… To solve the above problems, we propose using the CNNbased character recognition …
efficient and accurate text recognition. The discriminative features learned from CNN models have …

… character detection and Non-Maximum Suppression (NMS) are employed to find a word
candidate. To handle errors in classifier … CNN model for natural scene character recognition and …

… scene text recognition method inspired by human cognition mechanisms, in which a sliding
window and a character classifier … and Chinese scene text recognition; 3) The recognition …

… rate of scene text recognition based on CRNN, we explore different deeper CNN architectures
… One mainly concentrates on developing a powerful character classifier and then connects …

… the domain of scene text recognition. In this paper, a deep learning-based classifier combination
… of language identification from multi-lingual scene text images. In this work, a minimalist …

… A new approach for real-time scene text recognition is proposed … ter detection, and a back-end
Bi-RNN performs characterlevel … scene text recognition with correction and classification. …

… scene text detection by proposing a novel text-attentional convolutional neural network (Text-CNN…
against the CNN classifier used in [1] and [2] (referred as CNN-W). The performance of …

… techniques [4, 8–11] have been reported in recent years that tend to train their own scene
character classifiers. Most of these methods follow a bottom-up approach to group the …

… [6] provided an end-to-end pipeline for STR, where they perform multi-scale character
detection via SW classification. Features are first extracted by chosen entries in a HOG descriptor …

… as script identification, text/non-text classification and text-to-… directions on scene text
detection and recognition that need to … identification, text/non-text image classification, scene text …