Research on Genetic Segmentation and Recognition Algorithms

摘要

Proposed an improved genetic segmentation algorithm and recognition method base on PSO. In the genetic algorithm, 2-dimention chromosome coding is adopted; initialization of population with stochastic and symmetrical methods is produced to keep the variety of the population; OTSU is adopted to be as fitness function; a new individual is introduced in updated population. Abstracted three main components from the segmented image, and used neural networks trained by PSO to recognize the blood cells types. Experiments show that good results can be achieved steadily and quickly.