Our experiments show that features extracted from an adapted-CNN handsomely outperform hand-designed features on both spotting and recognition tasks for printed ...
In this paper, we use both CNN-adaptation and CNN feature extraction techniques to build robust representations for word spotting and recognition of printed and ...
Our experiments show that features extracted from an adapted-CNN handsomely outperform hand-designed features on both spotting and recognition tasks for printed ...
Request PDF | On Aug 1, 2015, Arjun Sharma and others published Adapting off-the-shelf CNNs for word spotting & recognition | Find, read and cite all the ...
Adapting off-the-shelf CNNs for word spotting & recognition. A Sharma. 2015 13th International Conference on Document Analysis and Recognition …, 2015. 53, 2015.
Dec 20, 2017 · We show our Attribute CNNs to achieve state-of-the-art results for segmentation-based word spot- ting on a large variety of data sets. Keywords ...
Evaluating Word String Embeddings and Loss Functions for CNN-Based Word Spotting ... Adapting off-the-shelf CNNs for word spotting & recognition · Arjun Sharma ...
Adapting off-the-shelf CNNs for word spotting & recognition pp. 986-990. Evaluation of deep convolutional nets for document image classification and ...
Abstract—Deep convolutional features for word images and textual embedding schemes have shown great success in word spotting. In this work, we follow these ...
Dec 5, 2017 · Pramod Sankar, “Adapting off-the-shelf CNNs for. Word Spotting & Recognition,” in International Conference on Docu- ment Analysis and ...