Akash Basudevan

Akash Basudevan

ABOUT ME
Deep Learning Researcher
Deep Learning Researcher

I have experience of 2+ years in the building and implementing of AI integrated solutions for business use cases across multiple domains specifically computer vision and natural language processing.

Having participated in various machine learning hackathons I have exposure to structured machine learning pipelines. He also loves participating in algorithmic challenges.

My interest lies in research roles in the field of artificial intelligence and building scalable machine learning solutions.

Hindi, English
New Delhi (+05:30)
Joined October 2017
EXPERTISE
3 years experience
I have done 2 internships in Python. One in python back end development and the other one i am currently doing which is Machine Learning ...
I have done 2 internships in Python. One in python back end development and the other one i am currently doing which is Machine Learning and Deep learning using Python only. Developed understanding of various techniques of Classification, Clustering, Regression and Dimensionality Reduction by applying them on different data sets. Also have experience in time series analysis of data. I have also worked with boto library for automation AWS management steps for an Remote Video Surveillance system .
Python 2Data science in pythonData Science
View more
2 years experience
2 years experience
2 years experience
1 year experience
2 years experience
SOCIAL PRESENCE
GitHub
Signature-Forgery-Recogntion
This repository includes the solution code we have made for axisbank challenge for the signature recognition part.
Python
1
0
2-Pass-Assembler
Based on the Instruction Set Architecture , it is a 2 pass assembler.
C
0
0
Stack Overflow
403 Reputation
0
2
10
EMPLOYMENTS
Machine Learning and Deep Learning Engineer
Nagarro
2018-01-01-Present
1) Video Analytics on Edge(Google coral, Nvidia Jetson): -> Smart Factory: Worked on the POC for safety accessory(Hard hat, etc) detectio...
1) Video Analytics on Edge(Google coral, Nvidia Jetson): -> Smart Factory: Worked on the POC for safety accessory(Hard hat, etc) detection in a particular zone around the workstation which consisted of robotic arms. The arms would work only if the safety conditions were met. -> Working on a large scale security system using face detection, face recognition, and face occlusion detection. -> Worked on analyzing social distancing from a CCTV footage. -> Worked on high-density crowd counting which cannot be done accurately with object detection models. 2) Information Extraction -> Automatically extracting Key/ Value pairs on various types of forms. -> Automatic Information Extraction From Shipping Labels: Reduced 90% manual labor by automatically extracting name and address components from images of the delivery invoices of multiple vendors such as Amazon, FedEx, Ups, etc. -> Line Chart Knowledge Extraction: Line Chart Knowledge Extraction is a tool that automatically extracts information from research paper line graph images with a limited scope. ->Table Detection and Automatic Information Extraction from images of Tables with limited scope using GANs. 3) Natural language Processing ->Question Answering System: Implemented an end to end question answering system for a huge corpus of pdf manuals. 4) Miscellaneous ->Exploratory Data Analysis: Extensive Exploratory Data Analysis on a multi-level dataset. Built base classification models to predict intermediate features.
Python
NumPy
Matplotlib
View more
Python
NumPy
Matplotlib
Pandas
Machine Learning
Computer Vision
Data Analysis
Data Science
Deep Learning
Data science in python
View more
Summer Internship
KritiKal Solutions
2017-05-01-2017-07-01
Remote Video Surveillance: Designed and Implemented the back end for a RVS System using Python, FFMPEG and openCV. Deployed the system on...
Remote Video Surveillance: Designed and Implemented the back end for a RVS System using Python, FFMPEG and openCV. Deployed the system on AWS and completely automated AWS management steps using boto library of python. Data Augmentation: Generated different perspectives of an image using the keras library ofpython and produced over 10 million images from 0.6 million images. Made frame extraction from video 50% more efficient by splitting videos in segments and mapping the frame numbers from the large video to the splitted videos. Explored basics of Neural Networks and Regression Analysis
Python
Flask
OpenCV
View more
Python
Flask
OpenCV
Amazon EC2
Computer Vision
Keras
View more
PROJECTS
Live Bidding Desktop Application
2018
This application simulates bidding at real time. It uses JDBC and MySQL for database purposes, Swings for GUI and core java for basic im...
This application simulates bidding at real time. It uses JDBC and MySQL for database purposes, Swings for GUI and core java for basic implementation. It supports features such as adding an item for bid in real time, bidding session of 30 seconds , adding credits to the account , login/logout of the account, multiple(3-4) people bidding at a time, etc.
Java
View more
Java
View more
SIgnature Forgery DetectionView Project
AxisBank Hackathon - Won 2nd prize among 3500+ teams.
2018
Built a completely custom architecture with triplet loss for signature forgery detection where the task is to determine if a particular g...
Built a completely custom architecture with triplet loss for signature forgery detection where the task is to determine if a particular given signature is a forgery or not.
Image Processing
Computer Vision
Python 3
View more
Image Processing
Computer Vision
Python 3
Deep Learning
TensorFlow
Keras
View more