Omer is available for hire

Omer Ishaq

Verified Expert in Engineering

AI, Machine and Deep Learning Developer

Location

Rawalpindi, Punjab, Pakistan

Toptal Member Since

April 22, 2022

Omer is a machine and deep learning researcher, engineer, and consultant with significant experience in academic research, consulting, and developing computer vision solutions in the software industry. He is proficient with PyTorch, OpenCV, Scikit-image, Scikit-learn, Google-Cloud-VMs, Google-Cloud-Run, and Google-Storage. Omer's interests include image classification, segmentation, object detection, clustering, low shot learning, image registration, and facial recognition.

Computer Vision Machine Learning Artificial Intelligence (AI)Python Deep Learning Data Analytics Data Visualization Natural Language Processing (NLP)Data Analysis Python 3 PyTorch OpenCV Scikit-learn Prompt Engineering OpenAI GPT-4 API Caffe

Portfolio

National Database and Registration Authority (NADRA)

Computer Vision, Deep Learning, Hugging Face, PyTorch, Python 3...

Freelance Work for DTEC DDC

OpenCV, Scikit-image, PyTorch, Python 3, Deep Learning, Python, Leadership...

Air University, Pakistan

Deep Learning, Image Analysis, Machine Learning, Computer Vision...

Experience

Image Processing - 16 years Machine Learning - 12 years Deep Learning - 7 years Python 3 - 7 years PyTorch - 6 years Scikit-learn - 5 years OpenCV - 5 years Natural Language Processing (NLP) - 1 year

Availability

Part-time

Preferred Environment

Ubuntu, Spyder, Visual Studio Code (VS Code), OpenCV, PyTorch, Scikit-learn

The most amazing...

...project I've designed and developed recently is a vision-based system for detecting, identifying, and reading product and label information in supermarkets.

Work Experience

Senior Data Scientist

2022 - PRESENT

National Database and Registration Authority (NADRA)

Spearheaded a national project using machine learning to expand the tax base in Pakistan. Led the design and development of this project, using decision trees for the categorization of individuals into different tax brackets.
Led a vision-based project for real-time verification of documents using deep learning. Used OCR to automatically extract English and Urdu information from multilingual documents. The project is deployed on a national scale.
Served as the technical lead and successfully developed a solution for the neural translation of names and addresses from English to Urdu.
Led a project to use LLMs for document retrieval based on the topic context. Designed a chatbot service for internal use in NADRA.

Technologies: Computer Vision, Deep Learning, Hugging Face, PyTorch, Python 3, Large Language Models (LLMs), OpenCV, Flask, LSTM, Chatbots, Artificial Intelligence (AI), Natural Language Processing (NLP), Regular Expressions, Pandas, Language Models, Python, Prompt Engineering, Leadership, GPT, OpenAI GPT-4 API, Image Recognition, Amazon Web Services (AWS), Data Science, OpenAI GPT-3 API, Data Analysis, Data Visualization, BERT, Text to Speech (TTS), Predictive Modeling, Classification, Data Analytics, You Only Look Once (YOLO), Computer Vision Algorithms

Consultant (Deep Learning and Image Analysis)

2018 - PRESENT

Freelance Work for DTEC DDC

Developed a computer vision system for detecting, identifying, and reading product and label information from shelves in supermarkets.
Built object detection, classification, and OCR pipelines.
Deployed massively multi-threaded solutions on Google Cloud Run.
Created a tool for unsupervised image clustering.

Technologies: OpenCV, Scikit-image, PyTorch, Python 3, Deep Learning, Python, Leadership, Artificial Intelligence (AI), Image Recognition, Computer Vision, Data Science, Predictive Modeling, Classification, Data Analytics, You Only Look Once (YOLO), Computer Vision Algorithms

Assistant Professor (Image Analysis and Deep Learning)

2016 - 2018

Air University, Pakistan

Supervised graduate students in the field of deep learning and computer vision.
Spearheaded a project for the creation of a Kinect-based tool for automated assistance in physiotherapy.
Oversaw a project on vision-based facial recognition.

Technologies: Deep Learning, Image Analysis, Machine Learning, Computer Vision, Genetic Algorithms, Python, Leadership, Artificial Intelligence (AI), Image Recognition, Predictive Modeling, Classification, Computer Vision Algorithms

Ph.D. Candidate (Full-time Employee at Uppsala University)

2012 - 2016

Uppsala University

Developed an image processing and deep learning tool for the detection of fluorescent biomarkers in microscopy images using Caffe.
Created a tool for the automated measurement of the tail curvature of Zebrafish in microscopy images for assistance in high throughput screening in drug discovery. A research paper was published in International Symposium on biomedical imaging.
Developed a tool for super resolution microscopy analysis using compressed sensing. A research paper detailing the results was published in the International Conference on pattern recognition.

Technologies: MATLAB, Scikit-learn, OpenCV, Python 3, Caffe, Computer Vision Algorithms

Research Assistant (Automated Medical Image Analysis) and MS Student

2005 - 2008

Simon Fraser University

Developed a tool for statistical shape analysis of the corpus callosum in magnetic resonance images.
Created a tool for registration-based segmentation of the corpus callosum in magnetic resonance images.
Built a tool for mid-sagittal plane identification in brain MR volumes.

Technologies: MATLAB, ITK, Computer Vision Algorithms

Experience

Computer Vision System for Supermarkets

Designed and developed the deep learning and image processing-based back end for a computer vision system that can detect, identify, and read the information about product and price labels from product shelves in supermarkets.

Automated Quantification of Zebrafish Tail Deformation for High-throughput Drug Screening

https://pubmed.ncbi.nlm.nih.gov/24499782/

Zebrafish is an important vertebrate model organism in biomedical and drug discovery research. It undergoes spinal deformation on exposure to certain chemicals. I developed an automated image analysis pipeline for accurate high-throughput measurement of tail deformations in multi-fish micro-plate wells. The method resulted in an accuracy of 95%.

Detection and Classification of Fluorescent Biomarkers in Microscopy Images

A MATLAB and Caffe-based system for detecting fluorescent biomarkers in microscopy images. The biomarkers are detected by fitting normal distributions to the microscopy images. The detected candidates are parsed through a classifier differentiating between real biomarkers and noise.

Education

2012 - 2016

Ph.D. in Computer Science

Uppsala University - Uppsala, Sweden

2005 - 2008

Master's Degree in Computer Science

Simon Fraser University - Vancouver, Canada

Skills

Libraries/APIs

OpenCV, PyTorch, Scikit-learn, LSTM, Pandas

Tools

You Only Look Once (YOLO), Spyder, Scikit-image, MATLAB, ITK, ChatGPT

Paradigms

Data Science

Languages

Python, Python 3

Storage

Google Cloud

Frameworks

Caffe, Flask

Platforms

Ubuntu, Visual Studio Code (VS Code), Amazon Web Services (AWS)

Other

Image Processing, Machine Learning, Medical Imaging, Computer Vision, Artificial Intelligence (AI), Image Recognition, Classification, Computer Vision Algorithms, Deep Learning, Image Analysis, Natural Language Processing (NLP), Leadership, GPT, OpenAI GPT-3 API, Data Analysis, Data Visualization, BERT, Text to Speech (TTS), Predictive Modeling, Data Analytics, Compressed Sensing, Hugging Face, Large Language Models (LLMs), Chatbots, Regular Expressions, Genetic Algorithms, Frameworks, Language Models, Prompt Engineering, OpenAI GPT-4 API

Collaboration That Works

How to Work with Toptal

Toptal matches you directly with global industry experts from our network in hours—not weeks or months.

Share your needs

Discuss your requirements and refine your scope in a call with a Toptal domain expert.

Choose your talent

Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.

Start your risk-free talent trial

Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.

Top talent is in high demand.

Start hiring