Talha U. Profile

0.0

(0 reviews)

You're now following

Error following user.

This user does not allow users to follow them.

You are already following this user.

Your membership plan only allows 0 follows. Upgrade here.

Successfully unfollowed

Error unfollowing user.

You have successfully recommended

Error recommending user.

Something went wrong. Please refresh the page and try again.

Email successfully verified.

$10 USD / hour

lahore,

pakistan

$10 USD / hour

It's currently 8:29 AM here

Joined September 22, 2021

0 Recommendations

Talha U.

@mdldev

0.0

(0 reviews)

0.0

$10 USD / hour

lahore,

pakistan

$10 USD / hour

N/A

Jobs Completed

N/A

On Budget

N/A

On Time

N/A

Repeat Hire Rate

Data Scientist | Machine Learning Engineer

I'm a Machine Learning Engineer with more than 4 years of professional experience. I am an expert in machine learning, data science, computer vision and Web applications. My main areas of expertise are: Machine learning, Computer Vision, NLP and Data Science - pattern recognition, classification, segmentation, object detection and tracking, recommendation system, CNNs, RNNs, GNNs, LLM Python, Django Framework, PyTorch, TensorFlow, Keras, OpenCV PostgreSQL, MySQL, NoSQL

See all Python Developers in Pakistan

Contact Talha U. about your job

Portfolio

The sugarcane industries establish agreements with farmers prior to the tillering phase of the plants, as they are interested in obtaining pre-harvest estimations of sugarcane fields to plan their production and purchasing strategies.

This project introduces a methodology for estimating the quantity of sugarcane plants during the tillering phase. It involves the utilization of object detection techniques to accurately identify and count the sugarcane plants.

Sugar cane crop estimation

11109681

Face Recognition For Attendance Management System Close the

Sugar cane crop estimation

11109681

Face Recognition For Attendance Management System Close the

Reviews

Changes saved

No reviews to see here!

Experience

Knowledge Platform

Mar 2021 - Present

I've implemented computer vision solutions for object detection, tracking, and face recognition, as well as NLP models for sentiment analysis and text classification. Developed real-time data pipelines, analyzed business requirements, and designed a predictive model using graph neural networks, replacing traditional systems.

Al-Khawarizmi Institute of Computer Science (KICS)

Sep 2019 - Feb 2021 (1 year, 5 months)

Research and development of computer vision and deep learning projects. I worked on the different models using TensorFlow, Keras, and different other libraries for experimentation for research and development.

Education

MS/M.Phil. In Computer Science

University of Central Punjab,

Pakistan

2019 - 2021

(2 years)

Bachelor of Computer Sciences

COMSATS Institute of Information Technology,

Pakistan

2014 - 2018

(4 years)

Publications

Interpretation of Expressions through Hand Signs Using Deep Learning Techniques

Springer

Our study presents an efficient solution to interpret sign language automatically using transfer learning with VGG16 architecture. The system can classify seven basic gestures representing emotions, achieving 99.98% accuracy. Comparison of performance with different architectures and optimizers further validates our approach.

COVID-19 SOP’s Violations Detection in Terms of Face Mask Using Deep Learning

IEEE

Amid the ongoing COVID-19 pandemic and the spread of variants, wearing face masks correctly is vital. Our study proposes an improved YOLOv4 model to autonomously monitor SOP compliance, detecting not just mask usage, but ensuring it covers the mouth and nose, alerting authorities for any breaches. This aids in effective pandemic management.

Intelligent Traffic Signal Automation Based on Computer Vision Techniques Using Deep Learning

IT Professional

Our goal is to alleviate urban traffic congestion via real-time signal automation. Using advanced deep learning techniques, we detect/count vehicles in real-time and adjust signal timings accordingly, enhancing traffic flow.