TW201621856A - A method for measuring display module gap width - Google Patents

Abstract

A method for measuring display module gap width is provided. The method includes capturing a sample image of the display module, wherein the sample image is divided to a frame region, an inner region, and a gap region. The frame region corresponds to a frame part of the display module, and the inner region corresponds to a display part of the display module, and the gap region corresponds to the gap between the frame part and the display part. Then the method determines a first segment and a second segment of the sample image. Then the method computes the distance between the first segment and the second segment. According to the automatically computed distance, the installation flaw of the display module can be detected and applying the method results in the enhancement of production efficiency and the reduction of human resource costs.

Description

Method for detecting display gap width of a module

The invention relates to a method for detecting the gap width of a display module, in particular to a method for detecting the boundary of each region in the display module by using image recognition technology, and calculating the gap width of the display module according to the corresponding line segment of the region boundary.

Due to the rapid development of modern technology, various production technologies have also been continuously improved. In order to get rid of the labor-intensive methods in the past, the manufacturing industry has gradually moved toward a fully automated production process in order to improve manufacturing efficiency and get rid of the dependence on manpower. ,reduce manufacturing cost.

In the current production process of the display module, the line needs to measure the width of the gap between the display portion of the display module (for example, the display area in the center of the display module) and the frame portion thereof (for example, the frame at the edge of the display module). . In general, when measuring the gap, a digital optical microscope is often used to manually judge the gap width, which causes a problem that the measurement time is too long and the measurement accuracy is insufficient.

In view of the above problems, the present invention provides a method for detecting the gap width of a display module, which can automatically measure the gap by using image recognition technology, thereby reducing human error and avoiding poor test time due to different measurement experience. Different, and further shorten the measurement time, improve measurement accuracy.

The invention provides a method for detecting a gap width of a display module. Firstly, a display module is captured from a first direction to generate an image to be tested. The image to be tested is divided into a frame area, an inner area and a gap area, and the frame area corresponding to the display module The frame portion corresponds to a display portion of the display module, and the gap region corresponds to a gap between the frame portion and the display portion. Then, the first line segment and the second line segment are determined in the image to be tested, the first line segment is a partial boundary of the frame region and the gap region, and the second line segment is a partial boundary between the gap region and the inner region. The distance between the first line segment and the second line segment is then calculated.

In an embodiment of the invention, in the step of determining the first line segment and the second line segment in the image to be tested, first, the image to be tested is binarized and the image is closed to obtain a binarized image. Then, the first boundary and the second boundary are detected according to the binarized image, the first boundary is a boundary between the frame region and the gap region, and the second boundary is a boundary between the gap region and the inner region. Then, the first line segment and the second line segment are determined from the first boundary and the second boundary, respectively. In addition, the distance between the first line segment and the second line segment is the pixel distance between the first line segment and the second line segment, and the actual physical distance is obtained through the conversion process.

In summary, the method for detecting the gap width of the display module of the present invention uses the camera to capture the image to be tested, and uses the image recognition technology to detect the boundary between the frame portion and the gap and the gap and the display portion in the image to be tested. Boundary, and find the straight line segment corresponding to the boundary, and calculate the distance of the gap based on the straight line segment found. By calculating the distance calculated by this automated method, the time and reduction of human strength measurement can be reduced. The error rate further increases production efficiency and reduces labor costs.

The above description of the present invention and the following description of the embodiments of the present invention are intended to illustrate and explain the spirit and principles of the invention.

S101-S105‧‧‧Steps

1‧‧‧ fixture

11, 12, 13, 14‧‧‧ photography modules

2‧‧‧Display module

21, 22, 23, 24‧‧‧ display modules

31, 32, 33‧‧‧ areas

Lines 41a, 41b, 42a, 42b‧‧

S501-S505‧‧‧Steps

1 is a flow chart of a method of detecting a gap width of a display module in accordance with an embodiment of the present invention.

2 is a schematic view of a jig and a display module according to an embodiment of the present invention.

Figure 3 is a schematic diagram of an image to be tested according to an embodiment of the present invention.

Figure 4 is another schematic view of an image to be tested according to an embodiment of the present invention.

Figure 5 is a flow chart showing the steps of determining a first line segment and a second line segment in an image to be tested according to an embodiment of the invention.

The detailed features and advantages of the present invention are set forth in the Detailed Description of the Detailed Description of the <RTIgt; </ RTI> <RTIgt; </ RTI> </ RTI> </ RTI> <RTIgt; The objects and advantages associated with the present invention can be readily understood by those skilled in the art. The following examples are intended to describe the present invention in further detail, but are not intended to limit the scope of the invention.

Please refer to FIG. 1. FIG. 1 is a flow chart of a method for detecting a gap width of a display module according to an embodiment of the present invention. As shown in Fig. 1, in step S101 First, the display module is firstly photographed from the first direction to generate an image to be tested, and the image to be tested is divided into a border area, an inner area, and a gap area. The frame area corresponds to the frame part of the display module (for example, the frame of the display module edge), and the inner area corresponds to the display part of the display module (for example, the display area in the center of the display module), and the gap area corresponds to the frame part and the display part. gap. In addition, please refer to FIG. 2, which is a schematic diagram of a fixture and a display module according to an embodiment of the invention. As shown in FIG. 2, the fixture 1 has four camera modules 11, 12, 13, and 14, which can capture the four corners 21, 22, 23, and 24 of the display module 2 from the first direction, when the display module 2 is placed. On the jig 1, the display module 2 will cover the jig 1 , so the four camera modules 11 to 14 on the jig 1 correspond to the four corners 21 to 24 of the display module 2 to capture the image to be tested.

For the image to be tested, please refer to FIG. 3, which is a schematic diagram of an image to be tested according to an embodiment of the present invention. As shown in FIG. 3, the image to be tested may be a grayscale image, and different regions may have different grayscales, and images with different grayscales have image color differences. The portion with the darkest color of the outermost pixel is the frame area 31, which actually represents the frame portion of the display module 2. The portion with a lighter intermediate color is the gap region 32, which actually represents the gap between the frame portion of the display module 2 and the display portion. The lightest portion of the inner color is the inner region 33, which actually represents the display portion mounted in the display module 2.

Next, in step S103, the first line segment and the second line segment are determined in the image to be tested. For example, please refer to FIG. 4 , which is another schematic diagram of an image to be tested according to an embodiment of the present invention. As shown in FIG. 4 , in this step, an image recognition algorithm may be utilized according to image color difference. Find the horizontal first line segment 41a and vertical To the first line segment 41b, and the lateral second line segment 42a and the longitudinal second line segment 42b, the image recognition algorithm is detailed later. In this way, the image to be tested can be clearly distinguished from the boundary of each region, wherein the horizontal first line segment 41a and the longitudinal first line segment 41b represent the boundary of the frame region and the gap region, and the horizontal second line segment 42a and the longitudinal second line segment 42b represents the boundary between the gap region and the inner region.

Next, in step S105, the distance between the first line segment and the second line segment is calculated. In this step, since the horizontal first line segment 41a and the lateral second line segment 42a are in one-to-one correspondence, the longitudinal first line segment 41b and the longitudinal second line segment 42b are in one-to-one correspondence, so that two corresponding two The line segment calculates the distance between the two line segments, and the foregoing distance may be the difference between the pixels of the two line segments in the image to be tested, and then the actual physical distance is obtained through the conversion formula. For example, in fact, the distance between pixels and the physical distance may have a certain proportional relationship, such that one pixel corresponds to a certain centimeter, so the corresponding physical distance can be converted through the proportional relationship, but the present invention does not Define the method of calculating the distance.

In step S105 of the foregoing FIG. 1 , the algorithm for determining the first line segment and the second line segment in the image to be tested is referred to FIG. 5 , and FIG. 5 is determined in the image to be tested according to an embodiment of the present invention. A flowchart of the steps of the first line segment and the second line segment is as shown in FIG. 5. In step S501, the image to be tested is first binarized and the image is closed to obtain a binarized image. The Otsu’s method and the Closing method are used in this step.

The Otsu algorithm is to find out a certain threshold and divide the image into two parts, the foreground object and the background object, according to the pixel gray scale of the image. Like binarization. Through the Otsu algorithm algorithm, the foreground and background of the image to be tested can be distinguished first to provide subsequent processing. For example, after performing the foregoing algorithm, the foreground object pixels in the image may be represented in black, and the background object pixels may be represented in white to further obtain a binarized image. The foreground background classification method of the present invention is not limited to this algorithm.

Then, after obtaining the binarized image processed by the algorithm described above, the foreground object in the image is closed by using the image closing method. The reason for taking this step in the image processing process is that after the foreground image is distinguished by the foreground scene, the edge of each foreground object that is distinguished by the foreground image is not necessarily a closed curve, and there may be a depression or break due to the misclassification of the foreground background. A hole or break that causes the foreground object to be incomplete. Therefore, the binarized image can be further reused by the image closure method to solve the above problem. The step of the image closure method is to first dilate the image and then erode (Erosion) to achieve the effect of closing the foreground object of the image. The image closure method of the present invention is not limited to this algorithm.

Next, in step S503, the first boundary and the second boundary are detected according to the binarized image, the first boundary is a boundary between the frame region and the gap region, and the second boundary is a boundary between the gap region and the inner region. The method of detecting image boundaries in this step uses Canny edge detection. Canni edge detection mainly uses Gaussian filter to reduce image noise, find the brightness gradient in the image, and then use threshold to classify whether each pixel belongs to the edge point, and obtain the binarized image of the edge of the object. The edge detection method of the present invention is not limited to this algorithm.

Next in step S505, respectively from the first boundary and the second boundary In the middle line, the first line segment and the second line segment are determined. The Hough transform algorithm is used in this step. Huo-style conversion is a method for recognizing geometric shapes in image processing. It is widely used in image processing and is not affected by the rotation of graphics. It is easy to change the geometry quickly. The reason for taking this step in the image processing process is that the first boundary and the second boundary obtained in the foregoing may actually be jagged pixel boundaries, rather than an ideal straight line segment, and therefore need to be further obtained by the Huo-style conversion. The first boundary and the second boundary correspond to the first line segment and the second line segment of the straight line. The line segment determining method of the present invention is not limited to this algorithm.

In an embodiment, according to the first line segment and the second line segment obtained in step S505, the distance between the two line segments is further calculated. For example, the distance calculation method may be to calculate the pixel pitch of the two line segments, and then pass through The conversion process gets the actual physical distance. The distance calculation method of the present invention is not limited to this.

The calculated distance can be determined by manual judgment or program automation to determine whether the currently detected display module meets the quality standard of the assembly process, for example, setting a threshold in advance, and if the detected gap distance is lower than the threshold, it represents The gap of this display module conforms to the standard and is a good product. If the detected gap distance is higher than the threshold, the gap representing the display module does not meet the standard and belongs to a defective product.

In summary, the method for detecting the gap width of the display module of the present invention uses the camera to capture the image to be tested, and uses the image recognition technology to detect the boundary between the frame portion and the gap and the gap and the display portion in the image to be tested. Boundary, and find the straight line segment corresponding to the boundary, and calculate the distance of the gap based on the straight line segment found. By calculating the distance calculated by this automated method, the time and reduction of human strength measurement can be reduced. The error rate further increases production efficiency and reduces labor costs.

Although the present invention has been disclosed above in the foregoing embodiments, it is not intended to limit the invention. It is within the scope of the invention to be modified and modified without departing from the spirit and scope of the invention. Please refer to the attached patent application for the scope of protection defined by the present invention.

S101-S105‧‧‧Steps

Claims (7)

A method for detecting a gap width of a display module includes: capturing a display module from a first direction to generate a to-be-tested image, wherein the image to be tested is divided into a frame area, an inner area, and a gap area, the frame The area corresponds to a frame portion of the module, the inner area corresponding to a display portion of the display module, the gap area corresponding to the gap between the frame portion and the display portion; determining a first in the image to be tested a line segment and a second line segment, the first line segment is a partial boundary of the frame region and the gap region, the second line segment is a partial boundary between the gap region and the inner region; and calculating the first line segment and the The distance between the second line segments. The method for detecting a gap width of a module according to claim 1, wherein the step of determining the first line segment and the second line segment in the image to be measured further comprises: binarizing the image to be tested and Performing image closure to obtain a binarized image; detecting a first boundary and a second boundary according to the binarized image, the first boundary is a boundary between the frame region and the gap region, and the second boundary is the a boundary between the gap region and the inner region; and determining the first line segment and the second line segment from the first boundary and the second boundary, respectively. The method for detecting a gap width of a module according to claim 2, wherein the image binarization refers to classifying each pixel of the image to be tested into at least one according to a pixel value. A foreground object and at least one background object, wherein the foreground object refers to a foreground in the image, and the background object refers to a background in the image, represented by black and white two pixel values, respectively. The method for detecting a gap width of a module according to claim 2, wherein in the step of binarizing the image to be tested and performing image closure, the image binarization method uses an Otsu's method, and Image closure is performed using the Image Closing method. The method for detecting a gap width of a module according to claim 2, wherein the detecting the first boundary and the second boundary in the step of detecting the first boundary and the second boundary according to the binarized image Use Canny edge detection. The method for detecting a gap width of a module according to claim 2, wherein in the step of determining the first line segment and the second line segment from the first boundary and the second boundary, determining the first line The method of the segment and the second segment uses a Hough transform. The method for detecting a gap width of a display module according to claim 1, wherein a distance between the first line segment and the second line segment is a pixel pitch of the first line segment and the second line segment, and then a conversion is performed. The process gets an actual physical distance.