Naila Hamid

I am currently a PhD candidate, Research Assistant and Visiting Lecturer at Punjab University, College of Information Technology, Pakistan, from where I received a BS degree in software engineering in 2012 and an MPhil degree in computer science in 2014. My research focuses on the fusion of geometric and chromatic information for improving low-level computer vision tasks. I am currently working with Dr. Nazar Khan for my PhD research.



Computer Vision and Machine Learning lab

PUCIT, old campus, Lahore



I have taught following courses at BS and MSc level:

·         Computer Organization and Assembly Language

·         Programming Fundamentals

·         Object Oriented Programming

·         Data Structures and Algorithms

·         Computer Networks

·         Linear Algebra

·         Discrete Mathematics


Research Projects:


Condition Monitoring of Roads in Winter Conditions

with Nazar Khan, Kashif Murtaza and Raqib Omer


In this work, we propose an automated computer vision based road condition monitoring solution in winter conditions. Our dataset includes road conditions such as fully covered with snow, partially covered, bare and partially bare. We treat each image independently and focus on reliable road region extraction followed by classification via chromo-geometric approaches.


Keywords: road detection, road condition classification, clustering, line segments, chromo-geometric approaches.

Road Region Refinement algorithm

with Nazar Khan and Kashif Murtaza


In road detection, sometimes a road boundary is cropped excessively and sometimes the road shoulder is also included in the road. One obvious remedy of these problems is to automatically expand/shrink the road mask to achieve greater accuracy. Our road region refinement algorithm is based on this idea. We use chromatic and geometric measures for the solution.


Keywords: road mask, vanishing point, line segments, chromo-geometric approaches.



LSM: Perceptually Accurate Line Segment Merging

with Nazar Khan


Existing line segment detectors tend to break up perceptually distinct line segments into multiple segments. We propose an algorithm for merging such broken segments to recover the original perceptually accurate line segments. The algorithm proceeds by grouping line segments on the basis of angular and spatial proximity. Then those line segment pairs within each group that satisfy novel, adaptive mergeability criteria are successively merged to form a single line segment. The adaptive mergeability criteria are based upon geometric and chromatic ques. The solution with geometric measures is available at  


Keywords: line segments, line segment detection, line detection, grouping, merging, spatial proximity, angular proximity, perception, Gestalt, perceptually accurate line segments, quantitative evaluation.




Naila Hamid, Nazar Khan, “LSM: perceptually accurate line segment merging,” J. Electron. Imaging 25(6), 061620 (2016), doi: 10.1117/1.JEI.25.6.061620.