JPH08110949A - Method for judging quality of fingerprint picture - Google Patents

Abstract

PURPOSE: To quickly and simply judge the quality of an inputted fingerprint picture by inputting and binarizing the fingerprint picture and judging the quality of the picture based upon the rate of the area of a binary picture in a prescribed area around the center of gravity of the binary picture. CONSTITUTION: An inputted fingerprint picture is binarized. The density of the binary picture is projected and intermediate value picture elements on a density projection plan X in X-axis direction and a density projection plan Y in Y-axis direction are calculated to find out the center of gravity GC of the binary picture of the inputted fingerprint picture. Then, the area S of a binary picture in a prescribed area (e.g. a square area) around the center of gravity GC is found out and the rate of the area S of the binary picture to the prescribed area A is calculated. A binary picture of which S/A value is included within a range of 0.4 to 0.55 is judged as fine quality. When the S/A value exceeds the proper value, the binary picture is judged as of defective quality.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method for determining the image quality of a fingerprint input image when performing fingerprint collation or the like.

[0002]

2. Description of the Related Art In fingerprint matching, the quality of the input image has a great influence on the accuracy of matching. For example,
If the fingerprint surface is excessively dry at the time of input, or if it is wet, the matching accuracy will deteriorate. However, at present, there is a problem that there is no method for determining the quality of a fingerprint image that is input quickly and easily.

[0003]

SUMMARY OF THE INVENTION The present invention was devised to solve such conventional problems, and provides a method for determining the image quality of a fingerprint image for determining the quality of an input image. With the goal.

[0004]

A fingerprint image quality judging method according to the present invention inputs a fingerprint image, binarizes the fingerprint image, finds a center of gravity from a density projection diagram of the binarized image, and sets the center of gravity as the center of gravity. The image quality of the input image is judged based on the ratio of the area of the binarized image in the predetermined area.

[0005]

According to the image quality determination method for a fingerprint image according to the present invention, it is possible to input a fingerprint image, binarize it, and obtain the center of gravity of the fingerprint image from the density projection diagram of this binarized image. It is possible to obtain the area of the binarized image in a predetermined area centered on the center of gravity.

[0006]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Next, one embodiment of a fingerprint image quality determination method according to the present invention will be described with reference to the drawings. FIG. 1 is a flowchart for carrying out the present invention, and FIG. 6 is a block diagram of an apparatus for carrying out the present invention. The present apparatus is composed of, for example, a central processing unit CPU, an image processing unit IPU and an image memory IM, the central processing unit CPU, the image processing unit IPU and the image memory IM are connected by a system bus SB, and the image memory IM and the image processing IM are further connected. The departments IM are connected by a local bus LB.

First, a fingerprint image touching the detection surface is input by an input device (not shown) (step 1-1), and this input image is registered in the image memory IM (step 1-2). The image registered in the image memory IM is taken into the image processing unit IPU via the local bus LB and binarized (step 1-3). Next, this binary image is subjected to density projection (step 1-4), and the density projection diagram is registered in the image memory IM (step 1-5). Then, the density projection diagram in the Y-axis direction in this density projection diagram is defined as Y, and the density projection diagram in the X-axis direction is defined as X, and the intermediate value pixel of these density projection diagrams X and Y is calculated by the central processing unit CPU by the following method. (Step 1-6).

The central processing unit CPU counts the number of pixels of the density projection diagram Y, and calculates a pixel having an intermediate value when the number of pixels is counted in parallel with the X axis. Further, the number of pixels of the density projection diagram X is obtained, and the pixel having an intermediate value when the number of pixels is counted in parallel with the Y axis is obtained. Then, as shown in FIG. 5, when a straight line parallel to the Y-axis and the X-axis is drawn from the pixel of these intermediate values, the intersection point on the above binary image is determined by the central processing unit CPU.
Is calculated (step 1-7). That is, this is the center of gravity GC of the input binary fingerprint image.

Next, the central processing unit CPU obtains the area S of the binary image of a predetermined area (for example, a square area) A with the center of gravity GC as the center, and the area S of this binary image becomes the predetermined area A. The occupied ratio is calculated (step 1-8).

Next, the quality of the image quality is judged based on the ratio (step 1-9). As shown in FIG. 2, when the binary image is good, the S / A ratio is approximately 0.4 to 0.
It has been empirically found to be 55, and a binary image that falls between these two values is judged to be of good quality (step 1-1).
0).

However, as shown in FIG. 3, when the fingerprint surface is too dry, the fingerprint pattern is not input and the image area of the ridge portion decreases. On the other hand, as shown in FIG. 4, when the fingerprint surface is too wet, moisture enters the dents between the ridges, which are taken in as ridges, and the area of the binary image increases conversely. In such a case, the S / A deviates from the proper ratio value, and each is judged to have a defective image quality (step 1-11).

In such a case, the input person is instructed to re-input (step 1-12). When a re-input instruction is issued, the fingerprint input image registered in the image memory IM is erased in step 1-2. When the input person performs the re-input according to the instruction, the re-entered fingerprint image is registered in the image memory IM. Then, the above process is repeated until the S / A falls within the proper range in step 1-9 and the image quality is determined to be good in step 1-10.

[0013]

As described above, according to the present invention, a fingerprint image is inputted and binarized, a center of gravity is obtained from a density projection diagram of this binarized image, and a predetermined area centered on the center of gravity Since the image quality of the input image is determined based on the ratio of the area of the binarized image, the quality of the input fingerprint image can be determined quickly and easily. As a result, proper input is finally realized, and accurate fingerprint matching is performed.

[Brief description of drawings]

FIG. 1 is a flowchart showing an embodiment of the present invention.

FIG. 2 is a diagram showing an example of good image quality.

FIG. 3 is a diagram showing an example of defective image quality due to drying.

FIG. 4 is a diagram showing an example of defective image quality due to moisture.

FIG. 5 is a diagram showing a binary fingerprint image and a density projection diagram.

FIG. 6 is a block diagram of an apparatus for implementing the present invention.

[Explanation of symbols]

 CPU central processing unit IPU image processing unit IM image memory SB system bus LB local bus A predetermined area

Claims (1)

[Claims] 1. A fingerprint image is input, the input image is binarized, the center of gravity of the fingerprint image is obtained from a density projection diagram of the binarized image, and the binarization of a predetermined area centered on the center of gravity is performed. A method for determining the image quality of a fingerprint image, which comprises determining the area of an image and determining the quality of the input image based on the ratio of the area.