Perfor. Increa. by Optimist. Learning Rate BAM And BPN for Recognition

ISBN-13: 9786139904358 / Angielski / Miękka / 2018 / 84 str.

Mainur Rahman Tarafder

Opis

The paper describes the recognition of character using BAM (Bidirectional Associative Memories) and multiple feed forward Back Propagation Network (BPN) algorithm. To do this, characters are scanned first with a scanner or written in any paint program and save the characters as image. The key function of preprocessing is to improve the image in ways the characters as image. The key function of preprocessing is to improve the image in ways that increase the chances for success of the other processes. Preprocessing typically deals with techniques for enhancing contrast, removing noise. Segmentation partitions an image into its constituent parts or objects. The key role of segmentation is to extract individual characters and words from the background. Representation and description is only part of the solution for transforming raw data into a from suitable for subsequent computer processing. Feature extraction deals with extracting features that result in some quantitative information of interest or features that are basic for differentiating one class of objects from another. These characters are filtered to remove noise. In order to remove noise I have used the Spatial filtering.

O autorze

Tarafder, Mainur Rahman
Engr. Mainur Rahman Tarafder. B.Sc. Engg. in CSE(RUET). M.Engg in ICT.BUET(Member of IEOM,Life Fellow of BCS,Member of IEB, Life Member BUET Alumni,LM REOSA,Member of ISOC(GLOBAL),Fellow Member of IAENG,Life Time Associate Member of ITPA,Member of ASET,Member of AES,EX-NDC,LAP & IEOM & IJSER & IJOAR Research Scholar, Fellow of IRED, Fellow of UACE)