In this paper, we propose a novel segmentation-free approach for keyword search in historical typewritten documents combining image preprocessing, synthetic data creation, word sp...
Basilios Gatos, Thomas Konidaris, Kostas Ntzios, I...
Content-Based Image Retrieval (CBIR) is one of the most active research areas in recent years. Many visual feature representations have been explored and many systems built. Howev...
A conventional color histogram (CCH) considers neither the color similarity across different bins nor the color dissimilarity in the same bin. Therefore, it is sensitive to noisy i...
A novel algorithm is proposed to learn pattern similarities for texture image retrieval. Similar patterns in di erent texture classes are grouped into a cluster in the feature spac...
In this paper, we propose a novel metric learning method based on regularized moving least squares. Unlike most previous metric learning methods which learn a global Mahalanobis d...