CN113378797A - Water drop detection method for fingerprint collecting head - Google Patents
Water drop detection method for fingerprint collecting head Download PDFInfo
- Publication number
- CN113378797A CN113378797A CN202110794729.0A CN202110794729A CN113378797A CN 113378797 A CN113378797 A CN 113378797A CN 202110794729 A CN202110794729 A CN 202110794729A CN 113378797 A CN113378797 A CN 113378797A
- Authority
- CN
- China
- Prior art keywords
- area
- image
- gray
- value
- map
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 38
- 238000001514 detection method Methods 0.000 title claims abstract description 21
- 230000002159 abnormal effect Effects 0.000 claims description 22
- 238000000034 method Methods 0.000 claims description 12
- 230000011218 segmentation Effects 0.000 claims description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000007797 corrosion Effects 0.000 description 3
- 238000005260 corrosion Methods 0.000 description 3
- 230000003628 erosive effect Effects 0.000 description 3
- 230000010339 dilation Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 241001085205 Prenanthella exigua Species 0.000 description 1
- 230000002547 anomalous effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000008961 swelling Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4007—Scaling of whole images or parts thereof, e.g. expanding or contracting based on interpolation, e.g. bilinear interpolation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20036—Morphological image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of fingerprint identification, and discloses a water drop detection method of a fingerprint acquisition head.
Description
Technical Field
The invention relates to the technical field of fingerprint identification, in particular to a water drop detection method of a fingerprint acquisition head.
Background
With the development of the internet of things technology, fingerprint identification has been widely applied to the fields of entrance guard, attendance checking, intelligent door lock, mobile phone unlocking and the like as an identity information authentication mode. At present, for the commonly used entrance guard lock or intelligent door lock in the market, if the fingerprint acquisition head of the door lock or the fingerprint acquisition board or the fingerprint acquisition screen has water drops, the normal operation of fingerprint identification can be influenced.
Disclosure of Invention
In view of the deficiencies of the background art, the present invention provides a water droplet detection method for a fingerprint pick-up head to detect the presence of water droplets on the fingerprint pick-up head.
In order to solve the technical problems, the invention provides the following technical scheme: the water drop detection method of the fingerprint collecting head comprises the following steps:
s1: acquiring a fingerprint acquisition image;
s2: calculating the gray difference value of the pixels of the adjacent columns of each row in the fingerprint acquisition image, and if the absolute value of the gray difference value of the pixels of the adjacent columns is greater than a first judgment threshold value, taking the pixels of the adjacent columns as a group of abnormal pixels;
s3: repeatedly executing the step S2 until the calculation and judgment of the gray scale difference values of the pixels of the adjacent columns of all the rows are completed;
s4: and counting the number of all abnormal pixels, and if the number of all the abnormal pixels is greater than a second judgment threshold value, judging that water drops exist on the fingerprint acquisition head.
In one embodiment, in executing steps S2 and S3, the fingerprint collection image is further reduced to obtain a thumbnail; if the number of all the abnormal pixels is less than or equal to the second determination threshold in step S4, the following steps are performed:
s5: performing global threshold segmentation on the thumbnail to generate a first intermediate map, which specifically comprises the following steps: acquiring gray values of pixel points of an ith row and a j column of the thumbnail to judge, wherein i and j are both even numbers, if the gray values of the pixels of the ith row and the j column of the thumbnail are smaller than a third judgment threshold, the gray values of the i/2 th row and the j/2 th column of the first intermediate map are 255, otherwise, the gray values of the i/2 nd row and the j/2 th column of the first intermediate map are 0;
s6: expanding and corroding a region with the gray value of 255 in the first intermediate map to generate a second intermediate map, expanding the second intermediate map to generate a third intermediate map, calculating the ratio of the area of the region with the gray value of 255 in the third intermediate map to the area of the whole third intermediate map, and if the ratio of the area of the region with the gray value of 255 in the third intermediate map to the area of the whole third intermediate map is smaller than a fourth judgment threshold, indicating that the effective area of the fingerprint acquisition image acquired in the step S1 is too small, and the detection needs to be finished, otherwise, executing the step S7;
s7: acquiring a fingerprint image in the thumbnail by performing dynamic threshold segmentation on the thumbnail to generate a fourth intermediate map;
s8, obtaining the area of the overlapped part of the area with the gray value of 255 in the third intermediate image and the fourth intermediate image, if the area of the overlapped part is larger than a fourth judgment threshold value, the fingerprint acquisition image is a normal fingerprint image, no water drop exists on the fingerprint acquisition head, the detection is finished, otherwise, the step S9 is carried out;
s9: and judging whether the graph of the area with the gray value of 255 in the third middle graph is concave or convex, if so, judging that the fingerprint acquisition image is a normal fingerprint image and no water drops exist on the fingerprint acquisition head, and if so, judging that the fingerprint acquisition image is a water drop image and the fingerprint acquisition head has water drops.
In certain embodiments, the thumbnail is one-quarter the size of the fingerprint acquisition image.
In certain embodiments, the process of generating the third intermediate map in step S6 is as follows: if the gray values of the pixel points in the m-th row and the n-th column of the second intermediate image are greater than the fifth judgment threshold, the gray values of the pixel points in the x-th row and the y-th column of the third intermediate image are 255, the gray values of the pixel points in the x-th row and the y-1-th column of the third intermediate image are 255, the gray values of the pixel points in the x-th row and the j-th column of the third intermediate image are 255, the gray values of the pixel points in the x-th row and the y-th column of the third intermediate image are 255, otherwise the gray values of the pixel points in the x-th row and the y-th column of the third intermediate image are 0, the gray values of the pixel points in the x-th row and the y-th column of the third intermediate image are 0.
In one embodiment, in step S5, the grayscale mean of the thumbnail is obtained, and the process of generating the fourth middle map in step S7 is as follows: and if the gray value of the pixel point of the j row and the k column of the thumbnail is subtracted by the gray value of the pixel point of the j row and the k column of the fifth intermediate image and then is larger than the dynamic threshold value, the gray value of the pixel point of the j row and the k column of the fourth intermediate image is 255, otherwise, the gray value of the pixel point of the j row and the k column of the fourth intermediate image is 0.
In one embodiment, in step S6, if the ratio of the area with the grayscale value of 255 in the third intermediate map to the area of the entire third intermediate map is greater than or equal to the fourth determination threshold, the central pixel coordinates (midX, midY) of the area with the grayscale value of 255 in the third intermediate map are obtained, and the specific step of determining whether the graph of the area with the grayscale value of 255 in the third intermediate map is concave or convex in step S9 is as follows: the region in the third intermediate map where the gradation value is 255 is regarded as a bright region,
s90: acquiring the heights rHei and lHei of the left edge and the right edge of the bright area and the height midHei of the middle area; if midHei < rHei or midHei < lHei, the following judgment is made: judging whether the gray value of the central point of the bright area is greater than 0 and whether the area of the overlapped part of the areas with the gray values of the third intermediate image and the fourth intermediate image being 255 is greater than a seventh judgment threshold value, if so, judging that the graph of the bright area is convex, and if not, judging that the graph of the bright area is concave; otherwise, executing step S91; the seventh determination threshold value is 100
S91: if midHei > rHei and midHei > lHei, and midHei is greater than the tenth determination threshold, the pattern of the bright area is convex; otherwise, executing step S92; the tenth determination threshold is two-thirds of the thumbnail height;
s92, obtaining widths tWid and bWid of the upper edge and the lower edge of the bright area and width midWid of the middle area, if midWid < tWid-C or midWid < bWid-C, making the following judgment: judging whether the gray value of the central point of the bright area is greater than 0 or not, and whether the area of the overlapped part of the areas with the gray values of the third intermediate image and the fourth intermediate image being 255 is greater than a seventh judgment threshold or not, if so, judging that the graph of the bright area is convex, and if not, judging that the graph of the bright area is concave; otherwise, executing step S93;
s93: if midWid > tWid and midWid > bWid, and midWid > eleventh decision threshold, the pattern of the bright region is convex; otherwise, executing step S94; the eleventh determination threshold is two-thirds of the thumbnail width;
s94, acquiring the width darkWid and the height darkHei of the bright area, and if the darkWid is larger than an eighth judgment threshold and the ratio of the area with the gray value of 255 in the third middle image to the area of the whole third middle image is smaller than a ninth judgment threshold, the graph of the bright area is concave; if darkHei is greater than the eighth determination threshold value and the ratio of the area of the region in the third intermediate map where the gradation value is 255 to the area of the entire third intermediate map is less than the ninth determination threshold value, the pattern of the bright region is concave.
Compared with the prior art, the invention has the beneficial effects that: calculating and judging gray level difference values of pixel points of adjacent columns of all rows of the fingerprint acquisition image to find abnormal pixel points in the fingerprint acquisition image, counting all the abnormal pixel points in the fingerprint acquisition image, and judging whether water drops exist on a fingerprint acquisition head when the number of all the abnormal pixel points is greater than a second judgment threshold value;
in addition, in order to ensure the accuracy of the water drop detection result, when the number of all abnormal pixels is larger than a second judgment threshold, the fingerprint acquisition image is reduced to obtain a thumbnail, the thumbnail is subjected to global threshold segmentation, expansion, corrosion and expansion to obtain a third intermediate image, the thumbnail is subjected to dynamic threshold segmentation to obtain a fourth intermediate image, the area of an overlapped area of which the gray value of the third intermediate image and the gray value of the fourth intermediate image are 255 is obtained, when the area of the overlapped area is larger than the fourth judgment threshold, the fingerprint acquisition image is considered to be a normal fingerprint image, when the area of the overlapped area is smaller than or equal to the fourth judgment threshold, whether the fingerprint acquisition image is a normal fingerprint image or a water drop image is judged by judging whether the graph of a bright area of the third intermediate image is convex or concave, so that whether the water drop exists on the fingerprint acquisition head can be detected by a multiple judgment mode, the accuracy of the detection result is ensured;
in addition, in the steps of the invention, the thumbnail is subjected to further abbreviation after global threshold segmentation, and then expansion, corrosion and expansion are carried out, rather than the thumbnail is directly subjected to expansion, corrosion and expansion, so that the detection time can be reduced.
Drawings
FIG. 1 is a schematic illustration of a normal fingerprint acquisition image;
FIG. 2 is a schematic illustration of an anomalous fingerprint acquisition image;
FIG. 3 is a schematic view of an image taken from a fingerprint acquisition head with water droplets thereon;
FIG. 4 is another schematic view of an image taken from a fingerprint acquisition head with water droplets thereon;
FIG. 5 is a flow chart of the present invention;
FIG. 6 is a schematic diagram of a thumbnail in an embodiment;
FIG. 7 is a schematic view of a first intermediate diagram in the embodiment;
FIG. 8 is a schematic diagram showing the effect of swelling and erosion on an image in the example;
FIG. 9 is a schematic view of a second intermediate view in the embodiment;
FIG. 10 is a schematic view of a third intermediate view in the embodiment;
fig. 11 is a schematic view of a fourth intermediate diagram in the embodiment.
Detailed Description
The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic views illustrating only the basic structure of the present invention in a schematic manner, and thus show only the constitution related to the present invention.
As can be seen from fig. 1 to 4, the normal fingerprint collection image is black in the middle and bright on both sides, and the black parts are distributed in a stripe shape. When water drops exist on the fingerprint acquisition head, two conditions can be caused, firstly, an image acquisition sensor for acquiring a fingerprint acquisition image is abnormal and cannot acquire images normally, the acquired images are as shown in fig. 2, the gray values of pixels between adjacent rows of the abnormal fingerprint acquisition image are discontinuous and have large differences, and secondly, the image acquisition sensor normally acquires images, but the images of the water drops are acquired, as shown in fig. 3 and 4, when the water drops exist on the fingerprint acquisition head, the acquired images are bright in the middle and dark at two sides. Based on the difference of the images in fig. 1 to 4, the specific steps of the present invention are as follows: overall flow diagram referring to figure 5,
the water drop detection method of the fingerprint collecting head comprises the following steps:
s1: acquiring a fingerprint acquisition image;
s2: calculating the gray difference value of the pixels of the adjacent columns of each row in the fingerprint acquisition image, and if the absolute value of the gray difference value of the pixels of the adjacent columns is greater than a first judgment threshold value, taking the pixels of the adjacent columns as a group of abnormal pixels;
s3: repeatedly executing the step S2 until the calculation and judgment of the gray scale difference values of the pixels of the adjacent columns of all the rows are completed;
s4: and counting the number of all abnormal pixels, and if the number of all the abnormal pixels is greater than a second judgment threshold value, judging that water drops exist on the fingerprint acquisition head.
Wherein the fingerprint collection image in step S1 is an image at the fingerprint collection head collected by the image sensor.
In practical use, the number of all abnormal pixels is counted by calculating the gray level difference of the pixels of the adjacent columns of the fingerprint acquisition image, and the fingerprint acquisition image can be considered as an abnormal image when the number of the abnormal pixels is larger than a first judgment threshold value, and water drops are arranged at the position of the fingerprint acquisition head.
As can be seen from fig. 5, in the present embodiment, the first determination threshold is 105, the second determination threshold is 100, and the total number of abnormal pixels is replaced with gusassnum. In actual use, the value of the first judgment threshold value and the value of the second judgment threshold value can be reset according to the acquisition area of the fingerprint acquisition head, the specific size can be determined according to actual needs, and the method is not limited here.
In actual use, when steps S2 and S3 are executed, the fingerprint collection image is further reduced to obtain a thumbnail, the obtained thumbnail may refer to fig. 6, in the flowchart of fig. 5, zoomlig represents the thumbnail, and the thumbnail is obtained for further detection and judgment; in the embodiment, in order to shorten the detection time, in the fingerprint acquisition image, the fingerprint acquisition image is reduced to one fourth of the original image in an interlaced and alternate dot mode; the fingerprint acquisition image can be reduced to the target size according to the actual requirement in the actual use process; in addition, in practical use, the fingerprint collection image can be reduced in a linear interpolation mode, but the method is long in time consumption and not an optimal choice.
When the number of all the abnormal pixels is less than or equal to the second determination threshold in step S4, the following steps are performed:
s5: performing global threshold segmentation on the thumbnail to generate a first intermediate graph, wherein in the flowchart of fig. 5, the darkReg is the first intermediate graph, and the details are as follows: acquiring gray values of pixel points of an ith row and a j column of the thumbnail and judging, wherein i and j are even numbers, if the gray values of the pixels of the ith row and the j column of the thumbnail are smaller than a third judgment threshold, the gray values of the i/2 th row and the j/2 th column of the first intermediate image are 255, otherwise, the gray values of the i/2 nd row and the j/2 th column of the first intermediate image are 0; in order to shorten the actual detection, in step S5, a pixel point is also extracted from the thumbnail by interlacing and extracting a pixel point for global threshold segmentation, and the first intermediate image generated finally is shown in fig. 7; in step S5, a first intermediate map is generated by interlacing and spacing pixels, where the first intermediate map is one-fourth of the size of the thumbnail;
s6: expanding and corroding a region with the gray value of 255 in the first intermediate map to generate a second intermediate map, expanding the second intermediate map to generate a third intermediate map, in the flowchart of fig. 5, dilReg refers to a map of the expanded first intermediate map, eroReg refers to the second intermediate map, and dark regbig refers to the third intermediate map, calculating the ratio of the area of the region with the gray value of 255 in the third intermediate map to the area of the whole third intermediate map, and if the ratio of the area of the region with the gray value of 255 in the third intermediate map to the area of the whole third intermediate map is smaller than a fourth judgment threshold, explaining that the effective area of the fingerprint collection image obtained in step S1 needs to be ended, otherwise, executing step S7 to be too small; the size of the third intermediate map in step S6 is the same as the size of the thumbnail, so the expansion ratio in step S6 is the same as the reduction ratio of the thumbnail to the first intermediate map in step S5;
specifically, the dilation and erosion in step S6 refer to morphological operations, similar to contour detection, in which dilation is to enlarge a bright white area in an image by adding pixels to a perceptual boundary of an object in the image, and erosion refers to, conversely, to remove pixels along the object boundary and reduce the size of the object, and a specific effect diagram may refer to fig. 8, where the middle image in fig. 8 is an original image, the left image in fig. 8 is an eroded image, and the right image in fig. 8 is an dilated image; in this embodiment, a schematic diagram of the second intermediate diagram is shown in fig. 9.
Specifically, in this embodiment, the second intermediate map is expanded to four times the original one, and the specific steps are as follows: if the gray values of the pixel points of the m-th row and the n-th column of the second middle graph are larger than the fifth judgment threshold, the gray scale value of the pixel point of the x-th row and the y-th column of the third intermediate image is 255, the gray scale value of the pixel point of the x-th row and the y + 1-th column of the third intermediate image is 255, otherwise, the gray scale value of the pixel point of the x-th row and the y-th column of the third intermediate image is 0, the gray scale value of the pixel point of the x-th row and the y + 1-th column of the third intermediate image is 0, the gray scale value of the pixel point of the x-th row and the y-th column of the third intermediate image is 0, and the gray scale value of the pixel point of the x-th row + 1-th column and the y + 1-th column of the third intermediate image is 0, where x is m × 2, y is n × 2, and the fifth determination threshold is 0, the generated third intermediate graph is shown in fig. 10;
s7: acquiring a fingerprint image in the thumbnail by performing dynamic threshold segmentation on the thumbnail to generate a fourth intermediate map; in the flowchart of fig. 5, dynImg refers to the fourth intermediate diagram;
specifically, in order to reduce the detection time, in step S5, the grayscale mean of the thumbnail is acquired, and the process of generating the fourth middle map in step S7 is as follows: if the gray-scale mean value is greater than the sixth determination threshold, setting the dynamic threshold as the first numerical value, otherwise, setting the dynamic threshold as the second numerical value, where the first numerical value is less than the second numerical value, performing mean filtering on the thumbnail to generate a fifth intermediate map, where if the gray-scale values of the pixel points in the j-th row and the k-th column of the thumbnail minus the gray-scale values of the pixel points in the j-th row and the k-th column of the fifth intermediate map are greater than the dynamic threshold, the gray-scale values of the pixel points in the j-th row and the k-th column of the fourth intermediate map are 255, otherwise, the gray-scale values of the pixel points in the j-th row and the k-th column of the fourth intermediate map are 0, and the finally generated fourth intermediate map is shown in fig. 11.
S8, obtaining the area of the overlapped part of the area with the gray value of 255 in the third intermediate image and the fourth intermediate image, if the area of the overlapped part is larger than a fourth judgment threshold value, the fingerprint acquisition image is a normal fingerprint image, no water drop exists on the fingerprint acquisition head, the detection is finished, otherwise, the step S9 is carried out; in the present embodiment, the fourth determination threshold is 500; in the flowchart of fig. 5, the area of the overlapped portion refers to lineSum;
s9: and judging whether the graph of the area with the gray value of 255 in the third middle graph is concave or convex, if so, judging that the fingerprint acquisition image is a normal fingerprint image and no water drops exist on the fingerprint acquisition head, and if so, judging that the fingerprint acquisition image is a water drop image and the fingerprint acquisition head has water drops.
Specifically, in order to perform step S9, in step S6, if the ratio of the area of the region in the third intermediate map whose gradation value is 255 to the area of the entire third intermediate map is greater than or equal to the fourth determination threshold, the center pixel point coordinates (midX, midY) of the region in the third intermediate map whose gradation value is 255 are acquired, and the specific step of determining whether the pattern of the region in the third intermediate map whose gradation value is 255 is concave or convex in step S9 is as follows: the region in the third intermediate map where the gradation value is 255 is regarded as a bright region,
s90: acquiring the heights rHei and lHei of the left edge and the right edge of the bright area and the height midHei of the middle area; if midHei < rHei or midHei < lHei, the following judgment is made: judging whether the gray value of the central point of the bright area is greater than 0 and whether the area of the overlapped part of the areas with the gray values of the third intermediate image and the fourth intermediate image being 255 is greater than a seventh judgment threshold value, if so, judging that the graph of the bright area is convex, and if not, judging that the graph of the bright area is concave; otherwise, executing step S91;
s91: if midHei > rHei and midHei > lHei, and midHei is greater than the tenth determination threshold, the pattern of the bright area is convex; otherwise, executing step S92; in the present embodiment, the tenth determination threshold is two thirds of the height of the thumbnail;
s92, obtaining widths tWid and bWid of the upper edge and the lower edge of the bright area and width midWid of the middle area, if midWid < tWid or midWid < bWid, making the following judgment: judging whether the gray value of the central point of the bright area is greater than 0 or not, and whether the area of the overlapped part of the areas with the gray values of the third intermediate image and the fourth intermediate image being 255 is greater than a seventh judgment threshold or not, if so, judging that the graph of the bright area is convex, and if not, judging that the graph of the bright area is concave; otherwise, executing step S93;
s93: if midWid > tWid and midWid > bWid, and midWid > eleventh decision threshold, the pattern of the bright region is convex; otherwise, executing step S94; in the present embodiment, the eleventh determination threshold is two thirds of the thumbnail width
S94, acquiring the width darkWid and the height darkHei of the bright area, and if the darkWid is larger than an eighth judgment threshold and the ratio of the area with the gray value of 255 in the third middle image to the area of the whole third middle image is smaller than a ninth judgment threshold, the graph of the bright area is concave; if darkHei is greater than the eighth determination threshold value, and the ratio of the area of the region in the third intermediate map where the gradation value is 255 to the area of the entire third intermediate map is less than the ninth determination threshold value, the pattern of the bright region is concave, which is 30 in this embodiment, and the eighth determination threshold value is 70.
In light of the foregoing, it is to be understood that various changes and modifications may be made by those skilled in the art without departing from the spirit and scope of the invention. The technical scope of the present invention is not limited to the content of the specification, and must be determined according to the scope of the claims.
Claims (6)
1. The water drop detection method of the fingerprint collecting head is characterized by comprising the following steps:
s1: acquiring a fingerprint acquisition image;
s2: calculating the gray difference value of the pixels of the adjacent columns of each row in the fingerprint acquisition image, and if the absolute value of the gray difference value of the pixels of the adjacent columns is greater than a first judgment threshold value, taking the pixels of the adjacent columns as a group of abnormal pixels;
s3: repeatedly executing the step S2 until the calculation and judgment of the gray scale difference values of the pixels of the adjacent columns of all the rows are completed;
s4: and counting the number of all abnormal pixels, and if the number of all the abnormal pixels is greater than a second judgment threshold value, judging that water drops exist on the fingerprint acquisition head.
2. The water droplet detecting method of a fingerprint pick-up head as claimed in claim 1, wherein in performing steps S2 and S3, further reducing the fingerprint pick-up image to obtain a thumbnail image; if the number of all the abnormal pixels is less than or equal to the second determination threshold in step S4, the following steps are performed:
s5: performing global threshold segmentation on the thumbnail to generate a first intermediate map, which specifically comprises the following steps: acquiring gray values of pixel points of an ith row and a j column of the thumbnail to judge, wherein i and j are both even numbers, if the gray values of the pixels of the ith row and the j column of the thumbnail are smaller than a third judgment threshold, the gray values of the i/2 th row and the j/2 th column of the first intermediate map are 255, otherwise, the gray values of the i/2 nd row and the j/2 th column of the first intermediate map are 0;
s6: expanding and corroding a region with the gray value of 255 in the first intermediate map to generate a second intermediate map, expanding the second intermediate map to generate a third intermediate map, calculating the ratio of the area of the region with the gray value of 255 in the third intermediate map to the area of the whole third intermediate map, and if the ratio of the area of the region with the gray value of 255 in the third intermediate map to the area of the whole third intermediate map is smaller than a fourth judgment threshold, indicating that the effective area of the fingerprint acquisition image acquired in the step S1 is too small, and the detection needs to be finished, otherwise, executing the step S7;
s7: acquiring a fingerprint image in the thumbnail by performing dynamic threshold segmentation on the thumbnail to generate a fourth intermediate map;
s8, obtaining the area of the overlapped part of the area with the gray value of 255 in the third intermediate image and the fourth intermediate image, if the area of the overlapped part is larger than a fourth judgment threshold value, the fingerprint acquisition image is a normal fingerprint image, no water drop exists on the fingerprint acquisition head, the detection is finished, otherwise, the step S9 is carried out;
s9: and judging whether the graph of the area with the gray value of 255 in the third middle graph is concave or convex, if so, judging that the fingerprint acquisition image is a normal fingerprint image and no water drops exist on the fingerprint acquisition head, and if so, judging that the fingerprint acquisition image is a water drop image and the fingerprint acquisition head has water drops.
3. The method of claim 2, wherein the thumbnail is one-quarter of the size of the fingerprint collection image.
4. The method for detecting water drops in a fingerprint pick-up head as claimed in claim 2, wherein in step S6, the process of generating the third middle map is as follows: if the gray values of the pixel points in the m-th row and the n-th column of the second intermediate image are greater than the fifth judgment threshold, the gray values of the pixel points in the x-th row and the y-th column of the third intermediate image are 255, the gray values of the pixel points in the x-th row and the y-1-th column of the third intermediate image are 255, the gray values of the pixel points in the x-th row and the j-th column of the third intermediate image are 255, the gray values of the pixel points in the x-th row and the y-th column of the third intermediate image are 255, otherwise the gray values of the pixel points in the x-th row and the y-th column of the third intermediate image are 0, the gray values of the pixel points in the x-th row and the y-th column of the third intermediate image are 0.
5. The method for detecting water drops in a fingerprint pick-up head as claimed in claim 2, wherein in step S5, the average gray scale value of the thumbnail is obtained, and the step S7 generates the fourth intermediate map as follows: and if the gray value of the pixel point of the j row and the k column of the thumbnail is subtracted by the gray value of the pixel point of the j row and the k column of the fifth intermediate image and then is larger than the dynamic threshold value, the gray value of the pixel point of the j row and the k column of the fourth intermediate image is 255, otherwise, the gray value of the pixel point of the j row and the k column of the fourth intermediate image is 0.
6. The method of claim 2, wherein if the ratio of the area with the gray level value of 255 in the third middle map to the area of the entire third middle map is greater than or equal to the fourth determination threshold in step S6, the step S9 is performed to determine whether the pattern of the area with the gray level value of 255 in the third middle map is concave or convex by obtaining the coordinates (midX, midY) of the center pixel of the area with the gray level value of 255 in the third middle map as follows: the region in the third intermediate map where the gradation value is 255 is regarded as a bright region,
s90: acquiring the heights rHei and lHei of the left edge and the right edge of the bright area and the height midHei of the middle area; if midHei < rHei or midHei < lHei, the following judgment is made: judging whether the gray value of the central point of the bright area is greater than 0 and whether the area of the overlapped part of the areas with the gray values of the third intermediate image and the fourth intermediate image being 255 is greater than a seventh judgment threshold value, if so, judging that the graph of the bright area is convex, and if not, judging that the graph of the bright area is concave; otherwise, executing step S91;
s91: if midHei > rHei and midHei > lHei, and midHei is greater than the tenth determination threshold, the pattern of the bright area is convex; otherwise, executing step S92;
s92, obtaining widths tWid and bWid of the upper edge and the lower edge of the bright area and width midWid of the middle area, if midWid < tWid or midWid < bWid, making the following judgment: judging whether the gray value of the central point of the bright area is greater than 0 or not, and whether the area of the overlapped part of the areas with the gray values of the third intermediate image and the fourth intermediate image being 255 is greater than a seventh judgment threshold or not, if so, judging that the graph of the bright area is convex, and if not, judging that the graph of the bright area is concave; otherwise, executing step S93;
s93: if midWid > tWid and midWid > bWid, and midWid > eleventh decision threshold, the pattern of the bright region is convex; otherwise, executing step S94;
s94, acquiring the width darkWid and the height darkHei of the bright area, and if the darkWid is larger than an eighth judgment threshold and the ratio of the area with the gray value of 255 in the third middle image to the area of the whole third middle image is smaller than a ninth judgment threshold, the graph of the bright area is concave; if darkHei is greater than the eighth determination threshold value and the ratio of the area of the region in the third intermediate map where the gradation value is 255 to the area of the entire third intermediate map is less than the ninth determination threshold value, the pattern of the bright region is concave.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110794729.0A CN113378797B (en) | 2021-07-14 | 2021-07-14 | Water drop detection method of fingerprint acquisition head |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110794729.0A CN113378797B (en) | 2021-07-14 | 2021-07-14 | Water drop detection method of fingerprint acquisition head |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113378797A true CN113378797A (en) | 2021-09-10 |
| CN113378797B CN113378797B (en) | 2024-06-11 |
Family
ID=77582027
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110794729.0A Active CN113378797B (en) | 2021-07-14 | 2021-07-14 | Water drop detection method of fingerprint acquisition head |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113378797B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115100086A (en) * | 2022-07-01 | 2022-09-23 | 江阴邦融微电子有限公司 | Water drop image processing method based on embedded platform |
| CN115880730A (en) * | 2023-03-08 | 2023-03-31 | 杭州八爪鱼微电子有限公司 | Fingerprint acquisition method and system, fingerprint acquisition equipment and readable storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006261761A (en) * | 2005-03-15 | 2006-09-28 | Secom Co Ltd | Image signal processing apparatus |
| JP2010231418A (en) * | 2009-03-26 | 2010-10-14 | Oki Semiconductor Co Ltd | Fingerprint reading device |
| JP2011078047A (en) * | 2009-10-02 | 2011-04-14 | Sanyo Electric Co Ltd | Imaging apparatus |
| CN102413354A (en) * | 2011-10-05 | 2012-04-11 | 深圳市联德合微电子有限公司 | Automatic optical detection method, device and system of mobile phone camera module |
| TW201524188A (en) * | 2013-12-10 | 2015-06-16 | Univ Nat Kaohsiung Applied Sci | Detecting method of abnormality of image capturing by camera |
| CN105491372A (en) * | 2015-11-24 | 2016-04-13 | 努比亚技术有限公司 | Mobile terminal and information processing method |
| US20160301857A1 (en) * | 2015-04-07 | 2016-10-13 | Fotonation Limited | Image processing method and apparatus |
| CN110532876A (en) * | 2019-07-26 | 2019-12-03 | 纵目科技（上海）股份有限公司 | Night mode camera lens pays detection method, system, terminal and the storage medium of object |
| CN110766679A (en) * | 2019-10-25 | 2020-02-07 | 普联技术有限公司 | Lens contamination detection method and device and terminal equipment |
| CN112016426A (en) * | 2020-08-20 | 2020-12-01 | 深圳市锐尔觅移动通信有限公司 | Fingerprint acquisition method and device |
| US20210067768A1 (en) * | 2018-02-16 | 2021-03-04 | Mitsubishi Electric Corporation | Abnormality detection device and abnormality detection method |
-
2021
- 2021-07-14 CN CN202110794729.0A patent/CN113378797B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006261761A (en) * | 2005-03-15 | 2006-09-28 | Secom Co Ltd | Image signal processing apparatus |
| JP2010231418A (en) * | 2009-03-26 | 2010-10-14 | Oki Semiconductor Co Ltd | Fingerprint reading device |
| JP2011078047A (en) * | 2009-10-02 | 2011-04-14 | Sanyo Electric Co Ltd | Imaging apparatus |
| CN102036013A (en) * | 2009-10-02 | 2011-04-27 | 三洋电机株式会社 | Imaging apparatus |
| CN102413354A (en) * | 2011-10-05 | 2012-04-11 | 深圳市联德合微电子有限公司 | Automatic optical detection method, device and system of mobile phone camera module |
| TW201524188A (en) * | 2013-12-10 | 2015-06-16 | Univ Nat Kaohsiung Applied Sci | Detecting method of abnormality of image capturing by camera |
| US20160301857A1 (en) * | 2015-04-07 | 2016-10-13 | Fotonation Limited | Image processing method and apparatus |
| CN105491372A (en) * | 2015-11-24 | 2016-04-13 | 努比亚技术有限公司 | Mobile terminal and information processing method |
| US20210067768A1 (en) * | 2018-02-16 | 2021-03-04 | Mitsubishi Electric Corporation | Abnormality detection device and abnormality detection method |
| CN110532876A (en) * | 2019-07-26 | 2019-12-03 | 纵目科技（上海）股份有限公司 | Night mode camera lens pays detection method, system, terminal and the storage medium of object |
| CN110766679A (en) * | 2019-10-25 | 2020-02-07 | 普联技术有限公司 | Lens contamination detection method and device and terminal equipment |
| CN112016426A (en) * | 2020-08-20 | 2020-12-01 | 深圳市锐尔觅移动通信有限公司 | Fingerprint acquisition method and device |
Non-Patent Citations (3)
| Title |
|---|
| HSIEN-CHOU LIAO ET AL: "Video-based water drop detection and removal method for a moving vehicle", 《NFORMATION TECHNOLOGY JOURNAL》, vol. 12, no. 4, pages 569 - 583, XP055240203, DOI: 10.3923/itj.2013.569.583 * |
| 朱永珍: "基于机器视觉的障碍导航辅助***", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》, no. 3, pages 1 - 82 * |
| 薛金利 等: "轨道机车车辆自动检测***性能提升方法", 《电力机车与城轨车辆》, vol. 44, no. 3, pages 79 - 84 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115100086A (en) * | 2022-07-01 | 2022-09-23 | 江阴邦融微电子有限公司 | Water drop image processing method based on embedded platform |
| CN115100086B (en) * | 2022-07-01 | 2024-01-30 | 江阴邦融微电子有限公司 | Water drop image processing method based on embedded platform |
| CN115880730A (en) * | 2023-03-08 | 2023-03-31 | 杭州八爪鱼微电子有限公司 | Fingerprint acquisition method and system, fingerprint acquisition equipment and readable storage medium |
| CN115880730B (en) * | 2023-03-08 | 2023-08-04 | 杭州八爪鱼微电子有限公司 | Fingerprint acquisition method, fingerprint acquisition system, fingerprint acquisition equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113378797B (en) | 2024-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113592861B (en) | Bridge crack detection method based on dynamic threshold | |
| CN108038883B (en) | Crack detection and identification method applied to highway pavement video image | |
| EP1725975B1 (en) | Method, apparatus and program for detecting an object | |
| CN113378797B (en) | Water drop detection method of fingerprint acquisition head | |
| CN115880304B (en) | Pillow defect identification method based on complex scene | |
| CN109242870A (en) | A kind of sea horizon detection method divided based on image with textural characteristics | |
| CN111382704A (en) | Vehicle line-pressing violation judgment method and device based on deep learning and storage medium | |
| CN115861320B (en) | Intelligent detection method for automobile part machining information | |
| CN114820625B (en) | Automobile top block defect detection method | |
| CN111080650B (en) | Method for detecting looseness and loss faults of small part bearing blocking key nut of railway wagon | |
| CN109540925B (en) | Complex ceramic tile surface defect detection method based on difference method and local variance measurement operator | |
| CN109815961B (en) | Pavement repairing type disease detection method based on local texture binary pattern | |
| CN111539980B (en) | Multi-target tracking method based on visible light | |
| CN113012124B (en) | Shoe print hole and embedded object feature detection and description method | |
| CN111738256A (en) | Composite material CT image segmentation method based on improved watershed algorithm | |
| CN114972397A (en) | Infrared image defect contour detection method for wind power blade composite material | |
| CN114972173A (en) | Defect detection method, defect detection device and system | |
| CN109978916B (en) | Vibe moving target detection method based on gray level image feature matching | |
| CN108765456A (en) | Method for tracking target, system based on linear edge feature | |
| CN115240197A (en) | Image quality evaluation method, image quality evaluation device, electronic apparatus, scanning pen, and storage medium | |
| CN112289377B (en) | Method, apparatus and computer program product for detecting bright spots on an image | |
| CN112085723A (en) | Automatic detection method for spring jumping fault of truck bolster | |
| CN109117843B (en) | Character occlusion detection method and device | |
| JP2000048120A (en) | Method for extracting character area of gray level image and recording medium having recorded the program thereon | |
| CN116542963A (en) | Float glass defect detection system and detection method based on machine learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |