Title :
Neural net based digital halftoning of images
Author :
Anastassiou, Dimitris
Author_Institution :
Dept. of Electr. Eng., Columbia Univ., New York, NY, USA
Abstract :
Various novel techniques for digital image halftoning are presented, performing nonstandard quantization subject to a fidelity criterion. Hopfield-type networks can be used for this task, minimizing a frequency-weighted mean squared error between the input (continuous-tone) and the output (bilevel) image. A novel kind of massively parallel analog network (the differential neural network) is introduced and shown to be appropriate for this task. This kind of network contains a nonmonotonic nonlinearity in lieu of the sigmoid function
Keywords :
neural nets; picture processing; Hopfield-type networks; differential neural network; digital halftoning; fidelity criterion; frequency-weighted mean squared error; images; massively parallel analog network; nonmonotonic nonlinearity; nonstandard quantization; Artificial neural networks; Differential equations; Digital images; Displays; Frequency; Magnetic analysis; Neural networks; Neurons; Nonlinear dynamical systems; Quantization;
Conference_Titel :
Circuits and Systems, 1988., IEEE International Symposium on
Conference_Location :
Espoo
DOI :
10.1109/ISCAS.1988.14975
