2020_CSE_26

 MODULE-4  Module-4 Desktop App Continuation. This week we continued to develop Desktop App. We added Main Features. Add User  : Once the product user is logged in he should be able to add employee data to the database. Therefore an Add user button is provided.   Employee name and data can be updated. Upload image button pops up a window to add file from device.   Start and Stop Camera/Capture : Buttons to Start and stop Capturing the video source . It Starts a new window streaming the live video input. Active Entries: The Captured faces from the video source is updated and displayed on the app. The Recognized face name is displayed. Logout : Button for current user to logout. Application Snapshot:

  MODULE-4 This week we did module-4 i.e Desktop App.  Why Desktop App? The consumers of our product will be accessing CCTV Cameras and hence Desktop apps are better. Desktop apps are usually the preferred platform for Administrators We will be developing it using the EEL framework. Why EEL Framework? Eel is a light-weight Python library for making simple offline HTML/JS GUI apps, with full access to Python capabilities and libraries. Eel hosts a local webserver, then lets you annotate functions in Python so that they can be called from Javascript, and vice versa. EEL  ARCHITECTURE  Code Snippets : EEL Code: Output :

                                   MODULE-3  DATABASE This Week we Established Database .We use FireBase which is a NOSQL Database . We Used FireBase Because : It provides User Authentication. Provides Real-Time Cloud Storage. Provides Flexible API for easy end developer Implementation. Configuration of Database : Once we create firebase , we get the credentials to acces the firebase features,without which we cannot work on it . The credential  is a json file which will be verified using certificate. All these are implemented using a python library provided by firebase called firebase_admin. Below is the Code for Intializing Firebase. User Authentication: Every Enterprise using the product will be given a login credential.  They can be authenticated from other accounts provided by google or other recognized organisations. Therefore it is a fairly simple process for authentication.  Below is an example. Cloud Storage: FireBase Provides Free Cloud Storage Where we can store our Data like

Last Week we saw various Face detection Models,But the important thing is to recognize those detected Faces. There are various Face Recognition Models out there. After Various studies, We have Chosen Dlib's Face Recognition model for our Project.  Contribution: Tharun K -  Working of Euclidean Distance Prashanth K - Open source Face_Recognition/deepface  models Manjunath A - Code Implementation Hanumesh V T - Evaluating Test Cases.  How do we differentiate between Two Faces? Every Face has its own unique descriptors called Face Descriptors. The Above Image Shows Face Descriptors and their respective Values. These Values are Unique for every Face .  In Dlib's model, There are 128 Face Descriptors. These Descriptors are stored in a 128-Bit Array .So When Two Faces are to be compared ,It is Done using  Euclidean Distance. Fig. Formula to Measure Euclidean Distance. The Euclidean Distance tells us How Close or Similiar two given faces are. The Lower the distance between them ,the s

  Weekly Update: 03-05-2021 Studied various ways and methods to obtain Video stream and their Pre-processing Techniques. Thus Concluded and developed Code for face detection. Details is as Follows. This week we compared different face detection models based on their performance. The two models we majorly focused on are 1.    Haar Cascade :           Object Detection using Haar feature-based cascade classifiers is an effective object detection method proposed by Paul Viola and Michael Jones in their paper, "Rapid Object  Detection using a Boosted Cascade of Simple Features" in 2001. It is a machine learning based approach where a cascade function is trained from a lot of positive and negative images. It is then used to detect objects in other images. 2.    Dlib’s Histogram of Oriented Gradients (HOG) The principle behind the histogram of oriented gradients descriptor is that local object appearance and shape within an image can be described by the distribution of intensity

Weekly Update :  26-04-2021. MODULES: 1.Face detection 2.Face Recognition 3. Database  4. Desktop app 5. Integration and Testing  6.Other Addons. FACE DETECTION FROM STREAMING SOURCE Studied various ways and methods to obtain Video stream and their Preprocessing Techniques. Thus Concluded and developed Code for face detection. Details is as Follows. 1. The Core Component of this project  is Capturing Faces and recognizing it. This is done Using Python Programming Language.  2. The Face Capturing is Done Using OpenCV Library which provides a real-time optimized Computer Vision library, tools, and hardware.   3. The Library Extracts Frames from the Video Stream obtained by the hardware like Camera and Other Devices. 4. Using Convolutional Neural Networks , we detect face from the Frames.