Hog and sift

Hog and Sift

1. OBJECT DETECTION HOG AND SIFT ALGORITHM

2. HOG ALGORITHM HOG stands for histogram of oriented gradients. The hog descriptor focuses on structure or shape of the object. It uses magnitude as well as direction of the gradient to compute the features. It generates histogram by using magnitude and direction of the gradient.

3. Here we calculating gradient magnitude and direction, to calculate pixels intensity we need X direction=|40-70|=30 Y direction=|20-70|=50 By these values we are calculating magnitude and direction of the gradient By using magnitude and direction we calculate feature vectors 20 40 70 70

4. e

5. Before getting the hog feature and after concatenating feature vectors we are supposed to do normalize. Suppose we have taken 150*300 pixels and multiply with 2 to increase the brightness and divided by 2 to decrease the brightness, then you cant compare two images without normalization bec’z the pixels intensity will be changed. But if you normalize the feature vectors it is easy to compare

6. • For hog features giving human template and giving output for convolving with human model Then it will predict whether it is human or not.

7. SIFT ALGORITHM SIFT stands for scalar invariant feature transform and was first presented in 2004, by  D. Lowe , University of British Columbia.  It is a way to describe a local area in an image. In this whole image is reduced to set of points. SIFT is invariance to image scale and rotation.  This algorithm is patented, so this algorithm is included in the Non-free module in OpenCV.

8. Major advantages of SIFT are Distinctiveness :  individual features can be matched to a large database of objects Quantity :  many features can be generated for even small objects Efficiency :  close to real-time performance Extensibility :  can easily be extended to a wide range of different feature types, with each adding robustness.

9. The scale space of an image is a function L( x,y , σ) that is produced from the convolution of a Gaussian kernel(Blurring) at different scales with the input image. Within an octave, images are progressively blurred using the Gaussian Blur operator. Mathematically, “blurring” is referred to as the convolution of the Gaussian operator and the image. Gaussian blur has a particular expression or “operator” that is applied to each pixel. What results is the blurred image. gaussian blur Gaussian blur operator

10. In difference of gaussian kernel(DOG) we use those blurred images to generate another set of images These dog images are used to find interesting points in the image. These process is done for all images in the gausian pyramid. After that we stack those different images on top of the each other and basically your looking extreme points. In these locally distinct which stand out and those are your key points.