Self-supervised deep reconstruction of mixed strip-shredded text documents
نویسندگان
چکیده
منابع مشابه
Combining Forces to Reconstruct Strip Shredded Text Documents
In this work, we focus on the reconstruction of strip shredded text documents (RSSTD) which is of great interest in investigative sciences and forensics. After presenting a formal model for RSSTD, we suggest two solution approaches: On the one hand, RSSTD can be reformulated as a (standard) traveling salesman problem and solved by well-known algorithms such as the chained Lin Kernighan heuristi...
متن کاملFeature extraction and clustering for the computer-aided reconstruction of strip-cut shredded documents
bstract. We propose a solution for the computer-aided recontruction of strip-cut shredded documents. First of all, the visual conent of the strips is automatically extracted and represented by a umber of numerical features. Usually, the pieces of different pages ave been mixed. A grouping of the strips belonging to a same page s thus realized by means of a clustering operator, to ease the suces...
متن کاملSemi-Automatic Reconstruction of Cross-Cut Shredded Documents
We propose a new approach for cross-cut shredded document reconstruction and evaluate it on the DARPA Shredder Challenge dataset. We begin by pre-processing chads. A set of costs based on shape (gaps, overlaps, edge similarity), graphical content (ruling line alignment, text line alignment), and semantic content (character and letter combinations) is calculated and used to rank putative chad ma...
متن کاملA Modular Framework for the Automatic Reconstruction of Shredded Documents
The unshredding problem is of interest in various domains such as forensics, investigative sciences and archeology, and has therefore been approached in many different ways. This paper tries to bridge the gap between previous, disparate, efforts by proposing a modular, probabilistic, solution. Novel approaches to two of the independent subproblems are presented and shown to both have good theor...
متن کاملA Memetic Algorithm for Reconstructing Cross-Cut Shredded Text Documents
The reconstruction of destroyed paper documents became of more interest during the last years. On the one hand it (often) occurs that documents are destroyed by mistake while on the other hand this type of application is relevant in the fields of forensics and archeology, e.g., for evidence or restoring ancient documents. Within this paper, we present a new approach for restoring cross-cut shre...
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: Pattern Recognition
سال: 2020
ISSN: 0031-3203
DOI: 10.1016/j.patcog.2020.107535