The Parameter Optimization of the Pulse Coupled Neural Network for the Pattern Recognition

Yonekawa, Masato; Kurokawa, Haruhisa

doi:10.1007/978-3-642-15825-4_13

Cited by 8 publications

(7 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As we mentioned in our previous studies [24] [25], one of the most remarkable features of the image matching is that the method is valid to recognize rotated or scale modified images. This feature should be effective for the image retrieval because the images in the database are generally disordered.…”

Section: Discussionmentioning

confidence: 94%

“…These are the most outstanding characteristics of PCNN-Icon, and this achieves good performance on the image matching problem [24] [25]. The PCNN-Icon has been applied to various issues in image processing e.g.…”

Section: B the Image Matching Using The Pcnn-iconmentioning

confidence: 98%

“…The PCNN parameter learning method for the image matching problem had been proposed in our previous work [24] [25]. In this learning method, the simple real coded genetic algorithm is applied [27].…”

Section: The Learning Rule For the Image Matchingmentioning

confidence: 99%

“…To improve the performance of the image matching using the PCNN, we had been proposed a learning method of the parameters in the PCNN [24] [25]. We had been showed its validity in our previous works.…”

Section: Introductionmentioning

confidence: 98%

See 3 more Smart Citations

The Content-Based Image Retrieval using the Pulse Coupled Neural Network

Yonekawa

Kurokawa

2012

The 2012 International Joint Conference on Neural Networks (IJCNN)

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 94%

Section: B the Image Matching Using The Pcnn-iconmentioning

confidence: 98%

Section: The Learning Rule For the Image Matchingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 98%

See 2 more Smart Citations

The Content-Based Image Retrieval using the Pulse Coupled Neural Network

Yonekawa

Kurokawa

2012

The 2012 International Joint Conference on Neural Networks (IJCNN)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The reconfigurability of the FPGA is adequate to support the parameter learning and that is also the merit of using the FPGA. Where the learning method of the parameters in the PCNN have been proposed in our recent work [12], and now [12] we are trying to apply the learning method to the IC-PCNN in our future works.…”

Section: Introductionmentioning

confidence: 99%

Hardware implementation of IC-PCNN for the color image segmentation

Yoshihara

Kurokawa

2014

2014 Ieee Region 10 Symposium

Self Cite

View full text Add to dashboard Cite

An image processing using the Pulse Coupled Neural Network(PCNN) has been proposed and well studied recently. To achieve a color image processing using the PCNN scheme, authors had been proposed the IC-PCNN as an extended model of the PCNN. In our previous paper, the successful results of color image segmentation had been shown by numerical experiments. This paper describes the hardware implementation of the Inhibitory Connected Pulse Coupled Neural Network(IC-PCNN) in FPGA. From the results, we evaluate the possibility of our IC-PCNN for the embedded system.

show abstract

An Evaluation of the Image Recognition Method Using Pulse Coupled Neural Network

Yonekawa

Kurokawa

2011

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The Parameter Optimization of the Pulse Coupled Neural Network for the Pattern Recognition

Cited by 8 publications

References 4 publications

The Content-Based Image Retrieval using the Pulse Coupled Neural Network

The Content-Based Image Retrieval using the Pulse Coupled Neural Network

Hardware implementation of IC-PCNN for the color image segmentation

An Evaluation of the Image Recognition Method Using Pulse Coupled Neural Network

Contact Info

Product

Resources

About