Found 184 Articles for OpenCV

The solidity of an object is computed as the ratio of contour area to its convex hull area. So to compute the solidity, we first have to find the contour area and convex hull area. The contour area of an object can be found using cv2.contourArea() function. Equivalent Diameter is the diameter of the circle whose area is the same as the contour area. The solidity and equivalent diameter can be computed as below − Syntax area = cv2.contourArea(cnt) hull = cv2.convexHull(cnt) hull_area = cv2.contourArea(hull) solidity = float(area)/hull_area equi_diameter = np.sqrt(4*area/np.pi) Where, cnt is a numpy array of the ... Read More

The aspect ratio of an object is computed as the ratio between the width and height of the bounding rectangle of the object. So, to compute the aspect ratio, we first have to find the bounding rectangle of the object. Bounding rectangle of an object can be found using cv2.boundingRect() function. It accepts the contour points of the object and returns top-left coordinate (x, y) and (width, height) of the bounding rectangle. We use the width and height to compute the aspect ratio. Syntax x, y, w, h = cv2.boundingRect(cnt) aspect_ratio = float(w)/h Here, "cnt" is a numpy array ... Read More

The extent of an object is computed as the ratio of contour area to its bounding rectangle area. So, to compute the extent, we first have to find the contour area and bounding rectangle area. The contour area of an object can be found using cv2.contourArea() function. Syntax The extent can be computed as follows − area = cv2.contourArea(cnt) x, y, w, h = cv2.boundingRect(cnt) rect_area = w*h extent = float(area)/rect_area Here, "cnt" is a numpy array of the contour points of an object in the image. Steps You can use the following steps to compute extent of an ... Read More

A bilateral filter operation is highly effective in smoothing the image and removing noises. The main advantage of the bilateral filtering is that it preserves the edges unlike in average and median filtering. Bilateral filtering operation is slower in comparison to other filters. We can perform bilateral filtering on an image using the cv2.bilateralFilter() method. Syntax Following is the syntax of this method. cv2.bilateralFilter(img, d, sigmaColor, sigmaSpace) This method accepts the following parameters − img − The input image on which the bilateral filter operation to be applied. d − A variable of the type integer representing the ... Read More

We can fit an ellipse to an object using the function cv2.fitEllipse(). The ellipse is inscribed in a rotated rectangle. The rotated rectangle is a bounding rectangle with minimum area enclosing the object. Syntax The syntax used for this function is − ellipse = cv2.fitEllipse(cnt) Where, "cnt" is the contour points. It is represented as an array of contour points. Output − It returns a tuple of tuples in ((x, y), (majorAxis, minorAxis), angle) format. (x, y) is the coordinates of center and (majorAxis, minorAxis) is the lengths of minor and major axes and angle is the rotation angle ... Read More

In OpenCV, a color (RGB) image is represented as a 3-dimensional numpy array. The pixel values of an image are stored using 8 bit unsigned integers (uint8) in range from 0 to 255. The bitwise OR operation on two images is performed on the binary representation of these pixel values of corresponding images. Syntax Here is the syntax to perform bitwise OR operation on two images − cv2.bitwise_or(img1, img2, mask=None) img1 and img2 are the two input images and mask is a mask operation. Steps To compute bitwise OR between two images, you can use the steps given below ... Read More

To add a watermark to an image, we will use the cv2.addWeighted() function from OpenCV. You can use the following steps to create a watermark on an input image − Import the required library. In all the following Python examples, the required Python library is OpenCV. Make sure you have already installed it. import cv2 Read the input image on which we are going to apply the watermark and read the watermark image. img = cv2.imread("panda.jpg") wm = cv2.imread("watermark.jpg") Access the height and width of the input image, and the height, width of the watermark image. h_img, w_img ... Read More

A minimum enclosing circle (circumcircle) of an object is a circle which completely covers the object with minimum area. We can find the minimum enclosing circle of an object using the function cv2.minEnclosingCircle(). Syntax The syntax of this function is − (x, y), radius = cv2.minEnclosingCircle(cnt) Where, "cnt" are the contour points. It is represented as an array of contour points. Output − It returns coordinate of center (x, y) and radius of minimum enclosing circle. (x, y) and radius are of float dtype. So, to draw a circle on the image, we convert them to integers. To draw ... Read More

A Convex Hull looks similar to contour approximation, but it is not exactly a contour approximation. A convex hull is a convex curve around an object. A convex curve is always bulged out, or at-least flat. A convex hull finds the convexity defects and corrects them. Syntax To find the convex hull, we use the following function − hull = cv2.convexHull(cnt, hull, clockwise, returnPoints) Arguments cnt are the contour points. It is represented as an array of contour points. hull is the output, normally we avoid it. clockwise − Orientation flag. If it is True, the output convex ... Read More

The Hu-Moments can be found using the cv2.HuMoments() function. It returns seven moments invariant to translation, rotation and scale. Seventh moment is skew-invariant. To compute the Hu-Moments, we need to first find the image. The image moments are computed for an object using the contour of the object. So, first, we detect the contour of the object and then apply cv2.moments() function to compute the moments. Syntax The following syntax is used for this function − M = cv2.moments(cnt) cv2.HuMoments(M) Here, cnt − It is a numpy array of the contour points of an object in the image. M ... Read More