Joint Line Segmentation and Transcription for End-to-End Handwritten Paragraph Recognition

Authors: Theodore Bluche

NeurIPS 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We carried out experiments on two public datasets of handwritten paragraphs: Rimes and IAM.
Researcher Affiliation Industry Théodore Bluche A2i A SAS 39 rue de la Bienfaisance 75008 Paris tb@a2ia.com
Pseudocode No No pseudocode or clearly labeled algorithm blocks were found in the paper.
Open Source Code No The paper does not provide an explicit statement about open-sourcing the code or a link to a code repository.
Open Datasets Yes We carried out the experiments on two public databases. The IAM database [29] is made of handwritten English texts copied from the LOB corpus. The Rimes database [1] contains handwritten letters in French.
Dataset Splits Yes The IAM database [29] is made of handwritten English texts copied from the LOB corpus. There are 747 documents (6,482 lines) in the training set, 116 documents (976 lines) in the validation set and 336 documents (2,915 lines) in the test set. The Rimes database [1] contains handwritten letters in French. The data consist of a training set of 1,500 paragraphs (11,333 lines), and a test set of 100 paragraphs (778 lines). We held out the last 100 paragraphs of the training set as a validation set.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running the experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers.
Experiment Setup Yes The networks are trained with RMSProp [36] with a base learning rate of 0.001 and mini-batches of 8 examples, to minimize the CTC loss over entire paragraphs.