Let’s take a look at HSV color space: You need white, which is close to the center and rather high. Start with sensitivity = 15 lower_white = np.array([0,0,255-sensitivity]) upper_white = np.array([255,sensitivity,255]) and then adjust the threshold to your needs. You might also consider using HSL color space, which stands for Hue, Saturation, Lightness. Then you … Read more
I suspect your test_image has an additional alpha channel per pixel, thus it has 4 channels instead of only three. Try: test_image = Image.open(test_image_name).convert(‘RGB’)
You need to use np.transpose to rearrange dimensions. Now, n x m x 3 is to be converted to 3 x (n*m), so send the last axis to the front and shift right the order of the remaining axes (0,1). Finally , reshape to have 3 rows. Thus, the implementation would be – img.transpose(2,0,1).reshape(3,-1) Sample … Read more
I am late to the party as well, but I installed OpenCV 2.4.9 for Mac OS X, and the drawMatches function doesn’t exist in my distribution. I’ve also tried the second approach with find_obj and that didn’t work for me either. With that, I decided to write my own implementation of it that mimics drawMatches … Read more
Complete solution for arbitrary Sobel kernel sizes and angles tl;dr: skip down to section ‘Examples’ To add another solution, expanding on this document (it’s not particularly high quality, but it shows some usable graphics and matrices starting at the bottom of page 2). Goal What we’re trying to do is estimate the local gradient of … Read more
First, aren’t you supposed to be using vl_sift instead of sift? Second, you can use SIFT feature matching to find correspondences in the two images. Here’s some sample code: I = imread(‘p1.jpg’); J = imread(‘p2.jpg’); I = single(rgb2gray(I)); % Conversion to single is recommended J = single(rgb2gray(J)); % in the documentation [F1 D1] = vl_sift(I); … Read more
For axis-aligned bounding boxes it is relatively simple. “Axis-aligned” means that the bounding box isn’t rotated; or in other words that the boxes lines are parallel to the axes. Here’s how to calculate the IoU of two axis-aligned bounding boxes. def get_iou(bb1, bb2): “”” Calculate the Intersection over Union (IoU) of two bounding boxes. Parameters … Read more
EDIT: I wrote a Python script for this. As your objective is blurring (for privacy protection), you basically need a high recall detector as a first step. Here’s how to go about doing this. The included code hints use OpenCV with Python. Convert to Grayscale. Apply Gaussian Blur. img = cv2.imread(‘input.jpg’,1) img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) … Read more
You were almost there. One problem though: case CV_EVENT_RBUTTONUP needs to break, and I would also add a break on default case. The following code sets the ROI, performs a simple grayscale processing on it and then copies the processed ROI back to the original image. For testing purposes I changed your code to use … Read more
I recommend the following steps: threshold() the image dilate() the image – this will remove the black line splitting the top and bottom section and also darker artifacts on the lower part findContours() using setting to retrieve only external contours(RETR_EXTERNAL) and simplify the output(CHAIN_APPROX_SIMPLE) process the contours further Step 1:threshold # threshold image ret,thresh = … Read more