy as np
import pytesseract
Define a function, process(), that will take in an image array, and return a binary image array that is the processed version of the image that will allow proper contour detection:
def process(img):
img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
_, thresh = cv2.threshold(img_gray, 200, 255, cv2.THRESH_BINARY)
img_canny = cv2.Canny(thresh, 100, 100)
kernel = np.ones((3, 3))
img_dilate = cv2.dilate(img_canny, kernel, iterations=2)
return cv2.erode(img_dilate, kernel, iterations=2)
I'm sure that you don't have to do this, but due to a problem in my environment, I have to add pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe' before I can call the pytesseract.image_to_data() method, or it throws an error:
pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'
Read in the original image, make a copy of it, and define the rough height of the large part of the decimal:
img = cv2.imread("image.png")
img_copy = img.copy()
hh = 50
Detect the contours of the processed version of the image, and add a filter that roughly filters out the contours so that the small text remains:
contours, _ = cv2.findContours(process(img), cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
for cnt in contours:
if 20 * hh < cv2.contourArea(cnt) < 30 * hh:
Define the bounding box of each contour that didn't get filtered out, and use the properties to enlarge those parts of the image to the height defined for the large text (making sure to also scale the width accordingly):
x, y, w, h = cv2.boundingRect(cnt)
ww = int(hh / h * w)
src_seg = img[y: y + h, x: x + w]
dst_seg = img_copy[y: y + hh, x: x + ww]
h_seg, w_seg = dst_seg.shape[:2]
dst_seg[:] = cv2.resize(src_seg, (ww, hh))[:h_seg, :w_seg]
Finally, we can use the pytesseract.image_to_data() method to detect the text. Of course, we'll need to threshold the image again:
gray = cv2.cvtColor(img_copy, cv2.COLOR_BGR2GRAY)
_, thresh = cv2.threshold(gray, 180, 255, cv2.THRESH_BINARY)
results = pytesseract.image_to_data(thresh)
for b in map(str.split, results.splitlines()[1:]):
if len(b) == 12:
x, y, w, h = map(int, b[6: 10])
cv2.putText(img, b[11], (x, y + h + 15), cv2.FONT_HERSHEY_COMPLEX, 0.6, 0)
cv2.imshow("Result", img)
cv2.waitKey(0)
I have been working with Tesseract for quite some time, so let me clarify something for you. Tesseract is extremely helpful if you're trying to recognize text in documents more than any other computer vision projects. It usually needs a binarized image to get a good output. Therefore, you will always need some image pre-processing.
However, after several trials in the past with all page segmentation modes, I realized that it fails when font size differs on the same line without having a space. Sometimes PSM 6 is helpful if the difference is low, but in your condition, you may try an alternative. If you don't care about the decimals, you may try the following solution:
img = cv2.imread(r'E:\Downloads\Iwzrg.png')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
img_blur = cv2.GaussianBlur(gray, (3,3),0)
_,thresh = cv2.threshold(img_blur,200,255,cv2.THRESH_BINARY_INV)
# If using a fixed camera
new_img = thresh[0:100, 80:320]
text = pytesseract.image_to_string(new_img, lang='eng', config='--psm 6 --oem 3 -c tessedit_char_whitelist=0123456789')
OUTPUT: 1227
I would like to recommend applying another image processing method.
Because I am dealing with a dark background, I first invert the image, before converting it to grayscale and thresholding it:
You applied global thresholding and couldn't achieve the desired result.
Then you can apply either adaptive-thresholding or inRange
For the given image, if we apply the inRange threshold:
To be able to recognize the image as accurately as possible we can add a border to the top of the image and resize the image (Optional)
In the OCR section, check if the detected region contains a digit
if text.isdigit():
Then display on the image:
The result is nearly the desired value. Now you can try with the other suggested methods to find the exact value.
The problem is .938 recognized as 235, maybe resizing using different values might improve the result.
Code:
from cv2 import imread, cvtColor, COLOR_BGR2HSV as HSV, inRange, getStructuringElement, resize
from cv2 import imshow, waitKey, MORPH_RECT, dilate, bitwise_and, rectangle, putText
from cv2 import copyMakeBorder as addBorder, BORDER_CONSTANT as CONSTANT, FONT_HERSHEY_SIMPLEX
from numpy import array
from pytesseract import image_to_data, Output
bgr = imread("Iwzrg.png")
resized = resize(bgr, (800, 600), fx=0.75, fy=0.75)
bordered = addBorder(resized, 200, 0, 0, 0, CONSTANT, value=0)
hsv = cvtColor(bordered, HSV)
mask = inRange(hsv, array([0, 0, 250]), array([179, 255, 255]))
kernel = getStructuringElement(MORPH_RECT, (50, 30))
dilated = dilate(mask, kernel, iterations=1)
thresh = 255 - bitwise_and(dilated, mask)
data = image_to_data(thresh, output_type=Output.DICT)
for i in range(0, len(data["text"])):
x = data["left"][i]
y = data["top"][i]
w = data["width"][i]
h = data["height"][i]
text = data["text"][i]
if text.isdigit():
print("Text: {}".format(text))
print("")
text = "".join([c if ord(c) < 128 else "" for c in text]).strip()
rectangle(thresh, (x, y), (x + w, y + h), (0, 255, 0), 2)
putText(thresh, text, (x, y - 10), FONT_HERSHEY_SIMPLEX, 1.2, (0, 0, 255), 3)
imshow("", thresh)
waitKey(0)

How can I filter out points of an edge-detected circle that are extremely noisy?

I am working on detecting the center and radius of a circular aperture that is illuminated by a laser beam. The algorithm will be fed images from a system that I have no physical control over (i.e. dimming the source or adjusting the laser position.) I need to do this with C++, and have chosen to use openCV.
In some regions the edge of the aperture is well defined, but in others it is very noisy. I currently am trying to isolate the "good" points to do a RANSAC fit, but I have taken other steps along the way. Below are two original images for reference:
I first began by trying to do a Hough fit. I performed a median blur to remove the salt and pepper noise, then a Gaussian blur, and then fed the image to the HoughCircle function in openCV, with sliders controlling the Hough parameters 1 and 2 defined here. The results were disastrous:
I then decided to try to process the image some more before sending it to the HoughCircle. I started with the original image, median blurred, Gaussian blurred, thresholded, dilated, did a Canny edge detection, and then fed the Canny image to the function.
I was eventually able to get a reasonable estimate of my circle, but it was about the 15th circle to show up when manually decreasing the Hough parameters. I manually drew the purple outline, with the green circles representing Hough outputs that were near my manual estimate. The below images are:
Canny output without dilation
Canny output with dilation
Hough output of the dilated Canny image drawn on the original image.
As you can see, the number of invalid circles vastly outnumbers the correct circle, and I'm not quite sure how to isolate the good circles given that the Hough transform returns so many other invalid circles with parameters that are more strict.
I currently have some code I implemented that works OK for all of the test images I was given, but the code is a convoluted mess with many tunable parameters that seems very fragile. The driving logic behind what I did was from noticing that regions of the aperture edges that were well-illuminated by the laser were relatively constant across several threshold levels (image shown below).
I did edge detection at two threshold levels and stored points that overlapped in both images. Currently there is also some inaccuracy with the result because the aperture edge does still shift slightly with the different threshold levels. I can post the very long code for this if necessary, but the pseudo-code behind it is:
1. Perform a median blur, followed by a Gaussian blur. Kernels are 9x9.
2. Threshold the image until 35% of the image is white. (~intensities > 30)
3. Take the Canny edges of this thresholded image and store (Canny1)
4. Take the original image, perform the same median and Gaussian blurs, but threshold with a 50% larger value, giving a smaller spot (~intensities > 45)
5. Perform the "Closing" morphology operation to further erode the spot and remove any smaller contours.
6. Perform another Canny to get the edges, and store this image (Canny2)
7. Blur both the Canny images with a 7x7 Gaussian blur.
8. Take the regions where the two Canny images overlap and say that these points are likely to be good points.
9. Do a RANSAC circle fit with these points.
I've noticed that there are regions of the edge detected circle that are pretty distinguishable by the human eye as being part of the best circle. Is there a way to isolate these regions for a RANSAC fit?
Code for Hough:
int houghParam1 = 100;
int houghParam2 = 100;
int dp = 10; //divided by 10 later
int x=616;
int y=444;
int radius = 398;
int iterations = 0;
int main()
{
namedWindow("Circled Orig");
namedWindow("Processed", 1);
namedWindow("Circles");
namedWindow("Parameters");
namedWindow("Canny");
createTrackbar("Param1", "Parameters", &houghParam1, 200);
createTrackbar("Param2", "Parameters", &houghParam2, 200);
createTrackbar("dp", "Parameters", &dp, 20);
createTrackbar("x", "Parameters", &x, 1200);
createTrackbar("y", "Parameters", &y, 1200);
createTrackbar("radius", "Parameters", &radius, 900);
createTrackbar("dilate #", "Parameters", &iterations, 20);
std::string directory = "Secret";
std::string suffix = ".pgm";
Mat processedImage;
Mat origImg;
for (int fileCounter = 2; fileCounter < 3; fileCounter++) //1, 12
{
std::string numString = std::to_string(static_cast<long long>(fileCounter));
std::string imageFile = directory + numString + suffix;
testImage = imread(imageFile);
Mat bwImage;
cvtColor(testImage, bwImage, CV_BGR2GRAY);
GaussianBlur(bwImage, processedImage, Size(9, 9), 9);
threshold(processedImage, processedImage, 25, 255, THRESH_BINARY); //THRESH_OTSU
int numberContours = -1;
int iterations = 1;
imshow("Processed", processedImage);
}
vector<Vec3f> circles;
Mat element = getStructuringElement(MORPH_ELLIPSE, Size(5, 5));
float dp2 = dp;
while (true)
{
float dp2 = dp;
Mat circleImage = processedImage.clone();
origImg = testImage.clone();
if (iterations > 0) dilate(circleImage, circleImage, element, Point(-1, -1), iterations);
Mat cannyImage;
Canny(circleImage, cannyImage, 100, 20);
imshow("Canny", cannyImage);
HoughCircles(circleImage, circles, HOUGH_GRADIENT, dp2/10, 5, houghParam1, houghParam2, 300, 5000);
cvtColor(circleImage, circleImage, CV_GRAY2BGR);
for (size_t i = 0; i < circles.size(); i++)
{
Scalar color = Scalar(0, 0, 255);
Point center2(cvRound(circles[i][0]), cvRound(circles[i][1]));
int radius2 = cvRound(circles[i][2]);
if (abs(center2.x - x) < 10 && abs((center2.y - y) < 10) && abs(radius - radius2) < 20) color = Scalar(0, 255, 0);
circle(circleImage, center2, 3, color, -1, 8, 0);
circle(circleImage, center2, radius2, color, 3, 8, 0);
circle(origImg, center2, 3, color, -1, 8, 0);
circle(origImg, center2, radius2,color, 3, 8, 0);
}
//Manual circles
circle(circleImage, Point(x, y), 3, Scalar(128, 0, 128), -1, 8, 0);
circle(circleImage, Point(x, y), radius, Scalar(128, 0, 128), 3, 8, 0);
circle(origImg, Point(x, y), 3, Scalar(128, 0, 128), -1, 8, 0);
circle(origImg, Point(x, y), radius, Scalar(128, 0, 128), 3, 8, 0);
imshow("Circles", circleImage);
imshow("Circled Orig", origImg);
int x = waitKey(50);
}
Mat drawnImage;
cvtColor(processedImage, drawnImage, CV_GRAY2BGR);
return 1;
}
Thanks #jalconvolvon - this is an interesting problem. Here's my result:
What I find important on and on is using dynamic parameter adjustment when prototyping, thus I include the function I used to tune Canny detection. The code also uses this answer for the Ransac part.
import cv2
import numpy as np
import auxcv as aux
from skimage import measure, draw
def empty_function(*arg):
pass
# tune canny edge detection. accept with pressing "C"
def CannyTrackbar(img, win_name):
trackbar_name = win_name + "Trackbar"
cv2.namedWindow(win_name)
cv2.resizeWindow(win_name, 500,100)
cv2.createTrackbar("canny_th1", win_name, 0, 255, empty_function)
cv2.createTrackbar("canny_th2", win_name, 0, 255, empty_function)
cv2.createTrackbar("blur_size", win_name, 0, 255, empty_function)
cv2.createTrackbar("blur_amp", win_name, 0, 255, empty_function)
while True:
trackbar_pos1 = cv2.getTrackbarPos("canny_th1", win_name)
trackbar_pos2 = cv2.getTrackbarPos("canny_th2", win_name)
trackbar_pos3 = cv2.getTrackbarPos("blur_size", win_name)
trackbar_pos4 = cv2.getTrackbarPos("blur_amp", win_name)
img_blurred = cv2.GaussianBlur(img.copy(), (trackbar_pos3 * 2 + 1, trackbar_pos3 * 2 + 1), trackbar_pos4)
canny = cv2.Canny(img_blurred, trackbar_pos1, trackbar_pos2)
cv2.imshow(win_name, canny)
key = cv2.waitKey(1) & 0xFF
if key == ord("c"):
break
cv2.destroyAllWindows()
return canny
img = cv2.imread("sphere.jpg")
#resize for convenience
img = cv2.resize(img, None, fx = 0.2, fy = 0.2)
#closing
kernel = np.ones((11,11), np.uint8)
img = cv2.morphologyEx(img, cv2.MORPH_CLOSE, kernel)
#sharpening
kernel = np.array([[-1,-1,-1], [-1,9,-1], [-1,-1,-1]])
img = cv2.filter2D(img, -1, kernel)
#test if you use different scale img than 0.2 of the original that I used
#remember that the actual kernel size for GaussianBlur is trackbar_pos3*2+1
#you want to get as full circle as possible here
#canny = CannyTrackbar(img, "canny_trakbar")
#additional blurring to reduce the offset toward brighter region
img_blurred = cv2.GaussianBlur(img.copy(), (8*2+1,8*2+1), 1)
#detect edge. important: make sure this works well with CannyTrackbar()
canny = cv2.Canny(img_blurred, 160, 78)
coords = np.column_stack(np.nonzero(canny))
model, inliers = measure.ransac(coords, measure.CircleModel,
min_samples=3, residual_threshold=1,
max_trials=1000)
rr, cc = draw.circle_perimeter(int(model.params[0]),
int(model.params[1]),
int(model.params[2]),
shape=img.shape)
img[rr, cc] = 1
import matplotlib.pyplot as plt
plt.imshow(img, cmap='gray')
plt.scatter(model.params[1], model.params[0], s=50, c='red')
plt.axis('off')
plt.savefig('sphere_center.png', bbox_inches='tight')
plt.show()
Now I'd probably try to calculate where pixels are statisticaly brigher and where they are dimmer to adjust the laser position (if I understand correctly what you're trying to do)
If the Ransac is still not enough. I'd try tuning Canny to only detect a perfect arc on top of the circle (where it's well outlined) and than try using the following dependencies (I suspect that this should be possible):

thresholding an image with bright zones

I am developing an app for iOS with openCV that take a picture from a monitor and extract a curve, but when the image has some bright zones after thresholding, I don't get the complete curve but some black zones
Original image
processed image after thresholding
original = [MAOpenCV cvMatGrayFromUIImage:_sourceImage];
cv::threshold(original, original, 70, 255, CV_THRESH_BINARY | CV_THRESH_OTSU);
findContours(original, contours, hierarchy,CV_RETR_CCOMP, CV_CHAIN_APPROX_SIMPLE );
cv::Mat skel(original.size(), CV_8UC1, cv::Scalar(0));
int idx = 0;
for(; idx >= 0; idx = hierarchy[idx][0])
{
if (contours[idx].size()>250 && idx>-1){
cv::Scalar color( 255,255,255);
drawContours(skel, contours, idx, color, CV_FILLED, 8, hierarchy);
}
}
cv::threshold(skel, skel, 100, 255, CV_THRESH_BINARY_INV);
cv::erode(skel,skel,cv::Mat(),cv::Point(-1,-1),2);
So how I can process the image to extract the curve when the image have some bright zones like the example
When you have a background with an uneven illumination, you may want to apply first a White Top-Hat (or here for MatLab, and here for OpenCV).
Here is the result I got using a structuring element of type disk with radius 3.
Then, whatever thresholding method you choose will work.
Wouldn't be sufficient to use Otsu's thresholding?
Code fragment:
import cv2
image = cv2.imread('d:/so.jpg', cv2.IMREAD_GRAYSCALE)
threshold, thresholded = cv2.threshold(image, 0, 255, type=cv2.THRESH_BINARY + cv2.THRESH_OTSU)
print(threshold)
cv2.imshow('so', image);
cv2.imshow('thresholded', thresholded)
cv2.waitKey(0)

Detect caps on bottles using opencv and python

I know that there are a hundred topics about my question in all over the web, but i would like to ask specific for my problem because I tried almost all solutions without any success.
I am trying to count circles in an image (yes i have already tried hough circles but due to light reflections, i think, on my object is not very robust).
Then I tried to create a classifier (no success i think there is no enough features so the detection is not good)
I have also tried HSV conversation and tried to find my object with color (again I had some problems because of the light and the variations of colors)
As you can see on image, there are 8 caps and i would like to be able to count them.
Using all of this methods, i was able to detect the objects on an image (because I was optimizing all the parameters of functions for the specific image) but as soon as I load a new, similar, image the results was disappointing.
Please follow this link to see the Image
Bellow you can find parts of everything i have tried:
1. Hough circles
img = cv2.imread('frame71.jpg',1)
img = cv2.medianBlur(img,5)
cimg = cv2.cvtColor(img,cv2.COLOR_GRAY2BGR)
if img == None:
print "There is no image file. Quiting..."
quit()
circles = cv2.HoughCircles(img,cv.CV_HOUGH_GRADIENT,3,50,
param1=55,param2=125,minRadius=25,maxRadius=45)
circles = np.uint16(np.around(circles))
for i in circles[0,:]:
# draw the outer circle
cv2.circle(cimg,(i[0],i[1]),i[2],(0,255,0),2)
# draw the center of the circle
cv2.circle(cimg,(i[0],i[1]),2,(0,0,255),3)
print len(circles[0,:])
cv2.imshow('detected circles',cimg)
cv2.waitKey(0)
cv2.destroyAllWindows()
2. HSV Transform, color detection
def image_process(frame, h_low, s_low, v_low, h_up, s_up, v_up, ksize):
temp = ksize
if(temp%2==1):
ksize = temp
else:
ksize = temp+1
#if(True):
# return frame
#thresh = frame
#try:
#TODO: optimize as much as possiblle this part of code
try:
hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
lower = np.array([h_low, s_low, v_low],np.uint8)
upper = np.array([h_up,s_up,h_up],np.uint8)
mask = cv2.inRange(hsv, lower, upper)
res = cv2.bitwise_and(hsv,hsv, mask= mask)
thresh = cv2.cvtColor(res, cv2.COLOR_BGR2GRAY)
#thresh = cv2.threshold(res, 50, 255, cv2.THRESH_BINARY)[1]
thresh = cv2.threshold(thresh, 50, 255, cv2.THRESH_BINARY)[1]
thresh = cv2.medianBlur(thresh,ksize)
except Exception as inst:
print type(inst)
#cv2.imshow('thresh', thresh)
return thresh
3. Cascade classifier
img = cv2.imread('frame405.jpg', 1)
cap_cascade = cv2.CascadeClassifier('haar_30_17_16_stage.xml')
caps = cap_cascade.detectMultiScale(img, 1.3, 5)
#print caps
for (x,y,w,h) in caps:
cv2.rectangle(img, (x,y), (x+w,y+h), (255,0,0),2)
#cv2.rectangle(img, (10,10),(100,100),(0,255,255),4)
cv2.imshow('image', img)
cv2.waitKey(0)
cv2.destroyAllWindows()
quit()
About training the classifier I really used a lot of variations of images, samples, negatives and positives, number of stages, w and h but the results was not very accurate.
Finally I would like to know from your experience which is the best method I should follow and I will stick on that in order to optimize my detection. Keep in mind that all images are similiar but NOT identical. There are some differences due to light, movement etc
Than you in advance,
I did some experiment with the sample image. I'm posting my results, and if you find it useful, you can improve it further and optimize. Here are the steps:
downsample the image
perform morphological opening
find Hough circles
cluster the circles by radii (bottle circles should get the same label)
filter the circles by a radius threshold
you can also cluster circles by their center x and y coordinates (I haven't done this)
prepare a mask from the filtered circles and extract the possible bottles region
cluster this region by color
Code is in C++. I'm attaching my results.
Mat im = imread(INPUT_FOLDER_PATH + string("frame71.jpg"));
Mat small;
int kernelSize = 9; // try with different kernel sizes. 5 onwards gives good results
pyrDown(im, small); // downsample the image
Mat morph;
Mat kernel = getStructuringElement(MORPH_ELLIPSE, Size(kernelSize, kernelSize));
morphologyEx(small, morph, MORPH_OPEN, kernel); // open
Mat gray;
cvtColor(morph, gray, CV_BGR2GRAY);
vector<Vec3f> circles;
HoughCircles(gray, circles, CV_HOUGH_GRADIENT, 2, gray.rows/8.0); // find circles
// -------------------------------------------------------
// cluster the circles by radii. similarly you can cluster them by center x and y for further filtering
Mat circ = Mat(circles);
Mat data[3];
split(circ, data);
Mat labels, centers;
kmeans(data[2], 2, labels, TermCriteria(CV_TERMCRIT_EPS+CV_TERMCRIT_ITER, 10, 1.0), 2, KMEANS_PP_CENTERS, centers);
// -------------------------------------------------------
Mat rgb;
small.copyTo(rgb);
//cvtColor(gray, rgb, CV_GRAY2BGR);
Mat mask = Mat::zeros(Size(gray.cols, gray.rows), CV_8U);
for(size_t i = 0; i < circles.size(); i++)
{
Point center(cvRound(circles[i][0]), cvRound(circles[i][1]));
int radius = cvRound(circles[i][2]);
float r = centers.at<float>(labels.at<int>(i));
if (r > 30.0f && r < 45.0f) // filter circles by radius (values are based on the sample image)
{
// just for display
circle(rgb, center, 3, Scalar(0,255,0), -1, 8, 0);
circle(rgb, center, radius, Scalar(0,0,255), 3, 8, 0);
// prepare a mask
circle(mask, center, radius, Scalar(255,255,255), -1, 8, 0);
}
}
// use each filtered circle as a mask and extract the region from original downsampled image
Mat rgb2;
small.copyTo(rgb2, mask);
// cluster the masked region by color
Mat rgb32fc3, lbl;
rgb2.convertTo(rgb32fc3, CV_32FC3);
int imsize[] = {rgb32fc3.rows, rgb32fc3.cols};
Mat color = rgb32fc3.reshape(1, rgb32fc3.rows*rgb32fc3.cols);
kmeans(color, 4, lbl, TermCriteria(CV_TERMCRIT_EPS+CV_TERMCRIT_ITER, 10, 1.0), 2, KMEANS_PP_CENTERS);
Mat lbl2d = lbl.reshape(1, 2, imsize);
Mat lbldisp;
lbl2d.convertTo(lbldisp, CV_8U, 50);
Mat lblColor;
applyColorMap(lbldisp, lblColor, COLORMAP_JET);
Results:
Filtered circles:
Masked:
Segmented:
Hello finally i think I found a way to count caps on bottles.
Read image
Teach (find correct values for HSV up/low limits)
Select desire color (using HSV and mask)
Find contours on the masked image
Find the minCircles for contours
Reject all circles beyond thresholds
I have also order a polarized filter which I think it will reduce glares a lot. I am open to suggestions for further improvement (robustness and speed). Both robustness and speed is crucial for my application.
Thank you.

Thresholding for a colour in opencv

I am trying to set up my programme to threshold for a colour (in BGR format). I have not fully decided which colour I will be looking for yet. I would also like the program to record how many pixels it has detected of that colour. My code so far is below but it is not working.
#include "cv.h"
#include "highgui.h"
int main()
{
// Initialize capturing live feed from the camera
CvCapture* capture = 0;
capture = cvCaptureFromCAM(0);
// Couldn't get a device? Throw an error and quit
if(!capture)
{
printf("Could not initialize capturing...\n");
return -1;
}
// The two windows we'll be using
cvNamedWindow("video");
cvNamedWindow("thresh");
// An infinite loop
while(true)
{
// Will hold a frame captured from the camera
IplImage* frame = 0;
frame = cvQueryFrame(capture);
// If we couldn't grab a frame... quit
if(!frame)
break;
//create image where threshloded image will be stored
IplImage* imgThreshed = cvCreateImage(cvGetSize(frame), 8, 1);
//i want to keep it BGR format. Im not sure what colour i will be looking for yet. this can be easily changed
cvInRangeS(frame, cvScalar(20, 100, 100), cvScalar(30, 255, 255), imgThreshed);
//show the original feed and thresholded feed
cvShowImage("thresh", imgThreshed);
cvShowImage("video", frame);
// Wait for a keypress
int c = cvWaitKey(10);
if(c!=-1)
{
// If pressed, break out of the loop
break;
}
cvReleaseImage(&imgThreshed);
}
cvReleaseCapture(&capture);
return 0;
}
To threshold for a color,
1) convert the image to HSV
2) Then apply cvInrangeS
3) Once you got threshold image, you can count number of white pixels in it.
Try this tutorial to track yellow color: Tracking colored objects in OpenCV
I can tell how to do it in both Python and C++ and both with and without converting to HSV.
C++ Version (Converting to HSV)
Convert the image into an HSV image:
// Convert the image into an HSV image
IplImage* imgHSV = cvCreateImage(cvGetSize(img), 8, 3);
cvCvtColor(img, imgHSV, CV_BGR2HSV);
Create a new image that will hold the threholded image:
IplImage* imgThreshed = cvCreateImage(cvGetSize(img), 8, 1);
Do the actual thresholding using cvInRangeS
cvInRangeS(imgHSV, cvScalar(20, 100, 100), cvScalar(30, 255, 255), imgThreshed);
Here, imgHSV is the reference image. And the two cvScalars represent the lower and upper bound of values that are yellowish in colour. (These bounds should work in almost all conditions. If they don't, try experimenting with the last two values).
Consider any pixel. If all three values of that pixel (H, S and V, in that order) lie within the stated ranges, imgThreshed gets a value of 255 at that corresponding pixel. This is repeated for all pixels. So what you finally get is a thresholded image.
Use countNonZero to count the number of white pixels in the thresholded image.
Python Version (Without converting to HSV):
Create the lower and upper boundaries of the range you are interested in, in Numpy array format (Note: You need to use import numpy as np)
lower = np.array((a,b,c), dtype = "uint8")
upper = np.array((x,y,z), dtype = "uint8")
In the above (a,b,c) is the lower bound and (x,y,z) is the upper bound.
2.Get the mask for the pixels that satisfy the range:
mask = cv2.inRange(image, lower, upper)
In the above, image is the image on which you want to work.
Count the number of white pixels that are present in the mask using countNonZero:
yellowpixels = cv2.countNonZero(mask)
print "Number of Yellow pixels are %d" % (yellowpixels)
Sources:
http://srikanthvidyasagar.blogspot.com/2016/01/tracking-colored-objects-in-opencv.html
http://www.pyimagesearch.com/2014/08/04/opencv-python-color-detection/
count number of black pixels in an image in Python with OpenCV

Resources