SVTRv2X: Enhanced scene text recognition via self-distilled mixture-of-experts. [PDF]
PLoS OneGuo J +5 more
europepmc +1 more source
Trends and Prospects of Biometrics: From Sensing to Perception and Cognition. [PDF]
Sensors (Basel)Cao Z, Schmid N, Pang L.
europepmc +1 more source
Detection and Recognition of Bilingual Urdu and English Text in Natural Scene Images Using a Convolutional Neural Network-Recurrent Neural Network Combination with a Connectionist Temporal Classification Decoder. [PDF]
Sensors (Basel)Kubra KT +5 more
europepmc +1 more source
An End-To-End Speech Recognition Model for the North Shaanxi Dialect: Design and Evaluation. [PDF]
Sensors (Basel)Qin Y, Yu F.
europepmc +1 more source
Gaoya dianqi随着社会对可持续发展的日益关注，电网绿色基建档案管理成为了电网实现节能减碳和数字化发展目标的重要推手，其中，档案管理的智能化识别是实现上述目标的关键步骤。针对线下收集电网基建档案内容的智能识别，文中提出一种基于改进长短期记忆（long short-term memory，LSTM）—连接时序分类（connectionist temporal classification，CTC）的电网基建档案电子化智能识别方法。该方法首先提取电网基建档案的图像数据 ...
陈然 +7 more
doaj
A deep learning approach for line-level Amharic Braille image recognition. [PDF]
Sci RepAsfaw NA, Belay BH, Alemu KM.
europepmc +1 more source
Attention-based handwritten Chinese recognition for power grid maintenance documents. [PDF]
Sci ProgXiao D +5 more
europepmc +1 more source
Phoneme-Aware Hierarchical Augmentation and Semantic-Aware SpecAugment for Low-Resource Cantonese Speech Recognition. [PDF]
Sensors (Basel)Zhang L, Wu S, Wang Z.
europepmc +1 more source
A dual-stream deep learning framework for continuous sign language recognition to enhance communication accessibility in the Ha'il region. [PDF]
Sci RepHarrouch H +3 more
europepmc +1 more source
OCRNet a robust deep learning framework for alphanumeric character recognition to assist the visually impaired. [PDF]
Sci RepNagasubramanian A +6 more
europepmc +1 more source