vault backup: 2024-12-31 01:47:41

.obsidian/workspace.json

@@ -29,12 +29,28 @@
             "state": {
               "type": "markdown",
               "state": {
-                "file": "Foundation of data science/notes/3.1 Multi Class Logistic Regression.md",
+                "file": "Biometric Systems/notes/13. Multi biometric.md",
                 "mode": "source",
                 "source": false
               },
               "icon": "lucide-file",
-              "title": "3.1 Multi Class Logistic Regression"
+              "title": "13. Multi biometric"
+            }
+          },
+          {
+            "id": "2854bd3b52a5b340",
+            "type": "leaf",
+            "state": {
+              "type": "pdf",
+              "state": {
+                "file": "Biometric Systems/slides/LEZIONE12_MULBIOMETRIC.pdf",
+                "page": 14,
+                "left": -8,
+                "top": 477,
+                "zoom": 1.9210084033613448
+              },
+              "icon": "lucide-file-text",
+              "title": "LEZIONE12_MULBIOMETRIC"
             }
           },
           {
@@ -44,9 +60,9 @@
               "type": "pdf",
               "state": {
                 "file": "Biometric Systems/slides/LEZIONE9_Ear recognition.pptx.pdf",
-                "page": 17,
+                "page": 8,
                 "left": -153,
-                "top": 845,
+                "top": 5,
                 "zoom": 1.3
               },
               "icon": "lucide-file-text",
@@ -226,19 +242,20 @@
   },
   "active": "dee6b7fc799ba9d4",
   "lastOpenFiles": [
+    "Biometric Systems/slides/LEZIONE12_MULBIOMETRIC.pdf",
+    "Biometric Systems/notes/13. Multi biometric.md",
+    "Biometric Systems/slides/LEZIONE9_Ear recognition.pptx.pdf",
+    "Foundation of data science/notes/3.1 Multi Class Logistic Regression.md",
     "Foundation of data science/notes/4 L1 and L2 normalization - Lasso and Ridge.md",
     "Foundation of data science/notes/3 Logistic Regression.md",
     "Biometric Systems/slides/LEZIONE4_Face introduction and localization.pdf",
     "Biometric Systems/slides/Biometric_System___Notes.pdf",
-    "Biometric Systems/slides/LEZIONE9_Ear recognition.pptx.pdf",
     "Foundation of data science/slides/multiclass_crossentropy_biasvariance.pdf",
-    "Foundation of data science/notes/3.1 Multi Class Logistic Regression.md",
     "Foundation of data science/slides/binary_classification.pdf",
     "Foundation of data science/slides/FDS_linear_regression_w_notes.pdf",
     "Foundation of data science/slides/IP CV Basics.pdf",
     "Foundation of data science/slides/FDS_intro_new.pdf",
     "Foundation of data science/slides/Variational Autoencoders.pdf",
-    "Foundation of data science/slides/Traditional discriminative approaches.pdf",
     "Biometric Systems/images/Pasted image 20241228171617.png",
     "Biometric Systems/images/Pasted image 20241228174722.png",
     "Biometric Systems/notes/4. Face detection.md",
@@ -247,7 +264,6 @@
     "Biometric Systems/notes/8 Face anti spoofing.md",
     "Biometric Systems/notes/7. Face recognition 3D.md",
     "Biometric Systems/notes/12. Iris recognition.md",
-    "Biometric Systems/notes/13. Multi biometric.md",
     "Biometric Systems/notes/2. Performance indexes.md",
     "Biometric Systems/notes/3. Recognition Reliability.md",
     "Biometric Systems/notes/9. Ear recognition.md",

Biometric Systems/notes/13. Multi biometric.md

@@ -41,18 +41,37 @@ example: use SIFT (scalar invariant feature transform)
 Phases:
 - feature extraction (SIFT feature set)
 - feature normalization: required due to the possible significant differences in the scale of the vector values
+- si crea un vettore solo composto dai due feature vector
 
 Problems to address:
-- feature selection / reduction (complete with slide)
+- **feature selection / reduction**
-- matching
+	- è più efficiente scegliere poche feature rispetto all'intero vettore, si possono usare tecniche come
+		- **clutering k-means** mantenendo solo i centri dei cluster
+			- performed after linking the two normalized vectors
+		- **neighborhood elimination**
+			- points at a certain distance are eliminated
+			- performed before linking, on the single vectors
+		- **points belonging to specific regions**
+			- only points in specific regions of the train (e.g. face, nose, mouth...) are maintained
+- **matching**
+	- **point pattern matching**
+		- method to find the number of paired "points" between the probe vector and the gallery one
+		- two points are paired if their distance is smaller than a threshold
 
 ##### Feature level fusion: parallel
 parallel combination of the two vectors:
-- vector normalization (shorter should be extended if size is different)
+- **vector normalization**
-- pre-processing of vectors: weighted combination through the coefficient $\theta$
+	- shorter vector is extended to match the size of the other one
-- further feature processing: PCA, L-L expansion, LDA
+	- e.g. zero-padding
+- **pre-processing of vectors
+	- step 1: transform vectors in unitary vectors (dividing them by their L2 norm)
+	- step 2: weighted combination through the coefficient $\theta$, based on the lenght of X and Y
+	- we can then use X as the real part and Y as the imaginary part of the final vector
+- **further feature processing:*
+	- using linear techniques like PCA, L-L expansion, LDA
 
-add CCA
+##### Feature level fusion: CCA
+The idea is to find a pair of transformations that maximizes the correlation between characteristics
 
 #### Score level fusion
 ![[Pasted image 20241212085003.png]]
@@ -124,13 +143,24 @@ Normalization functions:
 ![[Pasted image 20241212094046.png|300]]
 
 The Min-max normalization technique performs a “mapping” (shifting + compression/dilation) of the interval between the minimum and maximum values in the interval between 0 and 1
+Pro: range tra 0 e 1
+Contro: bisogna conoscere minimo e massimo dello score di ogni sottosistema
 ![[Pasted image 20241212093902.png|200]]
 
+Standardizzazione per media e varianza, ampiamente usato
+contro: non porta lo score in un range fisso
 ![[Pasted image 20241212093927.png|200]]
 
+median/MAD: si sottrae la mediana e si divide per la mediana dei valori assoluti
+funziona male se la distribuzione degli score non è gaussiana. Non preserva la distribuzione originale e non garantisce nemmeno un range fisso :/
 ![[Pasted image 20241212093943.png|200]]
 
+Sigmoide: porta nell'intervallo aperto (0, 1)
+contro 1: verso gli estremi distorce parecchio
+contro 2: dipende dai parametri k e c che dipendono a sua volta dalla distribuzione degli score
 ![[Pasted image 20241212094000.png|200]]
 
+Tanh: garantisce range (0, 1)
+contro: tende a concentrare eccessivamente i valori verso il centro (0.5).
 ![[Pasted image 20241212094016.png|200]]