Paper Information

Title: 

IDENTIFICATION OF DOMINANT FEATURES OF HUMAN VISION IN IMAGE SEGMENTS DETECTION AND USING THEM TO DETECTION SUSPICIOUS MASSES IN MAMMOGRAMS

Type: PAPER
Author(s): ENSHAEIYEH MOHAMMAD*,REZAEI RAD GHOLAM ALI
 
 *IRAN UNIVERSITY OF SCIENCE AND TECHNOLOGY, COLLEGE OF ELECTRICAL ENGINEERING, DR REZAEI RAD OFFICE, TEHRAN, IRAN
 
Name of Seminar: IRANIAN CONFERENCE ON BIOMEDICAL ENGINEERING
Type of Seminar:  CONFERENCE
Sponsor:  ANJOMANE MOHANDESI PEZESHKI IRAN
Date:  2004Volume 11
 
 
Abstract: 

IN THIS PAPER WITH STUDY OF HUGE NUMBER OF METHODS THAT HAVE BEEN PROPOSED IN IMAGE SEGMENTATION AND IDENTIFICATION AREA, WE PROPOSE THE MOST ADAPTED METHODS WITH HUMAN VISION TECHNIQUES. WITH INDICATE THE EXTERNAL FEATURES OF AN IMAGE AS DOMINANT FEATURES, THEN WE SHOW THAT BETWEEN THESE FEATURES, NEGATIVE CURVATURE MINIMA (NCM) POINTS, AND BETWEEN INTERNAL FEATURES, TEXTURES DETECTED USING PULSE COUPLED NEURAL NETWORKS (PCNNS) AND LAWS METHODS ARE THE ADAPTED METHODS WITH HUMAN VISION STRATEGY. THEN WE HAVE USES THESE FEATURES TO DETECT SUSPICIOUS MASSES IN MAMMOGRAM IMAGES AND ANALYSIS THE RESULTS AND COMPARE THEM WITH PEER PROPOSED METHODS. FINALLY WE HAVE PROPOSED A NEW AUGMENTED METHOD TO DO SEGMENTATION IN SAME WAY THAT HUMAN VISION DOES IT.

 
Keyword(s): 
 
Yearly Visit 4   tarjomyar
 
Latest on Blog
Enter SID Blog