1 / 4

Efficient Shape and Color Comparison Algorithms for Image Retrieval

This project explores comparing shapes using Hu Invariants and Fourier Descriptors, as well as comparing colors through Histograms to enable effective searching in a database. The research covers the process of turning images into Fourier descriptors and working with Hu Invariants. Challenges included a longer startup phase and limitations in debugging certain issues. Lessons learned involve setting clearer goals, prioritizing Fourier research, and improving the project's initial debugging process for efficiency in implementation.

xarles
Télécharger la présentation

Efficient Shape and Color Comparison Algorithms for Image Retrieval

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Similarity Original Goals Comparing shapes using Hu Invariants Comparing shapes using Fourier Descriptors Comparing colours using Histograms Comparing colours using combining Searching in a DB using the comparison algorithm Searching using a simpler and faster algorithm

  2. What I have accomplished Researched invariants and fouriers mainly Comparing shapes using Hu Invariants Having data on Hu Invariants Turning picture into Fouriers

  3. Mistakes and Problems Start-up took longer than needed and expected Long research period left little time for implementation Hu Invariants harder to work with than expected Close to no information debugging certain things Even after 3 weeks of research not enough knowledge in some areas.

  4. What I would have done different Lower goals Early make simple and clear case I wanted to solve Focused more on fourier during research Fixed some sort of debug in beginning of project Having a faster project start-up

More Related