Guo_project3.docx - Categorize Objects Using Shape Information Introduction The task of this program is to classify objects using only the shape

Guo_project3.docx - Categorize Objects Using Shape...

This preview shows page 1 - 2 out of 2 pages.

Categorize Objects Using Shape Information Introduction The task of this program is to classify objects using only the shape information of the objects. The total process is: 1) Use ‘canny’ method to obtain the edge information of objects in the pictures 2) Use the eight-coordinate scanning method to obtain the single contour information and the landmarks in the clockwise order 3) Use the landmarks to calculate the pre-shape 4) Calculate the mean shape 5) Calculate the Procrustes distance to classify objects through SVD method and so on 6) Finally for the results, the program calculates the categorization accuracy (Running: Assume the project folder is next to the data set folder, path is '../eth80- cropped256/'. Just run the m file ‘maincate’, the result will be displayed.) Rationality Analysis Since the shape and position of the target objects in the images are largely
Image of page 1

Subscribe to view the full document.

Image of page 2

Unformatted text preview: deviated, the obtained data does not have affine invariance and needs to be normalized. So we can use the Procrustes method to normalize all the shape sets in the sample set. Finally, we can obtain the similar degree of results by minimizing the measure of the shape difference (Procrustes distance), and then classify the target object. Result Analysis The final average accuracy of the program is 73.25% and the standard accuracy is 0.1055, which are within acceptable limits. At the same time, during multiple program runs, the program runs well and the time cost is low. However, the disadvantage is that there are some problems in the extraction of the edge and the landmarks of the color pictures----there are many unreasonable extracted edges, so the classification result on the color picture is not good....
View Full Document

  • Fall '17
  • Alexiander

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern

Ask Expert Tutors You can ask 0 bonus questions You can ask 0 questions (0 expire soon) You can ask 0 questions (will expire )
Answers in as fast as 15 minutes