Cookie Name	Cookie Description	When not logged in	When logged in
prima_cookies	Remembers whether you have already closed this message.	Yes	Yes
prima_notice	Remembers if you have alreaded viewed any notice/warning message(s). Such a message is used to inform users of potential downtime or issues that might affect the normal operation of the website. It is set to expire after the date when such notice is obsolete (eg after an expected downtime/error is fixed).	Yes	Yes
PHPSESSID	The ID of your session.	Yes	Yes
__utma	This is set by Google Analytics. It stores each user's amount of visits, and the time of the first visit, the previous visit, and the current visit.	Yes	Yes
__utmb, __utmc	These are set by Google Analytics. They are used to check approximately how long you stay on a site (when a visit starts, and approximately ends).	Yes	Yes
__utmz	This is set by Google Analytics. It stores where a visitor came from (search engine, search keyword, link).	Yes	Yes

RDCL2019 Submitted Methods

Method	Authors and Description
BINYAS	Showmik Bhowmik, Soumyadeep Kundu, Ram Sarkar - Department of Computer Science and Engineering, Jadavpur University, India. Mainly based on connected component analysis and morphology.
BKZA	Duc Nguyen, Cuong Ha - Ho Chi Minh City Uni-versity of Technology. Using deep learning to segment page and heuristic algorithms for post-processing.
DSPH	Tan Lu, Ann Dooms - Vrije Universiteit Brussel. Document Segmentation with Probabilistic Homogeneity, using: binarization, text / non-text classification, text region extraction, non-text structure extraction.
JBM	Klára Janoušková, Michal Bušta and Jiří Matas - Czech Technical University, Prague. The method uses following steps: Obtaining segmentation maps from a CNN, post-processing based on polygons, OCR (CNN-based).
LingDIAR	Dou Haobin - Lingban Tech Co., Ltd. Based on a multi-task deep network model trained with synthetic document images.
MHS	Tuan Anh Trana, Nam Quan Nguyena, Quoc Thang Nguyena, Hai Duong Nguyenb, Soo Hyung Kimc - (a): HoChiMinh National University City - HCMUT, Viet Nam & Cinnamon AI, (b): Concor-dia University, Canada, (c): Chonnam National University, Gwangju, Republic of Korea. Based on following steps: Negative/positive image detection, binarization, text / non-text classification, text segmentation, image classification, region refinement + labelling, OCR.
MICS	Yassine Ouali, Céline Hudelot - MICS, Centrale-Supélec, France. Method similar to Pyramid Scene Parsing Network in combination with training on augmented data and final inference / post-processing steps.
TAQ	Nam Quan Nguyen, Tran Hai Anh Vo, Quoc Thang Nguyen - Cinnamon AI Lab Inc. Based on following steps: text / non-text classification, text region improvements / smoothing, non-text classification.
ZLCW	Chendi Zang, Hui Li, Xinfeng Chang, Yaqiang Wu - Lenovo Research. Using FCN(fully convolutional networks) trained with 15 original training images, augmented to 3960 images (using cropping, gaussian blur, adding random noise as well as colour jittering).
FRE11	ABBYY FineReader Engine 11 with PRImA FineReader-to-PAGE wrapper. Not trained or optimised for this competition.
FRE12	ABBYY FineReader Engine 12 with PRImA FineReader-to-PAGE wrapper. Not trained or optimised for this competition.
Tess.4	Tesseract 4 with PRImA Tesseract-to-PAGE wrap-per. Not trained or optimised for this competition.

PRImA

RDCL2019 Submitted Methods