Browsing by Subject "Precision and recall"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Open Access Integrated segmentation and recognition of connected Ottoman script(S P I E - International Society for Optical Engineering, 2009-11) Yalniz, I. Z.; Altingovde, I. S.; Güdükbay, Uğur; Ulusoy, ÖzgürWe propose a novel context-sensitive segmentation and recognition method for connected letters in Ottoman script. This method first extracts a set of segments from a connected script and determines the candidate letters to which extracted segments are most similar. Next, a function is defined for scoring each different syntactically correct sequence of these candidate letters. To find the candidate letter sequence that maximizes the score function, a directed acyclic graph is constructed. The letters are finally recognized by computing the longest path in this graph. Experiments using a collection of printed Ottoman documents reveal that the proposed method provides >90% precision and recall figures in terms of character recognition. In a further set of experiments, we also demonstrate that the framework can be used as a building block for an information retrieval system for digital Ottoman archives. © 2009 Society of Photo-Optical Instrumentation Engineers.Item Open Access A new approach to search result clustering and labeling(Springer, Berlin, Heidelberg, 2011) Türel, Anıl; Can, FazlıSearch engines present query results as a long ordered list of web snippets divided into several pages. Post-processing of retrieval results for easier access of desired information is an important research problem. In this paper, we present a novel search result clustering approach to split the long list of documents returned by search engines into meaningfully grouped and labeled clusters. Our method emphasizes clustering quality by using cover coefficient-based and sequential k-means clustering algorithms. A cluster labeling method based on term weighting is also introduced for reflecting cluster contents. In addition, we present a new metric that employs precision and recall to assess the success of cluster labeling. We adopt a comparative strategy to derive the relative performance of the proposed method with respect to two prominent search result clustering methods: Suffix Tree Clustering and Lingo. Experimental results in the publicly available AMBIENT and ODP-239 datasets show that our method can successfully achieve both clustering and labeling tasks. © 2011 Springer-Verlag Berlin Heidelberg.