An image is essentially a matrix of intensity values. To describe an image, we introduce the concept of segments, patches, features, etc,. To further extract the information of an image, we introduce the use of Histogram of Oriented Gradients (HoG). Note that this section focus more on traditional CV techniques.

SIFT stands for Scale Invariant Feature Transform. It is an algorithm proposed in 2004 to transform image data into scale-invariant coordinates relative to local features. It is widely used in pose estimation, 3D reconstruction, object recognition and image retrieval

Image stitching is to combine two or more overlapping images to make one larger image. This section introduces the principle and algorithms used for image stitching, including RANSAC, forward/inverse warping and image blending

镜像的本质是一层又一层的镜像层组成的，每层都是制度不可修改的一组文件

In the analysis of algorithms, the master theorem for divide-and-conquer recurrences provides an asymptotic analysis for many recurrence relations that occur in the analysis of divide-and-conquer algorithms.