… features are used to improve word spotting results in printed historical documents. In [21], a
multilingual word spotting scheme, using shape-based features of words, including: gradient, …

… -the-art word spotting performance on standard handwritten … of around 0.90 for word spotting
with a representation size of … In [7, 48], profile features were combined with the shape-based …

… Query-based word spotting can be used for linear indexing algorithm is used to immense
amount of available handwritten document images, in order to make them responsive to …

… In this thesis, we present a keyword spotting in handwritten/historical document images.
We treat the problem of word spotting/word image matching in two parts: the first one is …

… a word spotting method for handwritten Arabic documents … : a word segmenter, a shape-based
matcher for words and a … Usually word spotting system follows one type of word image …

… word recognition approach has evolved as a well-studied research problem in the field of
handwritten document image … In general, the extraction of shape-based features from an object …

… In [5], word spotting problem is addressed using a shape-based matching scheme where
segmented word images are represented by local contour features. A segmentation-free …

… for recognition of words written in Bangla script. To the best of our knowledge, the effectiveness
of the CNN for handwritten word recognition … [14] have lately proposed a shape-based …

… as shape-based, texture-based, topological or their combinations to handle several pattern
recognition … In the present work, a database of handwritten Bangla word images representing …

… In this context, field-based document image retrieval will be a … Finally, a global shape-based
feature was computed for … was employed for word spotting from handwritten documents by …