M
Million Meshesha
Researcher at International Institute of Information Technology
Publications - 16
Citations - 231
Million Meshesha is an academic researcher from International Institute of Information Technology. The author has contributed to research in topics: Computer science & Amharic. The author has an hindex of 7, co-authored 9 publications receiving 215 citations. Previous affiliations of Million Meshesha include International Institute of Information Technology, Hyderabad.
Papers
More filters
Journal ArticleDOI
Matching word images for content-based retrieval from printed document images
Million Meshesha,C. V. Jawahar +1 more
TL;DR: An effective word image matching scheme is proposed that achieves high performance in the presence of script variability, printing variation, degradation and word-form variants and a novel partial matching algorithm is designed for morphological matching of word form variants in a language.
Book ChapterDOI
Retrieval from document image collections
TL;DR: A novel DTW-based partial matching scheme is employed to take care of morphologically variant words to achieve effective search and retrieval from a large collection of printed document images by matching image features at word-level.
Journal ArticleDOI
Retrieval of online handwriting by synthesis and matching
TL;DR: The proposed approach provides a keyboard-based search interface that enables to search handwritten data from any platform, in addition to pen-based and example-based queries, and allows cross-lingual document retrieval across Indian languages.
Journal ArticleDOI
Optical Character Recognition of Amharic Documents
Million Meshesha,C. V. Jawahar +1 more
TL;DR: An Optical Character Recognition (OCR) system for converting digitized documents in local languages and a novel feature extraction scheme using principal component and linear discriminant analysis, followed by a decision directed acyclic graph based support vector machine classifier is proposed.
Proceedings Article
Searching in Document Images.
TL;DR: A novel partial matching approach based on dynamic time warping (DTW) is proposed to take care of word form variations and morphologically variant words become similar in image space with the new partial matching procedure.