Chris Pollett > Students >
Kulkarni

    ( Print View)

    [Bio]

    [Blog]

    [CS297 Proposal]

    [CS297 - Deliverable 1]

    [CS297 - Deliverable 2]

    [CS297 - Deliverable 3]

    [CS297 - Deliverable 4]

    [CS297 Report - PDF]

    [CS298 Proposal]

    [CS298 - Deliverable 1]

    [CS298 - Report -PDF]

























Deliverable 2: Shape Classification using Doodle Classifier

DoodleClassifier is an openFrameworks application, part of the ml4a-ofx collection, which lets you train a classifier to accurately recognize drawings (doodles) from a camera.

Requirements

  • Openframeworks (C++ OpenGL)

Instructions

  • Download and install Openframeworks
  • Copy the source code provided below into the /apps folder and open on Xcode(MAC) or IDE of choice.
  • Build program and openframeworks should automatically open app if no errors found.
  • Draw a bunch of stars and circles on a piece of white paper.
  • Use the threshold and dilation slider on the bototm left to make sure all edges are detected.
  • Click the classify button and get classification shown at the bottom.

Source code: Shape Classification using Doodle Classifier - ZIP

Github: Shape Classification using Doodle Classifier