Using Local Slant Correction to Normalize Handwritten Text Samples
نویسنده
چکیده
In this paper we propose to use variable slant correction instead of an global correction, since the slant of handwritten text is not constant over a line of text. We present an algorithm that computes local slant, based on generalized projection and dynamic programming, and introduce a technique called slant map propagation. We apply it on a case study and report the results: local slant correction improves the word recognition rate from 37.3% to 42.24% and the word level accuracy from -14.99% to -3.18%, compared to global slant correction.
منابع مشابه
Slant normalization of handwritten numeral strings
Two word slant correction methods are evaluated in this work using handwritten numeral strings. A method originally proposed to word slant correction is adapted in order to improve the results for handwritten numeral strings. The original and modified methods are evaluated by means of some interesting analyses on the NIST SD19 database. In these analyses the difference, in terms of slant estima...
متن کاملNonuniform Slant Correction for Handwritten Word Recognition
Slant correction is a preprocessing technique to improve segmentation and recognition accuracy for handwritten word recognition. All conventional slant correction techniques were performed by the estimation of the average slant angle and the shear transformation. In this paper, a nonuniform slant correction technique for handwritten word recognition is proposed where the slant correction proble...
متن کاملWriter Identification Using an HMM-Based Handwriting Recognition System: To Normalize the Input or Not?
A system for writer identification based on handwritten text lines is described in this paper. The system uses Hidden Markov Model based recognizers which are designed for text line recognition. Features are extracted from a text line and used to train the recognizers. Prior to feature extraction, normalization operations are applied to a text line. On the one hand, there exists a strong correl...
متن کاملSlant Correction using Histograms
Slant is one of the characteristics that make handwriting harder to process automatically than printed text. For this reason slant correction is a standard step in systems for processing written text. In this article I will present an algorithm for automatically correcting slant. It works by first segmenting the text into words using horizontal and vertical projection histograms. Each word is t...
متن کاملNonuniform Slant Correction Using Dynamic Programming
Slant correction is an indispensable technique for handwritten word recognition systems. Conventional slant correction techniques estimate the average slant angle of component characters and then correct the slant uniformly. Thus these conventional techniques will perform successfully under the assumption that each word is written with a constant slant. However, it is more widely acceptable ass...
متن کامل