فهرست مقالات Persian handwritten

• دسترسی آزاد مقاله
  • صفحه چکیده
  • متن کامل
  
  1 - Categorization of Persian Detached Handwritten Letters Using Intelligent Combinations of Classifiers
  Hossein Sadr Mojdeh Nazari Solimandarabi Mahsa Mirhosseini Moghadam
  Abstract—detecting optical characters is the main responsibility to convert printed documents and manuscripts to digital format. In this article, detecting Persian handwritten letters by using the combination of classifiers and features were assessed, hence geomet چکیده کامل

  Abstract—detecting optical characters is the main responsibility to convert printed documents and manuscripts to digital format. In this article, detecting Persian handwritten letters by using the combination of classifiers and features were assessed, hence geometric and statistical sections' features were used. In order to detect each letter, we divide it into two parts; the major and the minor parts. Then, we present some features for them. Preprocess algorithm prepare the possibility to unify dimension features for multiple words and deliver to classifier for detecting . We can get the hierarchy classification by separating the letters. After that, the optimal answer will be reached by using GA method of different SVM, ML and KNN classifications. Extraction algorithm of needed features was proved by using the evaluation of the basis of PCA. Empirical results represent classification of 94.3 and 92 accuracy in simple and multiple parts in 20 times repetition, respectively. eywords— Classifiers' Combination, Optical Character recognition, Persian handwritten, Reducing feature. پرونده مقاله
• دسترسی آزاد مقاله
  • صفحه چکیده
  • متن کامل
  
  2 - A New Approach in Persian Handwritten Letters Recognition Using Error Correcting Output Coding
  Maziar Kazemi Muhammad Yousefnezhad Saber Nourian
  Classification Ensemble, which uses the weighed polling of outputs, is the art of combining a set of basic classifiers for generating high-performance, robust and more stable results. This study aims to improve the results of identifying the Persian handwritten letters چکیده کامل

  Classification Ensemble, which uses the weighed polling of outputs, is the art of combining a set of basic classifiers for generating high-performance, robust and more stable results. This study aims to improve the results of identifying the Persian handwritten letters using Error Correcting Output Coding (ECOC) ensemble method. Furthermore, the feature selection is used to reduce the costs of errors in our proposed method. ECOC is a method for decomposing a multi-way classification problem into many binary classification tasks; and then combining the results of the subtasks into a hypothesized solution to the original problem. Firstly, the image features are extracted by Principal Components Analysis (PCA). After that, ECOC is used for identification the Persian handwritten letters which ituses Support Vector Machine (SVM) as the base classifier. The empirical results of applying this ensemble method using 10 real-world data sets of Persian handwritten letters indicate that this method has better results in identifying the Persian handwritten letters than other ensemble methods and also single classifications. Moreover, by testing a number of different features, this paper found that we can reduce the additional cost in feature selection stage by using this method. پرونده مقاله