Handwritten numeral recognition using gradient and curvature of gray scale image

Shi, Meng; Fujisawa, Yoshiharu; Wakabayashi, Tetsushi; Kimura, Fumitaka

doi:10.1016/s0031-3203(01)00203-5

Cited by 152 publications

(51 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In other study, the contrast gradient of points has been used to recognize Latin handwritten digits [6]. In this method, normalization is the major preprocess before creating contrast gradient.…”

Section: Figure 1: Digit 3 Before and After Narrowing Phasementioning

confidence: 99%

See 1 more Smart Citation

Handwritten Recognition using Slope and Curvature Functions

Yaghoubi¹,

Karbasi²

2012

IJAIS

View full text Add to dashboard Cite

Letter recognition and handwritten processing is one of the major and open problems in Artificial Intelligent (AI) domain. This study introduces a method based on statistical and geometrical techniques to recognize handwritten digits and letters. These techniques use the fuzzy logic to create the vector curves. Inputs are online digits or letters and outputs are two arrays of slope and curvature values. The slope and curvature values of training data are stored in a database and used in comparison phase. The test results show that 96.98% of inputs are correctly recognized.

show abstract

Section: Figure 1: Digit 3 Before and After Narrowing Phasementioning

confidence: 99%

“…Specifically, this article proposes a new method to recognize Persian handwritten digits and letters through narrowing, clustering, and movement path identification which are introduced in [6]. At first, we specify the principal points of input image and their sequences.…”

Section: Figure 1: Digit 3 Before and After Narrowing Phasementioning

confidence: 99%

Handwritten Recognition using Slope and Curvature Functions

Yaghoubi¹,

Karbasi²

2012

IJAIS

View full text Add to dashboard Cite

show abstract

“…Thus, different approaches for feature extraction from characters are proposed [12]. For instance, stroke direction feature [13]- [14] and curvature feature [15] are two of these approaches.…”

Section: Introductionmentioning

confidence: 99%

A Decision Tree Based Method to Classify Persian Handwritten Numerals by Extracting Some Simple Geometrical Features

Alvari¹,

Fard²,

Salehi³

2013

IJCTE

View full text Add to dashboard Cite

Abstract-Automatic recognition of handwritten numerals has been widely proposed in various languages. However, some languages such as Persian still need more consideration. In this paper, we proposed a handwritten Persian numerals dataset, which is gathered from people with different range of educational level. Thus, it is more general than other similar Persian datasets. Additionally, a method to classify Persian handwritten numerals is presented, which uses simple geometrical features based on their shapes, and classifies them via a rule-based decision tree classifier. Compared to other similar methods, our proposed method has the advantages of high speed running, employing too few and simple features, and elimination of training phase.

show abstract

“…Many methods have been proposed with very high recognition rate [20,7,10,12,22,15,16,9,13,5]. Some of these techniques have found application in real systems, such as mail resorting [19] and bank check recognition [4,8].…”

Section: Introductionmentioning

confidence: 99%