Understanding Unsupervised Deep Learning for Text Line Segmentation

Ahmad Droby, Berat Kurar Barakat, Raid Saabni, Reem Alaasam, Boraq Madi, and Jihad El-Sana Abstract: We propose an unsupervised feature learning approach for segmenting text lines of hand-written document images with no labelling effort. Humans can easily group local text line features to global coarse patterns. We leverage this coherent visual perception of text lines […]

CLN8 Gene Compound Heterozygous Variants: A New Case and Protein Bioinformatics Analyses

The CLN8 disease type refers to one of the neuronal ceroid lipofuscinoses (NCLs) which are the most common group of neurodegenerative diseases in childhood. The clinical phenotypes of this disease are progressive neurological deterioration that could lead to seizures, dementia, ataxia, visual failure, and various forms of abnormal movement. In the current study, we describe […]

Optical Character Recognition Guided Image Super Resolution

  Recognizing disturbed text in real-life images is a difficult problem, as information that is missing due to low-resolution or out-of-focus text has to be recreated. Combining text super-resolution and optical character recognition deep learning models can be a valuable tool to enlarge and enhance text images for better readability, as well as recognize text […]