Hybrid of Rough Neural Networks for Arabic/Farsi Handwriting Recognition

Abstract

Abstract-Handwritten character recognition is one of the focused areas of research in the field of Pattern Recognition. In this paper, a hybrid model of rough neural network has been developed for recognizing isolated Arabic/Farsi digital characters. It solves the neural network problems; proneness to overfitting, and the empirical nature of model development using rough sets and the dissimilarity analysis. Moreover the perturbation in the input data is violated using rough neuron. This paper describes an evolutionary rough neural network based technique to recognize Arabic/Farsi isolated handwritten digital characters. This method involves hierarchical feature extraction, data clustering and classification. In contrast with conventional neural network, a comparative study is appeared. Also, the details and limitations are discussed.

Review : Pengenalan Pola Objek satu Dimensi

“…Terdapat enam jurnal pengenalan pola menggunakan metode neural network yakni (S. Wang, 2003), (Xu, n.d.), (Radwan, 2013), (Lecun et al, n.d.), (Liu et al, 2006) dan (Morimoto et al, 2000). Membandingkan metode Multi Weight Vector Neurons dengan Suport vector Machine, hasilnya Multi Vector Neurons lebih baik dari SVM (S. Wang, 2003).…”

“…Pendekatan ini berhasil merancang dan mengimplementasikan jaringan saraf kasar yang berjalan tanpa tuntutan. Setelah itu RS-RNN mampu memahami angka Arab/Farsi yang manual ditulis oleh pengguna (Radwan, 2013). Neural Network metode yang digunakan dalam peneltian ini menghasilkan khususnya NN propagasi balik multilapis menyediakan metode yang sederhana namun kuat dan umum untuk mensintesis pengklasifikasi dengan upaya minimal Namun sebagian besar sistem praktis menggabungkan NN dengan teknik lain untuk pra dan pasca pemrosesan Pada tugas pengenalan karakter yang terisolasi, jaringan multilapis dilatih dengan varian propagasi mundur telah mendekati keakuratan manusia (Lecun et al, n.d.).…”

Arabic Script based Digit Recognition Systems

“…Another effort found by Salimi ·and Giveki [17], in which PCA and 2DPCA Ensemble is used on singular value decomposition (SVD). In 2013, Rawdan [18] presented a novel method of centroid distance combination of Rough sets and Artificial Neural Network (RS_RNN) for Arabic/Farsi isolated numeral recognition. Author employed the hybrid model on IFHCBD database and got accuracy upto 93%.Shokoohi et al [19] perform experiment of CNN on features extracted using nonlinear algorithm from CENPARMI Farsi dataset.…”