Abhishek Ranjan, Shahzad Malik. Parallelizing a Face Detection and Tracking System for Multi-Core Processors.
In Proceedings of CRV 2012, Toronto, ON, Canada. p. 290-297.
This project looks at how the task of face detection and tracking can be efficiently parallelized on recent multi-core CPUs.
Shahzad Malik, Abhishek Ranjan, Ravin Balakrishnan. Interacting with Large Displays from a Distance with Vision-Tracked Multi-Finger Gestural Input.
In Proceedings of ACM Symposium on User Interface Software Technology (UIST) 2005, Seattle, WA, USA. p. 43-52.
Also invited to The Best of UIST 2005 at ACM SIGGRAPH 2006, Boston, MA, USA. Article No. 5.
Shahzad Malik. A Sketching Interface for Modeling and Editing Hairstyles.
In Proceedings of Eurographics Workshop on Sketch Based Interfaces and Modeling (EGSBM) 2005, Dublin, Ireland. p. 185-194.
Modeling detailed hairstyles for virtual 3D characters is a difficult and time-consuming process with existing 3D modeling tools. This project aims to simplify the process by presenting an intuitive sketching interface to model 3D hairstyles using a pressure-sensitive tablet.
Shahzad Malik, Joe Laszlo. Visual Touchpad: A Two-handed Gestural Input Device.
In Proceedings of ACM International Conference on Multimodal Interfaces (ICMI) 2004, State College, PA, USA. p. 289-296.
The Visual Touchpad is a low-cost alternative to more expensive multi-finger touch-sensitive hardware. Using two off-the-shelf web cameras and simple computer vision algorithms, the Visual Touchpad allows multiple fingertip positions to be detected for all five fingers of each hand, allowing for rich two-handed and multi-finger interactions.
Chris McDonald, Shahzad Malik, Gerhard Roth. Hand-based Interaction in Augmented Reality. In Proceedings of IEEE International Workshop on Haptic Audio Visual Environments and their Applications (HAVE) 2002, Ottawa, Ontario, Canada. p. 55-59.
Shahzad Malik, Chris McDonald, Gerhard Roth. Hand Tracking for Interactive Pattern-based Augmented Reality. In Proceedings of IEEE and ACM International Symposium on Mixed and Augmented Reality (ISMAR) 2002, Darmstadt, Germany. p. 117-126.
Shahzad Malik, Gerhard Roth, Chris McDonald. Robust 2D Tracking for Real-time Augmented Reality. In Proceedings of Vision Interface (VI) 2002, Calgary, Alberta, Canada. p. 399-406.
Dmitry O. Gorodnichy, Shahzad Malik, Gerhard Roth. Affordable 3D Face Tracking Using Projective Vision.
In Proceedings of Vision Interface (VI) 2002, Calgary, Alberta, Canada. p. 383-390.
We developed a real-time stereo (two-camera) face tracking system using standard USB web cameras. This allowed us to reconstruct 3D position and orientation information of a user's face and head, which could be used to control the movement of a virtual object in 3D space.
Dmitry O. Gorodnichy, Shahzad Malik, Gerhard Roth. Nouse 'Use Your Nose as a Mouse' - a New Technology for Hands-free Games and Interfaces.
In Proceedings of Vision Interface (VI) 2002, Calgary, Alberta, Canada. p. 354-360.
We developed a robust and real-time nose-tracking system using a standard web camera that allowed us to reliablity manipulate the mouse cursor and simple 2D video games in a hands-free manner. This project received considerable world-wide press coverage including CNN, CBC, New Scientist, and the Discovery Channel.
Sanjay Addicam, Shahzad Malik, Phil Tian. Building Intelligent Systems: Utilizing Computer Vision, Data Mining, and Machine Learning.
Intel Press, 2013.
This book investigates how computer vision, machine learning, and data mining can be used together to build smarter devices and systems. We explore some of the practical considerations of using artificial intelligence in the real world, tackling issues that are often overlooked in academic circles, such as performance optimization, benchmarking, robustness, and privacy.
Shahzad Malik. An Exploration of Multi-finger Interaction on Multi-touch Surfaces.
Ph.D. Thesis. University of Toronto, September 2007.
My Ph.D. thesis explores the design space of multi-finger interaction techniques for multi-touch devices. It presents a number of new approaches and widgets for using multiple fingers in a user interface, and it looks at how finger span could be used as an input modality. It also proposes and evaluates the performance of a computer vision based multi-touch input device that makes use of commodity web cameras.
Shahzad Malik. Robust Registration of Virtual Objects for Real-time Augmented Reality.
Masters Thesis. Carleton University, April 2002.
My Masters thesis presents the design and implementation of a robust pattern-based augmented reality system that tracks known planar patterns in real-time using computer vision techniques. Virtual 2D and 3D objects can then be augmented onto these patterns based on the plane’s orientation. I received some press coverage from this work in Yes Magazine back in 2004.
Shahzad Malik. Dynamic LOD Representation of Interactive 3D Worlds.
Honours Thesis. Carleton University, April 2000.
My undergraduate thesis presents the design and implementation of a simple and elegant system for dynamic detail levels of regularly spaced grids of elevation data. This allows for detailed visualizations of 3D terrain at real-time frame rates. Here is an old Win32 Demo if you're interested.
Real-time Hand Tracking for Interaction
This is a course project for CSC2503H Computational Vision at UofT. The system can track a user's hands and fingers in real-time (without the use of any special markers or gloves) in order to interact with a graphical user interface in either 2D or 3D.
Digital Face Replacement in Photographs
This is a course project I worked on for CSC2530H Visual Modeling at UofT. The basic idea is to be able to replace a person's face in a single photograph, under some arbitrary illumination, with that of another person.
Physically-based Animation of Humanoid Swimming
This is a course project I worked on for CSC2529H Computer Animation at UofT. We created a physically-based animation system to allow a humanoid 3D model to swim. The character applies simulated muscle forces in order to drive the body through the motions of a breaststroke. The interaction between the moving body parts and a fluid dynamics system results in drag forces that cause the swimmer’s body to be thrust forward.
Hand Printed Character Recognizer Using Neural Networks
This was my 4th year AI project at Carleton, which involved researching and implementing hand-printed character recognition technology using neural networks. The implementation turned out pretty good; even with a small training set it could recognize hand-written digits about 70% of the time. I'm almost certain that with a training set of around 1000 examples, the performance of the character recognizer could be increased to the 90% accuracy range.
The Govinda Epidemic
Get informed about Govindaness, a debilitating disease named after Bollywood star Govinda Ahuja.
Technologies for Improving the Accuracy of Depth Cameras
US Patent 9,602,796
Filed June 2013, Issued March 2017
Rohan Chandra, Abhishek Ranjan, Shahzad Malik
Parallel Face Detection and Tracking System
US Patent 9,292,753
Filed November 2012, Issued March 2016
Abhishek Ranjan, Shahzad Malik, Phil Hubert, Umesh Patel, Faizal Javer, Haroon Mirza, Bill Colson
Method and Apparatus for Measuring Audience Size for a Digital Sign
US Patent 8,766,914
Filed July 2012, Issued July 2014
Shahzad Malik, Abhishek Ranjan, Phil Hubert, Umeshbhai Patel, Bill Colson, Haroon Mirza, Faizal Javer
Method and Apparatus for Selecting an Advertisement for Display on a Digital Sign
US Patent Application (13/634,143)
Filed July 2012
Phil Tian, Sanjay Addicam, Chiranjeevi Kunapareddy, Shweta Phadnis, Shahzad Malik
Video Analytics Test System
US Patent Application (13/531,646)
Filed June 2012
Sanjay Addicam, Shahzad Malik, Abhishek Ranjan, Shweta Phadnis, Jose Avalos
Method and Apparatus for Selecting an Advertisement for Display on a Digital Sign According to an Approaching Object
US Patent Application
Filed April 2012
Sanjay Addicam, Shahzad Malik, Abhishek Ranjan, Shweta Phadnis, Jose Avalos
Digital Advertising System
US Patent Application
Filed January 2012
Andrew Kuzma, Brad Vrabete, Sanjay Addicam, Shahzad Malik, Abhishek Ranjan, Shweta Phadnis, Phil Tian, Chiranjeevi Kunapareddy
Method and System for Audience Measurement and Targeting Media
US Patent Application (20090217315)
Filed February 2008
Shahzad Malik, Haroon Mirza
This was a company I co-founded in 2006 which developed real-time audience measurement and retail intelligence solutions. Our technology used small video cameras and real-time computer vision algorithms to detect faces and people for measuring viewership of digital signage or estimating traffic flow patterns in a retail store. Intel Corporation acquired our company in 2010.
Home Remedies Web
This is a content-based website that I am involved with which focuses on the natural health space. It contains detailed articles about various home remedies for common health conditions, as well as the health benefits of many natural and herbal products.
Deaf Culture Centre Interactive Art Exhibit
I developed an interactive art installation to help showcase the expressiveness of sign language for the Deaf Culture Centre. The system used a web camera to track a user's hands in real-time to create colorful 3D shapes based on the speed, shape, and direction of hand motion. The full system was installed in 2006 at the Deaf Culture Centre in Toronto's Distillery District, and it is still in operation to this day.
This was a fun side venture during my Masters and PhD days, where I got a chance to dabble in the PC-based casual games market. I developed a puzzle action game called Bubble Frenzy, a scrambled word game called Mumbo Jumbo, a Sudoku game called Sudoku XP, and a webcam game called Motion Bubbles. If you have a clunky old PC, some of these games might still work for you!
This was a small little venture I was involved with in 1999, which basically attempted to create localized portal sites for various colleges or universities. Sites existed for Wilfrid Laurier University and the University of Calgary. The site featured a used book exchange, a ride sharing service, and campus-specific news updates and event information. In some ways, it had elements of recent web-based services and apps on Facebook, but the site never really caught on at the time and we eventually shut it down.
This was a technology-oriented news site I was involved with from 1999-2001, with a focus towards news coverage of the PC gaming scene. I was responsible for coding the Perl CGI scripts, which mainly involved ongoing additions or modifications to the web-based publishing system and back-end database.
Amen: The Awakening
This was a game I worked on at Cavedog Entertainment in Seattle, WA in 1997/98. It was going to be an "epic" 3D action/adventure game in the spirit of Half-Life, but with much more power and passion and drama. Unfortunately the project was cancelled after being 3 years under development, but it was fun technology to work on while it lasted.
Radix: Beyond the Void
This was a video game I worked on way back in 1994/95 with a group of friends, when everyone was playing games in MSDOS, messing around with silly things like IRQs, EMM, and config.sys files. Ah, the good ole days. This game was eventually published by Epic Games, who are better known these days as the developers of Unreal and Unreal Tournament. Building and shipping this game was an amazing learning experience from both a software development as well as business standpoint.
smalik [at] cs [dot] toronto [dot] edu