Changeset 33082 for other-projects/is-sheet-music-encore/trunk/image-identification/src/Main.java

Timestamp:

2019-05-16T11:15:02+12:00 (5 years ago)

Author:

cpb16

Message:

added notes from meeting

File:

• other-projects/is-sheet-music-encore/trunk/image-identification/src/Main.java (modified) (3 diffs)

other-projects/is-sheet-music-encore/trunk/image-identification/src/Main.java

@@ -16 +16 @@
 //https://riptutorial.com/opencv/example/21963/converting-an-mat-object-to-an-bufferedimage-object
 
+
+
+//GOAL for 21st
+
+
+//Classifier 01
+//Have args so can call "java image-identification-classifier01 XX XX"
+//args can be parameters in algorthim such as threshold or theta?
+//Run on 5000 images.
+//Record success rates
+//All done with makefile
+
+
+//But first understand houghline transform
+//Know what the algorithm being used is doing.
+//MAke constants for this classifier
+//Make java be able to run on CMD line
 
 public class Main {
@@ -65 +82 @@
             percentage = ((float)redCount/(float)pixelCount)*(float)100;
             //If more than %10 and less than %50 then its sheet music!
-            if(percentage > 10 && percentage < 50){
+            if(percentage > 10 && percentage < 50){ //MAKE THESE CONSTANTS!!
                 return true;}
         }
@@ -99 +116 @@
             Imgproc.HoughLines(edgesDetected, lines, 1, Math.PI / 180, 150); // runs the actual detection
             // Draw the lines
+            //LOOK OVER THIS AGAIN THE 1000 might be image height?
+            //THRESHOLD should be changed, based on img dimensions?
+
             for (int x = 0; x < lines.rows(); x++) {
                 double rho = lines.get(x, 0)[0],
                         theta = lines.get(x, 0)[1];
+                //CONVERT to Cartisean coord
                 double a = Math.cos(theta), b = Math.sin(theta);
                 double x0 = a * rho, y0 = b * rho;
+
                 Point pt1 = new Point(Math.round(x0 + 1000 * (-b)), Math.round(y0 + 1000 * (a)));
                 Point pt2 = new Point(Math.round(x0 - 1000 * (-b)), Math.round(y0 - 1000 * (a)));