Appling a Novel Cost Function to Hopfield Neural Network for Defects Boundaries Detection of Wood Image
<p/> <p>A modified Hopfield neural network with a novel cost function was presented for detecting wood defects boundary in the image. Different from traditional methods, the boundary detection problem in this paper was formulated as an optimization process that sought the boundary points...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2010-01-01
|
| Series: | EURASIP Journal on Advances in Signal Processing |
| Online Access: | http://asp.eurasipjournals.com/content/2010/427878 |
| _version_ | 1818863093066760192 |
|---|---|
| author | Qi Dawei Zhang Peng Zhang Xuefei Jin Xuejing Wu Haijun |
| author_facet | Qi Dawei Zhang Peng Zhang Xuefei Jin Xuejing Wu Haijun |
| author_sort | Qi Dawei |
| collection | DOAJ |
| description | <p/> <p>A modified Hopfield neural network with a novel cost function was presented for detecting wood defects boundary in the image. Different from traditional methods, the boundary detection problem in this paper was formulated as an optimization process that sought the boundary points to minimize a cost function. An initial boundary was estimated by Canny algorithm first. The pixel gray value was described as a neuron state of Hopfield neural network. The state updated till the cost function touches the minimum value. The designed cost function ensured that few neurons were activated except the neurons corresponding to actual boundary points and ensured that the activated neurons are positioned in the points which had greatest change in gray value. The tools of Matlab were used to implement the experiment. The results show that the noises of the image are effectively removed, and our method obtains more noiseless and vivid boundary than those of the traditional methods.</p> |
| first_indexed | 2024-12-19T10:10:16Z |
| format | Article |
| id | doaj.art-1e75339b078649f189695b72a9365a7a |
| institution | Directory Open Access Journal |
| issn | 1687-6172 1687-6180 |
| language | English |
| last_indexed | 2024-12-19T10:10:16Z |
| publishDate | 2010-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Advances in Signal Processing |
| spelling | doaj.art-1e75339b078649f189695b72a9365a7a2022-12-21T20:26:23ZengSpringerOpenEURASIP Journal on Advances in Signal Processing1687-61721687-61802010-01-0120101427878Appling a Novel Cost Function to Hopfield Neural Network for Defects Boundaries Detection of Wood ImageQi DaweiZhang PengZhang XuefeiJin XuejingWu Haijun<p/> <p>A modified Hopfield neural network with a novel cost function was presented for detecting wood defects boundary in the image. Different from traditional methods, the boundary detection problem in this paper was formulated as an optimization process that sought the boundary points to minimize a cost function. An initial boundary was estimated by Canny algorithm first. The pixel gray value was described as a neuron state of Hopfield neural network. The state updated till the cost function touches the minimum value. The designed cost function ensured that few neurons were activated except the neurons corresponding to actual boundary points and ensured that the activated neurons are positioned in the points which had greatest change in gray value. The tools of Matlab were used to implement the experiment. The results show that the noises of the image are effectively removed, and our method obtains more noiseless and vivid boundary than those of the traditional methods.</p>http://asp.eurasipjournals.com/content/2010/427878 |
| spellingShingle | Qi Dawei Zhang Peng Zhang Xuefei Jin Xuejing Wu Haijun Appling a Novel Cost Function to Hopfield Neural Network for Defects Boundaries Detection of Wood Image EURASIP Journal on Advances in Signal Processing |
| title | Appling a Novel Cost Function to Hopfield Neural Network for Defects Boundaries Detection of Wood Image |
| title_full | Appling a Novel Cost Function to Hopfield Neural Network for Defects Boundaries Detection of Wood Image |
| title_fullStr | Appling a Novel Cost Function to Hopfield Neural Network for Defects Boundaries Detection of Wood Image |
| title_full_unstemmed | Appling a Novel Cost Function to Hopfield Neural Network for Defects Boundaries Detection of Wood Image |
| title_short | Appling a Novel Cost Function to Hopfield Neural Network for Defects Boundaries Detection of Wood Image |
| title_sort | appling a novel cost function to hopfield neural network for defects boundaries detection of wood image |
| url | http://asp.eurasipjournals.com/content/2010/427878 |
| work_keys_str_mv | AT qidawei applinganovelcostfunctiontohopfieldneuralnetworkfordefectsboundariesdetectionofwoodimage AT zhangpeng applinganovelcostfunctiontohopfieldneuralnetworkfordefectsboundariesdetectionofwoodimage AT zhangxuefei applinganovelcostfunctiontohopfieldneuralnetworkfordefectsboundariesdetectionofwoodimage AT jinxuejing applinganovelcostfunctiontohopfieldneuralnetworkfordefectsboundariesdetectionofwoodimage AT wuhaijun applinganovelcostfunctiontohopfieldneuralnetworkfordefectsboundariesdetectionofwoodimage |