Thesis
Now that a decent Hit Rate has been achieved, the focus turns to reducing the False Alarms. One step to reducing the false alarms is to eliminate overlapping regions of interest, so that the false alarms picked up in about the same vicinity will count as 1 or 2 false alarms as opposed to 6 […]
Continue reading about Trial ::: haarcascade21 ::: [Reduction of overlapping ROIs]
Now that a decent Hit Rate has been achieved, the focus turns to reducing the False Alarms. One step to reducing the false alarms is to black out the suns disk, so that the false alarms picked up in the suns disk will eliminated from the count. Original False Alarm count was 95058, after some […]
Continue reading about Trial ::: haarcascade21 ::: [Black Out the Suns disk]
When creating samples from the marked images the default options are listed below. You notice that the default for the maxzangle is less than the defaults for the x and y angle values. So why is that? What do these parameters mean? The Haar Classifier was initially developed for facial detections, but has been […]
Continue reading about CreateSamples ::: [ Maxxangle, Maxyangle, Maxzangle ]
So now that the limitation of the performance application has been identified what does that mean for the previous haar classifiers we have tested and analyzed this far? Well to put it bluntly they were wrong. The results did not truly reflect the classifiers accuracy. So I took the haarcascade15, since this classifier had the […]
When creating a classifier to use for detection of solar cavities, the steps taken are essentially creating the samples to train with, train, and then test the performance. In testing the performance, I began looking through the output, and noticed some oddity. For some of the images the performance output would classify a MISS, so […]
In an attempt to analyze some data as well as performance of my classifier and implementation on solar cavity detection I decided it would be beneficial to see the data in terms of individual quadrant performance. Below is the confusion matrix for the outcomes of the Quadrant IV, based on 100 q4 (quadrant 4) positive […]
Continue reading about Template Matching – Confusion Matrix Analysis – Quadrant IV
In an attempt to analyze some data as well as performance of my classifier and implementation on solar cavity detection I decided it would be beneficial to see the data in terms of individual quadrant performance. Below is the confusion matrix for the outcomes of the Quadrant III, based on 100 q3 (quadrant 3) positive […]
Continue reading about Template Matching – Confusion Matrix Analysis – Quadrant III
In an attempt to analyze some data as well as performance of my classifier and implementation on solar cavity detection I decided it would be beneficial to see the data in terms of individual quadrant performance. Below is the confusion matrix for the outcomes of the Quadrant II, based on 100 q2 (quadrant 2) positive […]
Continue reading about Template Matching – Confusion Matrix Analysis – Quadrant II
In an attempt to analyze some data as well as performance of my classifier and implementation on solar cavity detection I decided it would be beneficial to see the data in terms of individual quadrant performance. Below is the confusion matrix for the outcomes of the Quadrant I, based on 100 q1 (quadrant 1) positive […]
Continue reading about Template Matching – Confusion Matrix Analysis – Quadrant I
In running through tests against all the haarcascades I create, I noticed that the number of Misses in Quadrant III seemed surprisingly high, even when the cavity was a very distinct one. Here is an example of the original image that was used to train the cascades. Here is an output file from the […]