2. Face Detaction or Object Detection
Combination of computer vision and image processing to find out object in
a image or video.
The Object detection includes classifying an object in the image and
localize its poition in the image.
This can be achived using image segmentation with AI.
3. Classify the face.
Localize the face
List of facial
features.
How it Looks like?
12. Cross Entropy
Measures the performance of a
classification model whose output
is a probability value between 0 &
1.
Increases as the predicted P(e)
diverges from the actual label.
13. Euclidean Distance
This loss function is usually used for regression problems,It measures the
distance between two distinct points.
15. Classification + Localization: Model
Classification
Head:
● C Scores for C
classes
Localization Head:
● Class agnostic:
(x,y,w,h)
● Class specific:
(x,y,w,h) X C
19. Face Recognition using Siamese Networks
This network allows to calculate the degree of similarity between two
inputs
20. Since we can not have multiple images of the same person in
our database,
21. Yolo Based Face Detection
Each grid cell has 5 associated values. The first one is the probability p of that cell
containing the center of a face.The other 4 values are the (x_center, y_center, width,
height) of the detected face (relative to the cell).
22. 2x [8 filter convolutional layer on 288x288 image]
Max pooling (288x288 to 144x144 feature map)
2x [16 filter convolutional layer on 144x144 feature map]
Max pooling (144x144 to 72x72 feature map)
2x [32 filter convolutional layer on 72x72 feature map]
Max pooling (72x72 to 36x36 feature map)
2x [64 filter convolutional layer on 36x36 feature map]
Max pooling (36x36 to 18x18 feature map)
2x [128 filter convolutional layer on 18x18 feature map]
Max pooling (18x18 to 9x9 feature map)
4x [192 filter convolutional layer on 9x9 feature map]
5 filter convolutional layer on 9x9 feature map for the final
grid
23. Auxiliary network
Outputs of the main network were not as accurate as expected. Hence, a small
CNN network was implemented to take as input a small image containing a face
24. Object Detection
l
● Input: Image
● Output: For each object class c and each
image i,an algorithm returns predicted
detections: ocations
with confidence scores .
25. Object Detection: Evaluation
● Today new metrics are emerging
○ Averaging precision over all IoU thresholds: 0.5:0.05:0.95
○ Averaging precision for different object sizes (small, medium, big)
○ Averaging recall as a metric to measure object proposal quality.
27. Mean Average Precision (mAP)
● The winner of each object class is the team with the highest average precision
● The winner of the challenge is the team with the highest mean Average
Precision (mAP) across all classes.
28. Object Detection: Evaluation
● Mean Average Precision (mAP) across all classes, based on Average Precision
(AP) per class, based on Precision and Recall.