&lt;title&gt;Sequential neural network combination for degraded machine-printed character recognition&lt;/title&gt;

Namane, Abdelkader; Arezki, Madjid; Guessoum, Abderrezak; Soubari, E. H.; Meyrueis, Patrick; Bruynooghe, Michel

doi:10.1117/12.587162

“…As a result the graphical objects (such as rectangular enclosures, straight lines, and logos) which do not provide any useful information can be simply detected and removed using common line detection algorithms (e.g. Hough transform) or basic morphological operations, and the main steps in the processing of such documents will typically consist of skew correction (so that the extracted strings are correctly reoriented to the horizontal direction) and handwritten text recognition (Hull, 1998), (Sarfraz et al, 2005), (Guillevic & Suen, 1997), (Namane et al, 2006).…”

Section: Document Image Analysis and Map Conversion Systems: A Brief Overviewmentioning

confidence: 99%

Recent Advances in Document Recognition and Understanding

Mori¹

2011

1

0

View full text Add to dashboard Cite

In the field of document recognition and understanding, whereas scanned paper documents were previously the only recognition target, various new media such as camera-captured documents, videos, and natural scene images have recently started to attract attention because of the growth of the Internet/WWW and the rapid adoption of low-priced digital cameras/videos. The keys to the breakthrough include character detection from complex backgrounds, discrimination of characters from noncharacters, modern or ancient unique font recognition, fast retrieval technique from large-scaled scanned documents, multi-lingual OCR, and unconstrained handwriting recognition. This book aims to present recent advances, applications, and new ideas that are relevant to document recognition and understanding, from technical topics such as image processing, feature extraction or classification, to new applications like camera-based recognition or character-based natural scene analysis. The goal of this book is to provide a new trend and a reference source for academic research and for professionals working in the document recognition and understanding field.

show abstract

“…As a result the graphical objects (such as rectangular enclosures, straight lines, and logos) which do not provide any useful information can be simply detected and removed using common line detection algorithms (e.g. Hough transform) or basic morphological operations, and the main steps in the processing of such documents will typically consist of skew correction (so that the extracted strings are correctly reoriented to the horizontal direction) and handwritten text recognition (Hull, 1998), (Sarfraz et al, 2005), (Guillevic & Suen, 1997), (Namane et al, 2006). Engineering drawings and blueprints contain a large amount of information presented as both text and graphics.…”

Section: Document Image Analysis and Map Conversion Systems: A Brief Ovmentioning

confidence: 99%