In order to apply machine vision technology replacing human vision to identify the plant germplasm resources. This paper select 5 different types of Diospyros lotus seeds, 7 different appearance features and 6 color features were extracted by machine vision technology based on traditional identification method. One input, seven hidden layers and one output has been used for the multilayer perception (MLP) in our system. K-fold cross Validation was used for the modeling and classified of Diospyros lotus seeds. The results showed that the average identification rate of 5 types seeds was reached 91.8%, which indicated that the established seed model could be used as an effective method for the accurate classification of the seeds.

No abstract

No abstract

Character segmentation is an important stage in Automatic Number Plate Recognition systems as good character separation leads to a high recognition rate. This paper presents an improved character segmentation algorithm based on pixel projection and morphological operations. An efficient architecture based on the proposed algorithm is also presented. The architecture has been successfully implemented and verified using the Mentor Graphics RC240 FPGA (Field Programmable Gate Arrays) development board equipped with a 4M-Gate Xilinx Virtex-4 LX40. A database of 1,000 UK binary NPs with varying resolution has been used for testing the performance of the proposed architecture. Results achieved have shown that the proposed architecture can process a number plate image in 0.2–1.4 ms with 97.7 % successful segmentation rate and consumes only 11 % of the available area in the used FPGA

No abstract