A two-stage method for text line detection in historical documents
نویسندگان
چکیده
منابع مشابه
A Two-Stage Method for Text Line Detection in Historical Documents
This work presents a two-stage text line detection method for historical documents. In a first stage, a deep neural network called ARU-Net labels pixels to belong to one of the three classes: baseline, separator or other. The separator class marks beginning and end of each text line. The ARU-Net is trainable from scratch with manageably few manually annotated example images (less than 50). This...
متن کاملText line detection in handwritten documents
Article history: Received 13 April 2007 Received in revised form 26 March 2008
متن کاملA New Method for Text-Line Segmentation for Warped Documents
Bound documents either scanned or captured with digital cameras often present a geometrical warp that makes text-lines curled. The identification of text-lines is one of the steps for document de-warping when only a single image is available. This paper presents a new method for text-line segmentation. It is based on a simple, but effective, skew detector proposed by ÁvilaLins and simplifies th...
متن کاملA TWO-STAGE METHOD FOR DAMAGE DETECTION OF LARGE-SCALE STRUCTURES
A novel two-stage algorithm for detection of damages in large-scale structures under static loads is presented. The technique utilizes the vector of response change (VRC) and sensitivities of responses with respect to the elemental damage parameters (RSEs). It is shown that VRC approximately lies in the subspace spanned by RSEs corresponding to the damaged elements. The property is leveraged in...
متن کاملHandwritten Text Recognition for Historical Documents
The amount of digitized legacy documents has been rising dramatically over the last years due mainly to the increasing number of on-line digital libraries publishing this kind of documents. The vast majority of them remain waiting to be transcribed into a textual electronic format (such as ASCII or PDF) that would provide historians and other researchers new ways of indexing, consulting and que...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: International Journal on Document Analysis and Recognition (IJDAR)
سال: 2019
ISSN: 1433-2833,1433-2825
DOI: 10.1007/s10032-019-00332-1