IPFA22-method-classification.md

+**This is the Appendix to the paper:**\
+S. Lobnig; C. Burmer; K. Schekotihin, "Detection of Failure Analysis Methods with Image Classification", 2022 IEEE International Symposium on the Physical and Failure Analysis of Integrated Circuits (IPFA), 2022
+
+This appendix provides additional information about the results of our experiments.
+
+## Experiment 1:
+
+![image](uploads/d1c61d36d3f2078b82b3e79e6c11c5fb/image.png) This is the Confusion Matrix of Experiment 1. The classifier was trained and tested on D<sub>1</sub>. The x-axis shows the prediction and the y-axis shows the actual class.
+
+## Experiment 2:
+
+![image](uploads/2f34fc1232b5213dce6e7e8256ab51f7/image.png) This is the Confusion Matrix of Experiment 2. Images of D<sub>2</sub> get classified with the model (from Experiment 1) trained on images of D1. The x-axis shows the predicted class, the y-axis shows the real class.
+
+## Experiment 3:
+
+![image](uploads/759b8f71dcf6519c31fe4f71c01cf2da/image.png) This is the Confusion Matrix of Experiment 3. The classifier was trained and tested on D<sub>1</sub> and D<sub>2</sub>. The x-axis shows the prediction and the y-axis shows the actual class.
+
+## Experiment 4:
+
+![image](uploads/2f34fc1232b5213dce6e7e8256ab51f7/image.png) This is the Confusion Matrix of Experiment 4. Images of D<sub>3</sub> get classified with the model (from Experiment 3) trained on images of D<sub>1</sub> and D<sub>2</sub>. The x-axis shows the predicted class, the y-axis shows the real class.
+
+## Experiment 5:
+
+![image](uploads/759b8f71dcf6519c31fe4f71c01cf2da/image.png) This is the Confusion Matrix of Experiment 5. The classifier was trained and tested on D<sub>1</sub>, D<sub>2</sub> and D<sub>3</sub>. The x-axis shows the prediction and the y-axis shows the actual class.
\ No newline at end of file