Created December 6, 2018

# Multimedia system with artificial intelligence

Self-learning system for the selection of musical compositions for listening, which would analyze the emotions of a person

197

## Things used in this project

### Hardware components

 ThunderSoft Thundercomm AI Kit
×1

### Software apps and online services

 MobileNet SSD
 Qualcomm Neural Processing SDK for AI v1.21.0
 Android Studio
 OpenCV
 ThunderSoft Face SDK
 ThunderSoft Object Dectetion SDK

## Code

### Eyes and mouth detection

Plain text
INPUT: Test image samples images (I) = {I1, I2, …,I n }
OUTPUT: Detected eyes and mouth
```BEGIN
Step 1: Input the samples images
(I) = { I1, I2, …, I n  }
Step 2: Read the image and store to the frame
F = { I1, I2, …, I n  }
Step 3: Read the contents of the xml file for face detection
and store in the memory
R = face.xml  //read face.xml, it stores in OpenCV lib.
Step 4:
i= {1,2,3,…,n}
fi ={f1, f2,…f n }
START loop
F 0  = 1
i = 0
While F i  > F(target) and i < n(Stages)
i = i + 1
Train classifier for stage(i)
Initialize weights
Normalize weights
Pick the (next) best weak classifier
Update weights
Evaluate F i
if F i  > f
go to Normalize Weights
Combine weak classifiers to form the strong
classifier stage
compute F i
Step 6: End of the algorithm
```

### eyes and mouth edge

Plain text
INPUT: Detected image(I)
OUTPUT: Edged image(I)
```BEGIN
X={1,2,3,...n}
C is that point the image in the frame
S is that sotre the image
X=0, C = 0, S=0
Step 1: Read the detected image from the system memory
R = Detected image(I)
Step 2: Detect in the image
START loop
For X = 1 to n
Read each pixel in I n
Point the image in the frame
C = Sobel (I n ) // import sobel function in OpenCV
lib
Store the image in the system directory
S = Store(C)  // import store function in
// OpenCV lib
End of For loop
Step 3: End of the algorithm 2
```

## Credits

### lab308

2 projects • 1 follower