Keshav Narayan

Papers

Total Citations

H-Index

About

Keshav Narayan is a researcher whose work lies at the intersection of computer vision and machine learning, with a particular focus on household object recognition. In his most-cited paper, "A Study of Household Object Recognition Using SIFT-Based Bag-of-Words Dictionary and SVMs" (2015), Narayan explored a classic yet foundational approach to visual recognition, combining Scale-Invariant Feature Transform (SIFT) features with a bag-of-words dictionary and support vector machines (SVMs). This work, garnering 5 citations, demonstrates his early contributions to developing robust methods for identifying everyday objects in cluttered environments—a key challenge for robotics and smart home applications. While his citation count is modest, Narayan's research addresses the practical need for systems that can understand and interact with their surroundings, laying groundwork for more advanced perception pipelines. His focus on combining traditional feature extraction with machine learning classifiers reflects a commitment to building reliable, interpretable models. For students and researchers, Narayan's work serves as a clear example of how foundational techniques in computer vision remain relevant, offering a stepping stone for exploring more complex deep learning approaches in object recognition.