Fatih Porikli

Papers

Total Citations

H-Index

About

Fatih Porikli is a prominent researcher specializing in computer vision, machine learning, and intelligent systems, with particular emphasis on image classification and active learning methodologies. His work addresses a fundamental challenge in modern artificial intelligence: how to build accurate recognition systems while minimizing the costly burden of data labeling. Porikli's most notable contributions center on active learning frameworks designed to improve classification efficiency. His 2010 paper on multi-class batch-mode active learning for image classification, which has garnered 22 citations, tackles the practical demands of robotics and surveillance systems, where accurate object recognition is mission-critical. By developing smarter strategies for selecting the most informative training samples, his research helps reduce the annotation effort required to achieve high classification performance. His subsequent 2012 work on coverage-optimized active learning for k-NN classifiers extends this vision to fast, training-free recognition pipelines essential for real-time robotic applications such as exploration and rescue operations. Through these contributions, Porikli has helped bridge the gap between theoretical machine learning and real-world deployment, making intelligent vision systems more practical and scalable. His research remains highly relevant to students and practitioners working at the intersection of robotics, computer vision, and data-efficient learning.