Neural networks for fast image compression /

algorithm was adopted. In order to keep the

Bibliographic Details
Main Author: Li, Mu
Format: Thesis eBook
Language:English
Published: [Place of publication not identified] : [publisher not identified] ; 1998.
Subjects:
Online Access:Link to OAKTrust copy

MARC

Tag First Indicator Second Indicator Subfields
LEADER 00000ctm a22000005a 4500
001 in00001506021
005 20220103114456.0
007 cr unu a
008 991029s1998 xx a b 000 0 eng d
035 |9 AJL1321AM 
035 |a (OCoLC)42729617 
040 |a TXA  |c TXA  |d UtOrBLW 
049 |a TXAM  |a TXAR 
099 |a 1998  |a Thesis  |a L528 
100 1 |a Li, Mu. 
245 1 0 |a Neural networks for fast image compression /  |c by Mu Li. 
264 1 |a [Place of publication not identified] :  |b [publisher not identified] ;  |c 1998. 
300 |a x, 62 leaves :  |b illustrations ;  |c 28 cm. 
336 |a text  |b txt  |2 rdacontent 
337 |a computer  |b c  |2 rdamedia 
338 |a online resource  |b cr  |2 rdacarrier 
500 |a "Major subject: Electrical Engineering". 
500 |a Vita. 
502 |b M.S.  |c Texas A&M University  |d 1998. 
504 |a Includes bibliographical references (leaves 42-44). 
520 |a algorithm was adopted. In order to keep the  
520 |a and decrease the number of neurons in the intermediate  
520 |a aspects: compression ratio, image distortion, and  
520 |a based on the predictive values and the input vectors.  
520 |a compress a gray-scale image. The system consists of  
520 |a compression part includes the input layer and the  
520 |a compression ratio. Moreover, the parallel architecture  
520 |a consists of the intermediate layer and the output  
520 |a converge, an adaptive back-propagation learning  
520 |a design of an image compression system involves three  
520 |a fidelity of the image, such that at the receiver, the  
520 |a for the learning process of the neural networks to  
520 |a generalization capability of the compression system  
520 |a good Peak-to-peak Signal to Noise Ratio and high  
520 |a image, a set of natural networks instead of one  
520 |a implement a new compression/decompression system to  
520 |a inherent in the architecture of the neural networks  
520 |a intermediate layer, while the decompression part  
520 |a layer, a preprocessing element is designed which  
520 |a layer. To gain high quality of the reconstructed  
520 |a makes the compression system process very quickly. 
520 |a network have been used in the system. Each neural  
520 |a network was trained with some image blocks which have  
520 |a number of bits transmitted as well as keeping the  
520 |a performs the necessary' processing of the image before  
520 |a predictor which predicts the current input block and a  
520 |a processing speed. In this thesis, we design and  
520 |a reconstructed image will have little distortion. The  
520 |a similar characteristics. In order to decrease the time  
520 |a subtracting element which generates residual vectors  
520 |a The final results shows that the reconstructed image  
520 |a The image compression system aims at reducing the graphics. 
520 |a the image is encoded. The preprocessor includes a  
520 |a three-layer feed forward neural networks. The  
520 |a which was processed by our proposed scheme had a very  
530 |a Also available online. 
650 4 |a Major electrical engineering. 
856 4 1 |u https://hdl.handle.net/1969.1/ETD-TAMU-1998-THESIS-L528  |z Link to OAKTrust copy  |t 0 
999 |a MARS 
999 f f |s 715f4fab-acef-32e9-9e9a-ed926059f160  |i e23f927c-4d85-3089-8f1d-3e656e221c04  |t 0 
952 f f |p noncirc  |a Texas A&M University  |b College Station  |c Cushing Memorial Library & Archives  |s cush tdrm  |d Cushing: Theses & Dissertations Microforms (Does not check out)  |t 0  |e 1998 Thesis L528  |h Other scheme  |i computer -- online resource 
952 f f |a Texas A&M University  |b College Station  |c Electronic Resources  |s www_evans  |d Available Online  |t 0  |e 1998 Thesis L528  |h Other scheme 
998 f f |a 1998 Thesis L528  |t 0  |l Available Online 
998 f f |a 1998 Thesis L528  |t 0  |l Cushing: Theses & Dissertations Microforms (Does not check out)