Title :
The Content-Based Image Retrieval using the Pulse Coupled Neural Network
Author :
Yonekawa, Masato ; Kurokawa, Hiroaki
Author_Institution :
Sch. of Comput. Sci., Tokyo Univ. of Technol., Hachioji, Japan
Abstract :
The image matching is one of the most important techniques in the image processing and the method using Pulse Coupled Neural Network (PCNN) was proposed in conventional study. Authors had been proposed a learning method to define the parameters in the PCNN for image matching. The learning method improves the performance of image matching using the PCNN. On the other hand, recently, a lot of researches on the Content-Based Image Retrieval (CBIR) have been studied. Also, some applications such as “Image search by the image” have been developed recently and these are based on this CBIR technique. In this study, we propose the method of the CBIR based on the image matching using PCNN. In our CBIR system, we assume that the image data is used as a query for image search. In the simulation results, we show the results of the retrieval for learned or unlearned query image. Also, we evaluate the performances of the system using recall and precision characteristics. From these results, we discuss the applicability of the method and we show the validity of the implementation of the image matching technique using PCNN to CBIR system.
Keywords :
content-based retrieval; image matching; image retrieval; learning (artificial intelligence); neural nets; CBIR technique; PCNN; content-based image retrieval; image data; image matching; image processing; image search; learned query image; learning method; performance improvement; pulse coupled neural network; unlearned query image; Biological cells; Correlation; Image matching; Image retrieval; Learning systems; Neurons;
Conference_Titel :
Neural Networks (IJCNN), The 2012 International Joint Conference on
Conference_Location :
Brisbane, QLD
Print_ISBN :
978-1-4673-1488-6
Electronic_ISBN :
2161-4393
DOI :
10.1109/IJCNN.2012.6252592