#featuredetection

Introduction

<To Be Written>

CODE

#include <iostream> #include <opencv2/opencv.hpp> using namespace std; using namespace cv; int main() { // First declaring three image containers - // image contains input image, // gray_image contains the grayscale converted input image // and keypoint_image contains final image with keypoints drawn on it. Mat image, gray_image, keypoint_image; // This is vector will contain the keypoint values vector<KeyPoint> keypoints; // Read the image in color format image = imread("manu.png",CV_LOAD_IMAGE_COLOR); // Declare Window to display the image namedWindow("Image", CV_WINDOW_AUTOSIZE); // Transform image from BGR format ro grayscale and cvtColor(image, gray_image, CV_BGR2GRAY); // Create a feature detector using FAST algorithm // You can also use - // "STAR" – StarFeatureDetector // "SIFT" – SIFT (nonfree module) // "SURF" – SURF (nonfree module) // "ORB" – ORB // "BRISK" – BRISK // "MSER" – MSER // "GFTT" – GoodFeaturesToTrackDetector // "HARRIS" – GoodFeaturesToTrackDetector with Harris detector enabled // "Dense" – DenseFeatureDetector // "SimpleBlob" – SimpleBlobDetector // Just replace the "FAST" string in the input of create() function by // the desired algorithms string defined above. Ptr<FeatureDetector> feature_detector = FeatureDetector::create("STAR"); // Detect keypoints in the gray_image and store them in keypoints. feature_detector->detect(gray_image, keypoints); // Display the number of keypoints detected cout << "Number of keypoints detected = " << keypoints.size() << endl; // Draw keypoints on the keypoint_image drawKeypoints(image, keypoints, keypoint_image, Scalar::all(-1), DrawMatchesFlags::DEFAULT); // Display the image imshow("Image",keypoint_image); // Wait until, user generates a keypoint event. waitKey(0); // return return 0; }

RESULTS

Feature Detection using FAST algorithm. Circles represent key points.

Also, when we use STAR algorithm, we get this result -

They have developed an anti-theft car seat that can effectively identify the person sitting in it. The seat itself is outfitted with 360 sensors and it measures the pressure applied at each of these sensors, generating a 3D representation of the weight and weight distribution. The way you sit is like a fingerprint.