The file Lab 9 - Real Estate Data.csv contains real estate transaction data from 2014 - 2015. There are 21,597 tuples of data, with each attribute described in the file. The task is to determine a multi-linear regression relationship of the form, x1 + x2 · Bedrooms + x3 · Bathrooms + x4 · Floors + x5 · W aterfront…

The goal of this assignment is to generalize your solution to lab 7. We restrict ourselves to graphs on 5 vertices, labeled x1, x2, x3, x4, x5. We form a directed graph on x1, x2, x3, x4, x5 by having all possible edges xixj . Make an .m file that takes as an input a 5 length vector V and an upper triangular…

The goal of this assignment is write an algorithm that can check if a matrix is diagonalizable over the real numbers, and if so, give an orthonormal basis of eigenvectors for the image of a square matrix. Complete the following steps: Step 1. Calculate the characteristic polynomial of A by using >>p = poly(A) (the polynomial is a vector, with the first number being the coefficient…

We develop MATLAB functions to solve upper and lower triangular systems and then solve a more general system with LU factorization. Activities 1. Suppose we have a 4 × 4 upper triangular system Ax = b as below: A =   −5 5 0 −2 0 6 5 7 0 0 9 −7 0 0 0 −4  

Write a function myLU to perform the LU factorization for an arbitrary n×n matrix (under the assumption that elimination can be performed without row exchanges). Run the function on the input, A =   1 2 7 1 8 2 8 3 7 22 11 26 14 28 2 5 16 15 27 12 24 8 22 66 77 117 66 107…

(1) Generate M a 3 × 3 real matrix with random entries ranging from 0 to 1. Compute M\b where b =   1 3 7   . Do this 100 times. Is there always a solution? Why do you think this is? (2) Set up the system of equations to solve the following magic matrix. Use the…

The binomial coefficient n k (read ”n choose k”) is defined as n k = n! (n − k)!k! where ! is the factorial symbol, (e.g., 4! = 4*3*2*1 = 24, 0! = 1! = 1) and n and k are non-negative integers with n > k. (1) Write a function called mybinomial.m that calculates n choose k without using MATLAB’s built-in binomial or factorial functions.

(1) Write a function called calculate Grades that takes an arbitrary length vector of grades, then curves them. (a) Compute the mean of grades (use for loop, not the built-in function mean()) (b) Normalize grades so that the mean is 70 by doing the following: curvedGrade = 70*grades/mean. (c) Test your function with a vector score = . Include the output in diary.

(1) For the following problems start a diary and turn in the print out as well as the plot. (2) Let A =   8 1 6 3 5 7 4 9 2   B =   2 7 6 9 5 1 4 3 8   (a) Calculate AB. (b) Calculate A times B componentwise.

Overview In this assignment you will be implementing an algorithm to reconstruct a 3D point cloud from a pair of images taken at different angles. In Part I you will answer theory questions about 3D reconstruction. In Part II you will implement the 8-point algorithm, triangulation, and other techniques to find and visualize 3D locations of corresponding image points. Part I…

Overview In this assignment, you will be implementing a panorama application step by step using planar homographies. Before we step into the implementation, we will walk you through the theory of planar homographies. In the programming section, you will first learn to find point correspondences between two images and use these to estimate the homography between them. Using this homography, you will…

Overview The bag-of-words (BoW) approach, which you learned about in class, has been applied to a myriad of recognition problems in computer vision. For example, two classic ones are object recognition and scene classification 1 . Beyond that, a great deal of study has aimed at improving the BoW representation. You will see a large number of approaches that remain in the spirit of BoW but improve upon the traditional approach which you will implement here.

Overview Figure 1: You will implement (1) a multi-layer perceptron (neural network) and (2) convolutiona neural network to recognize hand-written digit using the MNIST dataset. The goal of this assignment is to implement neural networks to recognize hand-written digits in the MNIST data. MNIST Data You will use the MNIST hand-written digit dataset to perform the first task (neural network). We have reduced the image size (28 × 28 → 14 × 14) and…

Overview Figure 1: You will design a visual recognition system to classify the scene categories. The goal of this assignment is to build a set of visual recognition systems that classify scene categories. The scene classification dataset consists of 15 scene categories including office, kitchen, and forest as shown in Figure 1 [1]. The system will compute a set of…

SIFT Feature Extraction (a) Image (b) SIFT Figure 1: Given an image (a), you will extract SIFT features using OpenCV. One of the key skills to learn in computer vision (and software development in general) is the ability to use other, open-source code, which allows you to not reinvent the wheel. We will use OpenCV library for SIFT features extraction given your images.

HOG Figure 1: Histogram of oriented gradients. HOG feature is extracted and visualized for (a) the entire image and (b) zoomed-in image. The orientation and magnitude of the red lines represent the gradient components in a local cell. In this assignment, you will implement a variant of HOG (Histogram of Oriented Gradients) in Python proposed by Dalal and Triggs [1] (2015 Longuet-Higgins Prize Winner).

Project Purpose Implement the two classes described below. Both classes must be added to the csce240_programming_assignment_5 namespace. NOTE: The only standard library includes allowed for this project are: iostream and string. You must properly manage memory using pointers. SongRecording private data members: - a string for the song title - a pointer to dynamically allocated memory holding the artist name(s) (strings)

Purpose – Implement the following two classes Weight Create a Weight class that holds the value and units of a weight in private double and string data members, respectively. The class should allow for the units to be ounces, pounds, grams, or kilograms. The class will contain a constructor, a ConvertUnits member function, and accessor and mutator functions for the private…

Purpose Write, test, and use the four functions described below to read a text file containing a word search grid, display the grid, and find words within the grid. Functions Function 1 – ReadWordSearch Implement the ReadWordSearch function. This function reads a text file containing the characters into a double-subscripted character array with kSize rows and kSize columns. kSize is a constant variable set in…

Program Purpose – Implement the functions described below IsSquare – Function that takes an integer argument and returns whether or not the argument is a perfect square (is equal to an integer squared). For example, IsSquare(4) should return true, and IsSquare(5) should return false. IsPerfect – Function that takes an integer argument and returns whether or not the argument is a perfect number.

Program Purpose – Convert numeric values expressed in bases between 2 and 9, inclusive, to the base 10 equivalents of those values. The program will output the base 10 values, the number of values input, and the largest value input. Overview In a positional numeration system with base b, each position represents a power of b. In the decimal system, which is a positional numeration system with base…

As we discussed in class, photometric stereo is a computational imaging method to determine the shape of an object from its appearance under a set of lighting directions. In the course of this homework, we will solve a simplified version of the photometric stereo problem. We will make certain assumptions: that the object is Lambertian and is imaged with an orthographic camera under a set…

Theory Q1.1 Theory Prove that softmax is invariant to translation, that is sof tmax(x) = sof tmax(x + c) 8c 2 R. Softmax is defined as below, for each index i in a vector x. sof tmax(xi) = exi P j exj Often we use c = max xi. Why is that a good idea? (Tip: consider the range of values that numerator will have with c = 0 and c = max xi) Q1.2 Theory Softmax can be written as a three step processes, with si = exi , S = Psi and sof tmax(xi) = 1 S si.

In this assignment, you will be implementing an algorithm to reconstruct a 3D point cloud from a pair of images taken at different angles. In Part I you will answer theory questions about 3D reconstruction. In Part II you will apply the 8-point algorithm and triangulation to find and visualize 3D locations of corresponding image points. Part I Theory Before implementing our own 3D reconstruction, let’s take a look at some simple theory questions that may arise.

1 Lucas-Kanade Tracking In this section you will be implementing a simple Lucas & Kanade tracker with one single template. In the scenario of two-dimensional tracking with a pure translation warp function, W(x; p) = x + p . (1) The problem can be described as follows: starting with a rectangular neighborhood of pixels N 2 {xd}D d=1 on frame It, the Lucas-Kanade tracker aims to move it by an offset p = T to obtain another rectangle on frame It+1, so that the pixel squared difference in the two rectangles is minimized: p⇤ = arg minp = X x2N ||It+1(x + p) It(x)||2 2 (2) = 2 6 4 It+1(x1 + p) .