Video image processing apparatus

• US 5,091,965 A
• Filed: 07/16/1990
• Issued: 02/25/1992
• Est. Priority Date: 07/16/1990
• Status: Expired due to Term

• Current Assignee: California Institute of Technology, Sony Corporation (Sony Group Corp.)
• Original Assignee: California Institute of Technology, Sony Corporation (Sony Group Corp.)
• Inventors: Kobayashi, Seiji, Psaltis, Demetri
• Primary Examiner(s): Boudreau, Leo H.
• Application Number:
  US07/553,995
• Time in Patent Office: 589 Days
• Field of Search: 382/14, 382/15, 382/27, 382/28, 382/35, 382/41, 364/513
• US Class Current: 382/157
• CPC Class Codes: G06N 3/02 Neural networks

Abstract

A video image processing apparatus in which an analog video image can be satisfactorily converted to a binary value by calculating theshold values of respective neurons and coupling coefficients of respective synapses of a neural network circuit on the basis of the input analog video image and a pre-determined function.

By arranging so a difference component E between the input analog video image and the binary value video image is defined as ##EQU1## where α is the coefficient, u.sub.(i) is the value which results from converting the input analog video image into the binary value, and P.sub.(i,j) is the value obtained from the function and g.sub.(i) is the value which is obtained from the function and the input analog video image, it is possible to convert the video image into the binary value by the use of the neural network circuit.

Further, by setting that the function to have a frequency characteristic of a human'"'"'s eyes, it is possible to obtain a binary value video image which is excellent from a human'"'"'s visual standpoint.

Furthermore, if the input analog video image is a computer hologram and the function is a window function which indicates a range of a desired video image in a reproduced image which results from Fourier-transforming the computer hologram, the noise in the range of the desired video image in the reproduced video image can be reduced to provide an excellent reproduced image.

Claims

1. A video image processing apparatus for converting an analog video image to a binary video image, said apparatus comprising:

input means for receiving said analog video image in the form of a computer hologram;

sampling means for sampling the received analog video image;

a neural network circuit having a plurality of neurons which are connected together through respective synapses;

setting means for setting a predetermined function which is a window function indicative of a range of a desired area of a reproduced video image which results from Fourier-transforming said computer hologram;

first computing means for computing respective threshold values for each of said neurons in said neural network circuit on the basis of the sampled value of the video image and said predetermined function; and

second computing means for computing respective coupling coefficients for each of said synapses of said neural network circuit on the basis of said predetermined function;

said neural network circuit processing said threshold values and said coupling coefficients so as to form said binary video image.

2. A video image processing apparatus for converting an analog video image to a binary video image, said apparatus comprising:

input means for receiving said analog video image;

sampling means for sampling the received analog video image;

a neural network circuit having a plurality of neurons which are connected together through respective synapses;

setting means for setting a predetermined function which has a frequency characteristic corresponding to that of a human'"'"'s eye;

first computing means for computing respective threshold values for each of said neurons in said neural network circuit on the basis of the sampled value of the analog video image and said predetermined function; and

second computing means for computing respective coupling coefficients for each of said synapses of said neural network circuit on the basis of said predetermined function;

said neural network circuit processing said threshold values and said coupling coefficients so as to form said binary video image.

3. A video image processing apparatus according to claim 3;

wherein said predetermined function is denoted by a low-pass filter characteristic.