Comparison of Gaussian and neural network classifiers on vowel recognition using the discrete cosine transform

1992 ◽  
Author(s):  
D.J. Burr
Keyword(s):  
Neural Network ◽  
Discrete Cosine Transform ◽  
Cosine Transform ◽  
Vowel Recognition ◽  
Neural Network Classifiers

scholarly journals DESIGN OF NEURAL NETWORK AS DATA FLOW MODEL FOR IMAGE COMPRESSION

2013 ◽  
pp. 195-199
Author(s):  
DANESHWARI I. HATTI ◽  
SAVITRI RAJU ◽  
MAHENDRA M. DIXIT
Keyword(s):  
Neural Network ◽  
Image Compression ◽  
Discrete Cosine Transform ◽  
Compression Ratio ◽  
Convergence Time ◽  
Training Algorithms ◽  
Hardware Complexity ◽  
Cosine Transform ◽  
Hidden Neurons

In digital communication bandwidth is essential parameter to be considered. Transmission and storage of images requires lot of memory in order to use bandwidth efficiently neural network and Discrete cosine transform together are used in this paper to compress images. Artificial neural network gives fixed compression ratio for any images results in fixed usage of memory and bandwidth. In this paper multi-layer feedforward neural network has been employed to achieve image compression. The proposed technique divides the original image in to several blocks and applies Discrete Cosine Transform (DCT) to these blocks as a pre-process technique. Quality of image is noticed with change in training algorithms, convergence time to attain desired mean square error. Compression ratio and PSNR in dB is calculated by varying hidden neurons. The proposed work is designed using MATLAB 7.10. and synthesized by mapping on Vertex 5 in Xilinx ISE for understanding hardware complexity. Keywords - backpropagation, Discrete

scholarly journals Pengenalan Pola Tulisan Tangan Aksara Arab Menggunakan Ekstraksi Fitur Discrete Cosine Transform Dan Klasifikasi Backpropagation Artificial Neural Network

2021 ◽  
Vol 3 (1) ◽  
pp. 43-50
Author(s):  
Farhan Yakub Bawazir
Keyword(s):  
Neural Network ◽  
Middle East ◽  
Discrete Cosine Transform ◽  
North Africa ◽  
Extraction Method ◽  
Cosine Transform ◽  
Feature Extraction Method ◽  
Arabic Script ◽  
Age Range ◽  
Backpropagation Artificial Neural Network

Arabic is a language that is spoken as the first or native language of more than 280 million people, most of whom live in the Middle East and North Africa. Apart from the Middle East and North Africa, Arabic is also familiar and often used in Indonesia because of the majority of Indonesia's population is Muslim and Arabic is the language of worship in Islam. The recognition of Arabic handwritten letters is one of the studies that has been done before, where the accuracy results obtained vary according to the research and methods used. This study aims to determine the accuracy resulting from the recognition of Arabic script handwriting patterns using a combination of the DCT(Discrete Cosine Transform) feature extraction method and the ANN Backpropagation classification method. The data used for this study were data from handwritten sources on A4 HVS paper using markers with categories of age from 7-13 years old and 18-23 years old with 15 respondents in each group and a total dataset image of 8400. Testing the best model model obtained on all images produces an accuracy of 80.79%, using the images of age range 17-23 years produces 87.27% accuracy, and the images of age range 7-13 produces an accuracy of 72.84%. Keywords: pengenalan pola, tulisan tangan, aksara, DCT, backpropagation

Sign in / Sign up

Export Citation Format

Share Document