A survey of methods and strategies in character segmentation
read more
Citations
Online and off-line handwriting recognition: a comprehensive survey
ASTER: An Attentional Scene Text Recognizer with Flexible Rectification
Twenty years of document image analysis in PAMI
An overview of character recognition focused on off-line handwriting
Word spotting in the wild
References
The state of the art in online handwriting recognition
Off-line cursive script word recognition
An off-line cursive handwriting recognition system
Segmentation methods for character recognition: from segmentation to document structure analysis
Machine recognition of handwritten words: A project report
Related Papers (5)
Feature extraction methods for character recognition--a survey
Online and off-line handwriting recognition: a comprehensive survey
Frequently Asked Questions (10)
Q2. What have the authors stated for future works in "A survey of methods and strategies in character segmentation" ?
The authors apologize to researchers whose important contributions may have been overlooked.
Q3. What was used in the first stage of a hybrid recognition system?
Upper contour analysis was also used in [47] for a pre-segmentation algorithm that served as part of the second stage of a hybrid recognition system.
Q4. How can the authors perform the segmentation task at a low cost?
By testing their adjacency relationships to perform merging, or their size and aspect ratios to trigger splitting mechanisms, much of the segmentation task can be accurately performed at a low cost in computation.
Q5. What was the common method of representing words and letters?
In [67], words and letters were represented by means of tree dictionaries: possible words were described by a letter tree (also called a "trie") and letters were described by a feature tree.
Q6. What is the common method of segmenting an image?
Splitting of an image classified as connected is then accomplished by finding characteristic landmarks of the image that are likely to be segmentation points, rejecting those that appear to be situated within a character, and implementing a suitable cutting path.
Q7. What is the need for a term such as "Dissection"?
in many current studies, as the authors shall see, segmentation is a complex process, and there is a need for a term such as "dissection" to distinguish the image-cutting subprocess from the overall segmentation, which may use contextual knowledge and/or character shape description.
Q8. What was the effect of the technique on the output images?
The authors noted that the technique was heavily dependent on the quality of the input images, and tended to fail on both very heavy or very light printing.
Q9. What is the reason why segmentation is so rarely mentioned in pre-70s literature?
The twin facts that early OCR development dealt with constrained inputs, while research wasmainly concerned with representation and classification of individual symbols, explains why segmentation is so rarely mentioned in pre-70s literature.
Q10. How can the system make use of this knowledge?
As the system knows in advance what it is searching for, it can make use of high-level contextual knowledge to improve recognition, even at low-level stages.