Jana Zujovic
Northwestern University
14 Papers
44 Citations
Jana Zujovic is an academic researcher from Northwestern University. The author has contributed to research in topics: Image texture & Similarity (network science). The author has an hindex of 9, co-authored 14 publications.
Chat about Author
Papers
Structural Texture Similarity Metrics for Image Analysis and Retrieval
TL;DR: New metrics for texture similarity are developed that accounts for human visual perception and the stochastic nature of textures and outperform peak signal-to-noise ratio, structural similarity metric (SSIM) and its variations, as well as state-of-the-art texture classification metrics, using standard statistical measures.
Classifying paintings by artistic genre: An analysis of features & classifiers
Jana Zujovic,Lisa Gandy,Scott E. Friedman,Bryan Pardo,Thrasyvoulos N. Pappas +4 more
- 23 Oct 2009
TL;DR: An approach to automatically classify digital pictures of paintings by artistic genre that better addresses the task of classifying consumer-quality digital captures than other existing approaches is described.
Image Analysis: Focus on Texture Similarity
Thrasyvoulos N. Pappas,David L. Neuhoff,H. de Ridder,Jana Zujovic +3 more
- 09 Jul 2013
TL;DR: This work examines the relation of STSIMs to existing models of texture perception, texture analysis/synthesis, and texture segmentation, and highlights the importance of signal characteristics and models of human perception, both for algorithm development and testing/validation.
Perceptual similarity metrics for retrieval of natural textures
Jana Zujovic,Thrasyvoulos N. Pappas,David L. Neuhoff +2 more
- 23 Oct 2009
TL;DR: Experimental results with a database of 748 distinct texture images, indicate that the new metric outperforms the other metrics in the retrieval of identical textures, according to a number of standard statistical measures.
Effective and efficient subjective testing of texture similarity metrics
TL;DR: Experimental results and comparisons with structural texture similarity metrics demonstrate both the effectiveness of the proposed subjective testing procedure and the performance of the metrics.
14