Isolated Handwritten Farsi Numerals Recognition Using Sparse and Over-Complete Representations

Pan, Wumo; Bui, Tien D.; Suen, Ching Y.

doi:10.1109/icdar.2009.80

Cited by 15 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have used Stochastic Gradient Approach as it avoids being stuck in poor local minima which is highly likely due to the non linear nature of the error surface. A simplified CNN was presented in [25] which we have used for our work instead of using the rather complicated LeNet-5 [26]. The model has five layers.…”

Section: Artificial Immune Systems (Ais): Ais Use Clonal Selection An...mentioning

confidence: 99%

A Novel Hybrid CNN-AIS Visual Pattern Recognition Engine

Bhalla

Chaudhury

Jain

2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Machine learning methods are used today for most recognition problems. Convolutional Neural Networks (CNN) have time and again proved successful for many image processing tasks primarily for their architecture. In this paper we propose to apply CNN to small data sets like for example, personal albums or other similar environs where the size of training dataset is a limitation, within the framework of a proposed hybrid CNN-AIS model. We use Artificial Immune System Principles to enhance small size of training data set. A layer of Clonal Selection is added to the local filtering and max pooling of CNN Architecture. The proposed Architecture is evaluated using the standard MNIST dataset by limiting the data size and also with a small personal data sample belonging to two different classes. Experimental results show that the proposed hybrid CNN-AIS based recognition engine works well when the size of training data is limited in size.

show abstract

Section: Artificial Immune Systems (Ais): Ais Use Clonal Selection An...mentioning

confidence: 99%

A Novel Hybrid CNN-AIS Visual Pattern Recognition Engine

Bhalla

Chaudhury

Jain

2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…In contrast, very little research had reported the recognition of Persian (Arabic) handwritten digits (Liu et al, 2009;Pan et al, 2009;Borji et al, 2008;Suen et al, 2006;Soltanzadeh and Rahmati, 2004;Amin, 1998). However, today research on Farsi (Persian) scripts and *Corresponding author.…”

Section: Introductionmentioning

confidence: 99%

Persian handwritten digits recognition: A divide and conquer approach based on mixture of MLP experts

Javidi¹

2011

Int. J. Phys. Sci.

View full text Add to dashboard Cite

In pursuit of Persian handwritten digit recognition, many machine learning techniques have been utilized. Mixture of experts (MOE) is one of the most popular and interesting combining methods which has great potential to improve performance in machine learning. In MOE, during a competitive learning process, the gating networks supervise dividing input space between experts and experts obtain specialization on those subspaces. In this model, simple linear networks are used to form the building blocks of the MOE architecture. But in this study, due to complexity of Persian handwritten digit classification, the multi layer perceptrons, MLP, is used as gating and expert networks. We call this architecture the mixture of multilayer perceptrons experts (MOME). Comparative evaluation is accomplished with two real-world datasets: SRU Persian numerals and a very large dataset of Persian handwritten digit (HODA). In this paper, experiments are conducted to evaluate the performance of MOME with various appraisal criteria and also, classification capabilities of various neural network ensembles are compared with MOME. Our experimental results indicate significant improvement in recognition rate of our investigated method, MOME, in all practical tests.

show abstract

“…This article does not use complex CNN structure [6], but refer to simplify the structure of the CNN [7]. Our CNN structure is shown in Figure 1.There are seven layers.…”

Section: Cnnmentioning

confidence: 99%