Color correcting method and apparatus

• US 5,929,906 A
• Filed: 10/24/1996
• Issued: 07/27/1999
• Est. Priority Date: 12/07/1995
• Status: Expired due to Fees

• Current Assignee: Shiro Usui, TOYO Ink Manufacturing Company Limited
• Original Assignee: Shiro Usui, TOYO Ink Manufacturing Company Limited
• Inventors: Arai, Yoshifumi, Usui, Shiro
• Primary Examiner(s): Ho, Tuan V.
• Application Number:
  US08/736,257
• Time in Patent Office: 1,006 Days
• Field of Search: 348/207, 348/222, 348/223, 348/225, 348/228, 348/234, 348/235, 348/236, 348/362, 348/366, 348/649, 348/650, 348/651, 348/652, 348/653, 348/654, 348/655, 358/518, 358/520, 382/156, 382/162, 382/167, 706/15, 706/17, 706/25
• US Class Current: 348/223.1
• CPC Class Codes: H04N 1/6086 by scene illuminant, i.e. conditions at the time of picture capture, e.g. flash, optical filter used, evening, cloud, daylight, artificial lighting, white point measurement, colour temperature

Abstract

A color correcting unit receives color separation values such as CMY values from an image input unit. Under the control of a control portion, inputs to a first conversion portion constituted by a neural network which has been trained in advance on the basis of the spectral distribution of an arbitrary illuminant are corrected so that outputs from the first conversion portion satisfy the color separation values and a predetermined requirement. The input values to the first conversion portion, which satisfy the predetermined requirement, are sent to an image output unit. The image output unit outputs an image in accordance with these input values.

Claims

1. A color correcting method in a system for printing an image of an object on the basis of a color separation value of the image of the object under a given illuminant, the method comprising the steps of:

converting a color separation value to be supplied to a system for printing an image of an object into an intermediate colorimetric system value of one of a spectral reflectance and a spectral transmittance;

calculating an estimation value of a colorimetric value of the object under a reference illuminant in accordance with the intermediate colorimetric system value and a spectral distribution of the reference illuminant; and

optimizing the color separation value in accordance with the estimation value of the colorimetric value and a colorimetric value of an image of the object under a given illuminant.

2. A method according to claim 1, wherein the optimizing step comprises a substep of optimizing the color separation value so that one of a square error and an average color difference between the estimation value of the colorimetric value and the colorimetric value of the object under the given illuminant becomes minimum.

3. A method according to claim 1, wherein the predetermined colorimetric values are colorimetric values of the reproduction target under the desired illuminant.

4. A method according to claim 1, wherein the color separation value is a set of R (red), G (green), and B (blue).

5. A method according to claim 1, wherein the color separation value is one of a set and a set of C, M, Y, and K (black).

6. A method according to claim 1, in which said converting step uses a neural network which has been trained for conversion from the color separation value to the intermediate colorimetric value.

7. A method according to claim 6, wherein the neural network is a multi-layered feedforward neural network.

8. A method according to claim 1, wherein the optimizing step comprises performing nonlinear optimization.

9. A method according to claim 1, wherein the reference illuminant is one illuminant selected from the group consisting of an A illuminant, a B illuminant, a C illuminant, a D illuminant having an arbitrary color temperature, and F1 to F2 illuminants, all of which are defined by the CIE (Commission Internationale de I'"'"'Eclairage).

10. A color correcting apparatus comprising:

an image input unit for imaging an object under a given illuminant, the object being printed by a given printing device to generate a color separation value;

first conversion means, having a first neural network, for converting the color separation value;

first conversion means, having a first neural network, for converting the color separation value into an intermediate colorimetric system value being one of a spectral reflectance and a spectral transmittance;

means for obtaining an estimation value of the colorimetric value of the object under a reference illuminant in accordance with the intermediate colorimetric system value and a spectral distribution of the reference illuminant; and

optimization means for optimizing the color separation value so that at least one of a square error and an average color difference between the estimation value of the colorimetric value and a colorimetric value of an object under the given illuminant becomes minimum.

11. A color correcting apparatus according to claim 10, in which the optimizing means comprises:

second conversion means having a second neural network, for converting the color separation value into the intermediate colorimetric system value of the object under the given illuminant.