License plate information reader device for motor vehicles

• US 6,373,962 B1
• Filed: 04/23/1999
• Issued: 04/16/2002
• Est. Priority Date: 04/24/1998
• Status: Expired due to Fees

• Current Assignee: UME Tech Yugen Kaisha
• Original Assignee: UME Tech Yugen Kaisha
• Inventors: Hamada, Toshio, Kanade, Takeo, Umezaki, Taizo
• Primary Examiner(s): Boudreau, Leo
• Assistant Examiner(s): Tabatabai, Abolfazl
• Application Number:
  US09/296,606
• Time in Patent Office: 1,089 Days
• Field of Search: 382/105, 382/229, 382/156, 382/158, 382/177, 250/338, 340/907, 340/933, 348/113
• US Class Current: 382/105
• CPC Class Codes: G06V 20/625 License plates
• CPC Class Codes: G06V 20/63 Scene text, e.g. street names

Abstract

In a license plate information reader device (A) for motor vehicles, a CCD camera (1) is provided to produce video image data (11) involving a license plate obtained by photographing a front and rear portion of a motor vehicle. An A/D converter (3) produces a digital multivalue image data (31) by A/D converting the video image data (11). A license plate extracting device (4) is provided to produce a digital multivalue image data (41) corresponding to an area in which the license plate occupies. A literal region extracting device (5) extracts a literal positional region of a letter sequence of the license plate based on the image obtained from the license plate extracting device (4). A literal recognition device (6) is provided to recognize a letter from a literal image (571) of the literal positional region obtained from the literal region extracting device (5). An image emphasis device is provided to emphasize the literal image (571) of the literal positional region by replacing a part of the literal region extracting device (5) with a filter net which serves as a neural network.

Claims

1. A license plate information reader device for motor vehicles comprising:

a photographing means provided to produce video image data including a license plate obtained by photographing a front and rear portion of a motor vehicle;

an image taking means having an A/D converter to produce a digital image data by A/D converting the video image data;

a license plate extracting means provided to detect a position of the license plate in the digital image data so as to produce an image including the license plate;

a literal regional extracting means provided to extract a literal position region of a letter sequence of the license plate based on the image obtained from the license plate extracting means;

a literal recognition means provided to recognize a letter from a literal image of the literal positional region obtained from the letter region extracting means;

an image emphasis means provided to emphasize the literal image of the literal positional region by replacing a part of the letter region extracting means with a filter net which serves as a neural network; and

the literal recognition means including a letter recognizing neural network which produces a literal code corresponding to the literal image obtained from the letter region extracting means and fed thereto.

2. A license plate information reader device for motor vehicles comprising:

a photographing means provided to produce video image data including a license plate obtained by photographing a front and rear portion of a motor vehicle;

an image taking means having an A/D converter to produce a digital image data by A/D converting the video image data;

a license plate extracting means provided to detect a position of the license plate in the digital image data so as to produce an image including the license plate;

a literal regional extracting means provided to extract a literal positional region of a letter sequence of the license plate based on the image obtained from the license plate extracting means;

a literal recognition means provided to recognize a letter from a literal image of the literal positional region obtained from the letter region extracting means;

an image emphasis means provided to emphasize the literal image of the literal positional region by replacing a part of the letter region extracting means with a filter net which serves as a neural network;

the image emphasis means further comprising;

the literal image having an area including the license plate having a plurality of image patterns;

a filter net which learns the literal image and an area of the letter region corresponding to each of digits of number of the license plate, and the filter net being partly incorporated into the letter region extracting means so as to obtain an output value which the filter net produces in correspondence to each of the digits of the literal image of the license plate when the input image data is fed; and

a literal image region being emphasized with a logical product of the input image data and the output value produced from the filter net.

3. A license plate information reader device for motor vehicles comprising:

a photographing means provided to produce video image data including a license plate obtained by photographing a front and area portion of a motor vehicle;

an image taking means having an A/D converter to produce a digital image data by A/D converting the video image data;

a license plate extracting means provided to detect a position of the license plate in the digital image data so as to produce an image including the license plate;

a literal regional extracting means provided to extract a literal positional region of a letter sequence of the license plate based on the image obtained from the license plate extracting means;

a literal recognition means provided to recognize a letter from a literal image of the literal positional region obtained from the letter region extracting means;

an image emphasis means provided to emphasize the literal image of the literal positional region by replacing a part of the letter region extracting means with a filter net which serves as a neural network;

the literal recognition means including a letter recognizing neural network which produces a literal code corresponding to the literal image obtained from the letter region extracting means and fed thereto; and

the image emphasis means further comprising;

the literal image having an area including the license plate having a plurality of image patterns;

a filter net which learns the literal image and an area of the letter region corresponding to each of digits of number of the license plate, and the filter net being partly incorporated into the letter region extracting means so as to obtain an output value which the filter net produces in correspondence to each of the digits of the literal image of the license plate when the input image data is fed; and

a literal image region being emphasized with a logical product of the input image data and the output value produced from the filter net;

the literal image region of each of the digits of the literal image of the license plate being emphasized by providing first means which puts an edge emphasis to a contour area of the obtained image, and further forming a compression image pattern in order to use it to learning data for the filter net; and

second means which puts the edge emphasis to the contour area of the image obtained from the letter region extracting means, and forming a compression image pattern in order to use it for an input pattern fed to the filter net.

4. A license plate information reader device for motor vehicles comprising:

a photographing means provided to produce video image data including a license plate obtained by photographing a front and rear portion of a motor vehicle;

an image taking means having an A/D converter to produce a digital image by A/D converting the video image data;

a license plate extracting means provided to detect a position of the license plate in the digital image data so as to produce an image including the license plate;

a literal regional extracting means provided to extract a literal positional region of a letter sequence of the license plate based on the image obtained from the license plate extracting means;

a literal recognition means provided to recognize a letter from a literal image of the literal positional region obtained from the letter region extracting means;

an image emphasis means provided to emphasize the literal image of the literal positional region by replacing a part of the letter region extracting means with a filter net which serves as a neural network;

the literal recognition means including a letter recognizing neural network which produces a literal code corresponding to the literal image obtained from the letter region extracting means and fed thereto;

the image emphasis means further comprising;

the literal image having an area including the license plate having a plurality of image patterns;

a filter net which learns the literal image and an area of the letter region corresponding to each of digits of number of the license plate, and the filter net being partly incorporated into the letter region extracting means so as to obtain an output value which the filter net produces in correspondence to each of the digits and the literal image of the license plate when the input image data is fed; and

a literal image region being emphasized with a logical product of the input image data and the output value produced from the filter net.