Apply Online (June 08 - July 19,2020)

Click here for details

GIK Undergraduate Admissions,Fall Semester 2020. Click here for details
GIK Institute's measures against Coronavirus. Click here for details


Engr. Muhammad Abdullah Akmal

Qualifications: MSc.
Research Interests: Data Mining, Cloud Computing and Services, NLP, Robotics, Image processing, Physics, Artificial Intelligence, Pattern Recognition, Blockchains
Telephone: +92-324-4600546
Website: http://


My motivation to join GiK was two folds

  1. Introduce practically in the course, by which we can improve the professional skills in the students. When they join industry they dont feel lost.
  2. Do some out of the box projects problem solving projects.


Following are my projects on which I have worked:

  1. I have applied Traditional Machine Learning approach for the anonmaly detection in the fruits. It was a funded project from the DAAD (Institute of Artificial Intelligence, Germany). It runs over a life cycle of a fruit and detect if there is any anomaly and then predict would that anomaly turn out to be bruise or not. 
  2. I worked on Table detection using the Deep Learning. This process use to classify Table and non table regions in a document. We presented this approach in the ICDAR/IAPR 2017. 
  3. Worked with the baby company of Steam engine, called Gamesessions. It provides the platform for downloading and playing a trail of a game over a span of time.
  4. Worked on Data visualisation using Neural Machine translation for the company SlantedTheory UK. Graphic visualisation from the raw dataset was created by identifying the structure of data using Seq2Seq RNN based encoder.
  5. Currently providing consultancy to the American based startup called Friendly Health. They mainly deals in digitisation for the documents for different insurer's and health agencies. I provide my consultancy to them in NLP, Machine Learning and Cloud Computing.


S. F. Rashid, A. Akmal, M. Adnan, A. A. Aslam and A. Dengel, "Table Recognition in Heterogeneous Documents Using Machine Learning," 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Kyoto, 2017, pp. 777-782.
doi: 10.1109/ICDAR.2017.132
keywords: {document image processing;learning (artificial intelligence);neural nets;optical character recognition;table layouts;table contents;heterogeneous document images;nontable elements;table recognition;heterogeneous documents;table structure recognition;modern OCR systems;non-table elements;Feature extraction;Optical character recognition software;Layout;Neural networks;Training;Image recognition;Character recognition},

Edit Profile