Color image processing apparatus for color-correcting input image data using neural network

• US 5,774,230 A
• Filed: 05/23/1996
• Issued: 06/30/1998
• Est. Priority Date: 06/21/1995
• Status: Expired due to Term

• Current Assignee: Sharp Kabushiki Kaisha (Hon Hai Precision Industry Co., Ltd.)
• Original Assignee: Sharp Kabushiki Kaisha (Hon Hai Precision Industry Co., Ltd.)
• Inventors: Goto, Makio
• Primary Examiner(s): FRAHM, ERIC S
• Application Number:
  US08/652,790
• Time in Patent Office: 768 Days
• Field of Search: 358/296, 358/298, 358/504, 358/518, 358/520, 358/523, 358/530, 382/162, 382/167, 395/21, 395/23
• US Class Current: 382/162
• CPC Class Codes: H04N 1/603 controlled by characteristics of the picture signal generator or the picture reproducer

Abstract

A color image processing apparatus including a read device for reading an original image, a color correcting device for color-correcting input image data using a color-correcting neural network, and an output device for outputting color-corrected image data. The neural network with teacher data, which are in effect learning color data reflecting the visual characteristics of human eyes, using learning data produced by reading a copy image produced based on the learning color data. Accordingly, the neural network can correct colors accurately in a manner to fully reflect the visual characteristics of human eyes, thereby making the color difference between the original image and a copy of the same less noticeable.

Claims

1. A color image processing apparatus including:

read means for reading an original image;

color correcting means for color-correcting input image data using a color-correcting neural network; and

output means for outputting color-corrected image data;

said color-correcting neural network learning using teacher data and learning data,

said teacher data being learning color data produced by adding data of a first color and/or deleting data of a second color to/from data of master color samples, said first color being a color to which human eyes are highly sensitive, said second color being a color to which human eyes are less sensitive,

said learning data being image data produced by said read means as said read means reads an image produced by said output means based on said learning color data.

2. The color image processing apparatus as defined in claim 1, wherein said color correcting means includes a plurality of color-correcting neural networks for individual color characteristics of said input image data, so colors of the input image data are corrected using a neural network for a specific color characteristic in response to a color characteristic of the input image data.

3. The color image processing apparatus as defined in claim 1, wherein said color correcting means includes a color-correcting neural network which learns using teacher data and learning data,

said teacher data being latest color-corrected image data,

said learning data being input image data produced by said read means as said read means reads an image produced by said output means based on said latest color-corrected image data.

4. The color image processing apparatus as defined in claim 2, wherein said color correcting means includes a color-correcting neural network which learns using teacher data and learning data,

said teacher data being latest color-corrected image data,

said learning data being input image data produced by said read means as said read means reads an image produced by said output means based on said latest color-corrected image data.

5. The color image processing apparatus as defined in claim 1 further including a memory unit for storing the master color samples data and said learning color data used as said teacher data, said memory unit being connected to said color correcting means.

6. The color image processing apparatus as defined in claim 1, wherein said color correcting means converts the input image data in the form of a RGB signal into one of a CMY signal and a CMYK signal.

7. The color image processing apparatus as defined in claim 1, wherein said color correcting means includes a portrait neural network and a landscape neural network in said plurality of color-correcting neural networks.

8. The color image processing apparatus as defined in claim 7 further including an image selecting device for judging whether an original image is a portrait or a landscape, and said image selecting device for selecting one of said portrait neural network and landscape neural network based on said judgement.

9. The color image processing apparatus as defined in claim 1, wherein said color correcting means includes a general neural network and a user'"'"'s neural network in said plurality of color-correcting neural networks.

10. The color image processing apparatus as defined in claim 9 further including a learning device for supplying the learning data and the teacher data to said user'"'"'s neural network.