A Neural Network CMOS Circuit Implementation for Real-Time Halftoning Applications. Sadowski, R., Ballmann, M., & Shoop, B. In Circuits and Systems, 2006. MWSCAS '06. 49th IEEE International Midwest Symposium on, volume 2, pages 614 -618, 8, 2006.
doi  abstract   bibtex   
We report on an underlying hardware approach to implement a neural network for real-time image halftoning. We present simulation and experimental results using a modified current starved comparator as the quantizing element that has a 40 fold reduction in pixel current over our previous designs. The neuron is self-biasing with error weighting achieved through current division to enable operation at a variety of bias voltages. The circuit is designed for integration with a flip-chip bonded photodiode array for imaging applications.
@inproceedings{4267429,
	Author = {Sadowski, R.W. and Ballmann, M.C. and Shoop, B.L.},
	Booktitle = {Circuits and Systems, 2006. MWSCAS '06. 49th IEEE International Midwest Symposium on},
	Date-Added = {2012-08-20 12:52:39 +0000},
	Date-Modified = {2012-08-28 18:16:07 +0000},
	Doi = {10.1109/MWSCAS.2006.381805},
	Issn = {1548-3746},
	Keywords = {bias voltages;digital halftoning;flip-chip bonded photodiode array;hardware approach;image processing;modified current starved comparator;neural network CMOS circuit implementation;optoelectronic devices;quantizing element;real-time halftoning applications;CMOS digital integrated circuits;flip-chip devices;image processing;integrated circuit design;neural nets;optoelectronic devices;photodiodes;},
	Month = {8},
	Pages = {614 -618},
	Title = {A Neural Network CMOS Circuit Implementation for Real-Time Halftoning Applications},
	Volume = {2},
	Year = {2006},
	Abstract = {We report on an underlying hardware approach to implement a neural network for real-time image halftoning. We present simulation and experimental results using a modified current starved comparator as the quantizing element that has a 40 fold reduction in pixel current over our previous designs. The neuron is self-biasing with error weighting achieved through current division to enable operation at a variety of bias voltages. The circuit is designed for integration with a flip-chip bonded photodiode array for imaging applications.},
	Bdsk-File-1 = {YnBsaXN0MDDUAQIDBAUIJidUJHRvcFgkb2JqZWN0c1gkdmVyc2lvblkkYXJjaGl2ZXLRBgdUcm9vdIABqAkKFRYXGyIjVSRudWxs0wsMDQ4RFFpOUy5vYmplY3RzV05TLmtleXNWJGNsYXNzog8QgASABqISE4ACgAOAB1lhbGlhc0RhdGFccmVsYXRpdmVQYXRo0hgNGRpXTlMuZGF0YU8RAbYAAAAAAbYAAgAACEFyY2hpdmlvAAAAAAAAAAAAAAAAAAAAAAAAAMyPzdRIKwAAAADY/wwwNDI2NzQyOS5wZGYAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAANmFzFf/rgAAAAAAAAAAAAEAAwAACQAAAAAAAAAAAAAAAAAAAAAGUGFwZXJzABAACAAAzI+xtAAAABEACAAAzFfjjgAAAAEAEAAA2P8AANj9AADY+gAAAFYAAgBPQXJjaGl2aW86RG9jdW1lbnRhemlvbmk6AEFydGljb2xpIHNjaWVudGlmaWNpOgBDYXRhbG9nYXRpOgBQYXBlcnM6ADA0MjY3NDI5LnBkZgAADgAaAAwAMAA0ADIANgA3ADQAMgA5AC4AcABkAGYADwASAAgAQQByAGMAaABpAHYAaQBvABIAQy9Eb2N1bWVudGF6aW9uaS9BcnRpY29saSBzY2llbnRpZmljaS9DYXRhbG9nYXRpL1BhcGVycy8wNDI2NzQyOS5wZGYAABMAES9Wb2x1bWVzL0FyY2hpdmlvAP//AACABdIcHR4fWCRjbGFzc2VzWiRjbGFzc25hbWWjHyAhXU5TTXV0YWJsZURhdGFWTlNEYXRhWE5TT2JqZWN0XxATUGFwZXJzLzA0MjY3NDI5LnBkZtIcHSQloiUhXE5TRGljdGlvbmFyeRIAAYagXxAPTlNLZXllZEFyY2hpdmVyAAgAEQAWAB8AKAAyADUAOgA8AEUASwBSAF0AZQBsAG8AcQBzAHYAeAB6AHwAhgCTAJgAoAJaAlwCYQJqAnUCeQKHAo4ClwKtArICtQLCAscAAAAAAAACAQAAAAAAAAAoAAAAAAAAAAAAAAAAAAAC2Q==},
	Bdsk-Url-1 = {http://dx.doi.org/10.1109/MWSCAS.2006.381805}}

Downloads: 0