Computer Vision and Machine Learning Lab (CVML)
Projects
Automatic Security and Surveillance System for Video Streams
[On-going]
The Islamic republic of Pakistan is the world's sixth most populous country and is placed 5th on the list of strongest nations militarily. In addition, Pakistan in Asia has much geographical importance because of its strategic location. Firstly, Pakistan is…
Smart Phone based Natural Language Description of Visual Scene
[On-going]
This project proposal implements a visual scene understanding system on a mobile phone platform. It builds on our recent work, a bottom-up approach to describing video contents in natural language. It is a part of a three-year project, and the…
Safe Farming: Crop raiding prevention from vertebrates
[On-going]
This research proposes a model of safe farming in which the crops of the farm (field) are going to be protected from vertebrates (animals and birds with a backbone). One of the main problems for the farmers in farming is…
MMI-DSS: Mobile Medical Imaging Decision Support System
[On-going]
Proposed project is step towards the development and upgrading of health facility in Pakistan, by providing e-health system at door step. We are proposing a novel computer decision supported framework for people of Pakistan, which will target basically in the…
English to Urdu Translator
[On-going]
This project relates Natural Language Processing with Speech Processing. Given any sentence in English it translates it into Urdu using specific defined dictionary. We can also add and edit words in dictionary directly. It was implemented in C#.
Methods of Voice Conversion
[On-going]
Methods related to voice conversion were explored and experimented. Basic idea of the work is to convert voice of one person to other person with same or different gender. Spectral Analysis and Linear Prediction Coding were main algorithms used in…
Design and Implementation of Efficient Information Retrieval Algorithm for Chest X-Ray Images
[On-going]
The focus of the thesis was to process chest X-ray images for identification of separate parts. Most important is the recognition of rib cages as they are of utmost importance. Rib cages are differentiated from lungs and any other…
Gait based human identification
[On-going]
Humans can be recognized based on their gait(walking style). Several body parts play significant roles in generating human gaits. These body parts are processed using image processing to generate useful features such as torso, stride, arm length, arms angle, leg…
Abstractive Video and Video Summarization
[On-going]
We are investigating on techniques for abstraction and extraction of videos. Trailer generation before the production of video and summarization after the video production are two main tasks which we are aiming at. Audio, visual and text information are the…
Discovering Video Semantics
[On-going]
We propose to automatically generate richer video semantics where semantics are defined as the theme of the video based on objects and their activities. The video semantics have great potential to help video organization, indexing and searching with focus on…
Low cost and power efficient ANPR system: An ANPR (Automatic No. Plate Recognition) System, keeping in mind the road traffic in Pakistan.
[On-going]
This research is an effort to develop a low power and cost efficient VRS (Vehicle Recognition System) using short-range wireless technologies. VRS is a system in which the image of the vehicle is captured using High Definition cameras installed at…