Deep Learning Face recognition: Part 1

-
What is Face Recognition?
  1. It is an ability to recognize a face of a person in an image.
  2. In early days operator has to manually tag the location of each facial features.
  3. The new complex statistical model was built and used to increase the accuracy of recognition.
  4. The advent of deep learning led to huge advances in face recognition.
  5. Researchers openly shared their solution for building face recognition.
Uses of Face Recognition?
  1. Identify verification.
  2. Automatically organizing raw photo libraries by the person.
  3. Tracking a specific person.
  4. Counting unique people.
  5. Finding people with similar appearances.
Tools for Face Recognition:
  1. Commercial face recognition services
    1. Amazon Rekognition API: used for FACE RECOGNITION, EMOTION DETECTION, MOTION DETECTION
    2. Microsoft Azure Face API: used for FACE RECOGNITION, AGE AND GENDER DETECTION, AND FACE SIMILARITY MATCHING.
  2. Open source face recognition:
    1. OpenFace: Brandon Amos and Carnegie Mellon university
    2. dlib: Davis King
    3. Face_recognition: Simplified Python interface for dlib face recognition 
Face Recognition as a multi-step pipeline:
  1. Locate and extract faces from each image.
  2. Identify facial features in each image.
  3. Align faces to match the pose template.
  4. Encode faces using a trained neural network.
  5. Check the Euclidean distance between face encoding.
I have learnt how Face recognition and detection can be implemented in python and OpenCV from different sources, I would like to present it in a short format in mostly 5 parts. 

Comments

Post a Comment

Popular posts from this blog

Splitting criteria

-
Image
This package helps to find splitting criteria in C4.5 Information Gain ID3 uses information gain as its attribute selection measure. This measure is based on pioneering work by Claude Shannon on information theory, which studied the value or “information content” of messages. Let node N represent or hold the tuples of partition D. The attribute with the highest information gain is chosen as the splitting attribute for node N. This attribute minimizes the information needed to classify the tuples in the resulting partitions and reflects the least randomness or “impurity” in these partitions. Such an approach minimizes the expected number of tests needed to classify a given tuple and guarantees that a simple (but not necessarily the simplest) tree is found. The expected information needed to classify a tuple in D is given by: where pi is the probability that an arbitrary tuple inDbelongs to classCi and is estimated by |Ci,D|/|D|. A log function to the base 2 is used becaus...
Read more

How to Handle Noisy Data in preprocessing of data?

-
Binning method:(one of the method) first sort data and partition into (equi-depth) bins then one can smooth by bin means,  smooth by bin median, smooth by bin boundaries, etc. Equal-width (distance) partitioning: It divides the range into N intervals of equal size: uniform grid if A and B are the lowest and highest values of the attribute, the width of intervals will be: W = (B-A)/N. The most straightforward But outliers may dominate the presentation Skewed data is not handled well. Equal-depth (frequency) partitioning: It divides the range into N intervals, each containing approximately same number of samples Good data scaling Managing categorical attributes can be tricky. Code for binning (if needed we can edit for user input instead of random) : Feel free to comment about mistakes and doubts.
Read more

Embedding the GitHub Gists codes into blogs

-
Image
Create the gist of your codes: Then get the embedding link. Click the HTML link and place the embedded link at the desired position. Code your code snippet appears as magic with git link in the below. Above process works for dynamic themes like Contempo in bloggers, but it fails for other dynamic themes so go for step 5. https://stackoverflow.com/questions/18788724/issues-adding-github-gist-to-my-blogusing-google-blogger/21355714#21355714  is the link where you can find the information to display the codes of Github with Gists in dynamic blogs.
Read more