CN112798108B - Ceramic tile self-adaptive color separation method and device - Google Patents
Ceramic tile self-adaptive color separation method and device Download PDFInfo
- Publication number
- CN112798108B CN112798108B CN202011591277.8A CN202011591277A CN112798108B CN 112798108 B CN112798108 B CN 112798108B CN 202011591277 A CN202011591277 A CN 202011591277A CN 112798108 B CN112798108 B CN 112798108B
- Authority
- CN
- China
- Prior art keywords
- tile
- color
- image
- feature
- area image
- 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.)
- Active
Links
- 238000000926 separation method Methods 0.000 title claims abstract description 99
- 239000000919 ceramic Substances 0.000 title claims abstract description 70
- 238000009826 distribution Methods 0.000 claims abstract description 65
- 238000000034 method Methods 0.000 claims abstract description 63
- 230000008569 process Effects 0.000 claims abstract description 43
- 238000007781 pre-processing Methods 0.000 claims abstract description 22
- 238000001914 filtration Methods 0.000 claims abstract description 14
- 238000011156 evaluation Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims description 27
- 238000012937 correction Methods 0.000 claims description 18
- 230000004044 response Effects 0.000 claims description 18
- 230000003044 adaptive effect Effects 0.000 claims description 13
- 230000009466 transformation Effects 0.000 claims description 9
- 238000005286 illumination Methods 0.000 claims description 8
- 238000003384 imaging method Methods 0.000 claims description 8
- 230000011218 segmentation Effects 0.000 claims description 8
- 238000011161 development Methods 0.000 claims description 6
- 230000018109 developmental process Effects 0.000 claims description 6
- 230000033001 locomotion Effects 0.000 claims description 4
- 230000001360 synchronised effect Effects 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 abstract description 16
- 238000001514 detection method Methods 0.000 abstract description 14
- 238000004040 coloring Methods 0.000 abstract description 4
- 230000005540 biological transmission Effects 0.000 description 5
- 230000008030 elimination Effects 0.000 description 4
- 238000003379 elimination reaction Methods 0.000 description 4
- 239000003086 colorant Substances 0.000 description 3
- 238000004806 packaging method and process Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 239000011449 brick Substances 0.000 description 2
- 230000004069 differentiation Effects 0.000 description 2
- 239000000428 dust Substances 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- 238000005507 spraying Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000005498 polishing Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000005245 sintering Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/46—Measurement of colour; Colour measuring devices, e.g. colorimeters
- G01J3/50—Measurement of colour; Colour measuring devices, e.g. colorimeters using electric radiation detectors
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
- B07C5/342—Sorting according to other particular properties according to optical properties, e.g. colour
- B07C5/3422—Sorting according to other particular properties according to optical properties, e.g. colour using video scanning devices, e.g. TV-cameras
Abstract
The invention discloses a tile self-adaptive color separation method and device. The method comprises the steps of preprocessing, plate separation and color separation of collected tile images, wherein the color separation comprises two processes of color separation and color separation. The preprocessing comprises the process of correcting the gray value of the image according to three channel values in the calibration area. The plate division comprises the processes of orthogonally rotating the template, correspondingly extracting texture features, and carrying out the correlation filtering of space-time constraint and similarity evaluation based on the feature space of the template. The color forming comprises a process of determining the characteristic center and the characteristic distribution range of the initial color number, a process of determining the characteristic center and the characteristic distribution range of the new color number and a process of matching the color characteristics of the ceramic tile in the counted color numbers. According to the invention, standard templates do not need to be configured in advance, and the plate division of each batch of ceramic tiles is automatically completed according to the characteristics of the ceramic tile production process. The invention can adaptively finish the coloring of each color number without configuring a standard color number, and leads the coloring and color separation result to be more accurate along with the increase of the detection quantity.
Description
Technical Field
The invention relates to the technical field of computer vision processing, in particular to a tile self-adaptive color separation method and device.
Background
The production process of the ceramic tile comprises the steps of spraying and printing colors, patterns and patterns on a blank through an ink jet machine, and then sintering and polishing the blank in a kiln in sequence to obtain the final ceramic tile. The ceramic tiles on the market mainly have the types of fixed plate grains, continuous grains, infinite continuous grains and the like, wherein the continuous grain tiles have coherent, atmospheric and simple decoration characteristics due to the fact that the continuous grain tiles can completely present the grains of natural stone, and are popular among market consumers in recent years.
The dimension of the single ceramic tile with continuous grains ranges from 600 multiplied by 1200mm to 2400 multiplied by 1200mm, and the dimension after splicing exceeds the dimension which can be produced by a kiln once. Therefore, the continuous grain brick is often cut into a plurality of sub-boards for production in the production process, the patterns of each sub-board are complex and not repeated, and the subsequent sorting and packaging are difficult. In addition, because the ceramic tile is influenced by uncertain factors in each production link, for example, the influence of multiple factors such as material proportion and kiln temperature, even if the ceramic tile with the same pattern also has color deviation, a ceramic factory needs to divide the plate according to the pattern of the ceramic tile before final packaging, and color separation is carried out according to the color deviation condition of the ceramic tile.
At present, the plate and color separation in a ceramic tile production line mainly depends on visual distinguishing and manual marking of workers, and then sorting equipment realizes the sorting and packaging of ceramic tiles by identifying manual marking. However, the manual detection mode has a limit, and generally does not exceed 6 plate surface patterns, otherwise, the detection accuracy cannot be guaranteed. In addition, the worker is inevitably fatigued and distracted after working for a long time, resulting in low detection efficiency and unstable accuracy. And the existing mode can not give consideration to plate separation and color separation, and can only be finished as two independent processes, thereby spending a large amount of manual labor.
In the existing plate dividing process, workers compare tiles on a production line with template tiles in real time, find out corresponding sub-plate positions of the current tiles in the template tiles and mark plate numbers. However, because of the limited speed of manual identification, the continuous grain bricks with complicated grains or excessive sub-boards cannot be distinguished.
The existing color separation process includes two steps of off-line color separation and on-line color separation. Off-line color is done by laying randomly sampled tiles flat in a well lit room to determine the total number of color numbers for the batch of tiles. And the on-line color separation is to compare the ceramic tiles on the production line with the templates in real time and mark color numbers according to the color separation result.
The existing detection method requires that detection personnel have abundant working experience, flexible strain and long-time working capability. However, even this method is very attractive in manual detection, and is very easy to cause errors in plate separation and color separation after long-time fatigue and under the condition of more patterns and colors, thereby causing loss in production and sale.
In the existing scheme of plate/color separation through a machine, for example, a tile plate separation method based on a deep learning model is adopted, a sample is required to be pre-trained, firstly, a camera is used for collecting images of tiles with different patterns, and a database with a certain scale is established; then, training the model according to the corresponding relation between the image and the pattern label; and finally, carrying out online plate division detection on the ceramic tile by using the trained model. The problem with this approach is that the model needs to be trained in advance, and the trained model cannot be used directly for different batches of tile patterns, and is therefore difficult to deploy in an actual production process.
Or the existing automatic color separation method of the ceramic tile firstly utilizes a camera to collect images, then extracts color features of the ceramic tile images, compares the color features with color features of template images collected in advance, and determines the ceramic tile images as the current color number when the color features are smaller than a preset threshold value, or determines the ceramic tile images as the new color number when the color features are not larger than the preset threshold value. The problem with this type of process is that it requires standard plates of each color number, which is unpredictable before the start of production and therefore presents difficulties in implementation. Moreover, the method of presetting the fixed threshold has poor adaptability to different patterns and different production batches, and industrial workers obviously lack the professional knowledge of the work of the adjustment system, which causes difficulty in actual deployment.
The above-mentioned conventional schemes are described in some conventional documents, for example, "CN204116238U — a tile texture on-line detection and classification device" shows a ceramic texture detection and classification device, but a specific classification method is not described. "CN 103324759B-a ceramic tile intelligent recognition device" provides a search and comparison device for similar ceramic tiles, which is used for rapidly retrieving similar ceramic tile patterns on an intelligent platform and cannot be used for online detection and classification on a production line. "CN 109614994A-a ceramic tile classification recognition method and device" provides a method and device for classifying ceramic tiles by using computer vision and deep learning, but the scheme needs a pre-training model to achieve a better classification effect, and is difficult to deploy in the actual production process. "CN 202010275495-a detection device for tile grading and color separation-application publication" shows a ceramic color separation device, but does not describe the color separation method. "CN 201911403603-a tile sorting system-application publication" shows a sorting system for tile color separation, but does not describe specific color separation methods and procedures. The 'CN 201911403922-a method and a device for generating a color difference detection model and separating color of a ceramic tile-application publication' provides a method for extracting color characteristics and realizing color separation by using a deep residual error network, but the method requires a large-scale training data set to be collected in advance, and is difficult to deploy in the actual production process.
Disclosure of Invention
The invention aims to: aiming at the existing problems, the ceramic tile self-adaptive color separation method and the ceramic tile self-adaptive color separation device are provided, which do not depend on a ceramic tile pattern template and a standard color number template, automatically finish the color separation of the ceramic tile and self-adaptively finish the color separation of the ceramic tile with various types.
The technical scheme adopted by the invention is as follows:
a tile adaptive color separation method, comprising:
A. preprocessing an input tile image to obtain a tile area image;
B. a step of separating the tile area image based on the texture thereof;
C. the step of color separation is carried out on the ceramic tiles of each format respectively, and comprises two processes of color separation and color separation:
color development process:
counting the color feature distribution of a preset number of tile area images from an input first tile area image to determine the feature center and the distribution range of the color feature of the current color number, and reserving the color feature of a preset proportion range close to the feature center as the feature distribution range of the current color number;
color separation process:
in the color feature space corresponding to the format, judging whether the color feature of the current tile area image falls into the feature distribution range of the recorded color number, if so, taking the color number corresponding to the falling feature distribution range as the color number corresponding to the current tile area image, otherwise, adding the color feature of the current tile area image as a new color number, and determining the feature center and the feature distribution range of the new color number by the following method:
and counting the color feature distribution of the images in the preset number of tile areas to determine the feature center and the distribution range of the color feature of the new color number, and reserving the color feature with a preset proportion depending on the feature center as the feature distribution range of the new color number.
Further, the step B includes: adding the first tile area image and the corresponding texture features into a template library, wherein the steps of keeping the tile area image at four angles of 0 degree, rotating 90 degrees, rotating 180 degrees and rotating 270 degrees are included, and the corresponding texture features are respectively extracted. Extracting texture features of the subsequent tile area images, performing relevant filtering operation of space-time constraint on the extracted texture features in a feature space of the template library, and searching a position with the maximum response value; and then carrying out similarity evaluation on the detected tile area image and the template in the matched template library, if the evaluated similarity is above a given threshold value, taking the version number corresponding to the matched template as the version number corresponding to the current tile area image, and otherwise, adding the current tile area image and the corresponding texture features thereof into the template library.
Further, the template library is set with an upper limit of the number of templates. And if the similarity between the texture features of the current tile area image and the texture features of all templates in the template library is smaller than a given threshold value and the templates in the template library reach the upper limit of the number, regarding the current tile area image, taking the version number corresponding to the maximum position of the response value when the current tile area image and the feature space of the template library are subjected to the relevant filtering operation of space-time constraint as the version number corresponding to the current tile area image.
Further, the preprocessing in the step a includes processes of gray value correction, foreground segmentation and geometric transformation; wherein the process of gray value correction comprises: and correcting the gray value of the whole tile image according to the three channel values in the calibration area in the tile image.
Further, the tile image is acquired by a tile image acquisition device, the tile image acquisition device comprises a tile transmission device, an image acquisition device and a rack, the tile transmission device is installed on the rack, and the image acquisition device is arranged on a transmission path of the tile transmission device; the ceramic tile conveying device comprises a correcting device and a conveying belt, wherein the correcting device is arranged at the front end of the conveying belt; the image acquisition device comprises a darkroom, a linear light source, a rotary encoder, a photoelectric switch and a linear array industrial camera; the darkroom cover is arranged on the conveyor belt; the linear light source and the linear array industrial camera are both arranged in the darkroom and above the conveyor belt, and the illumination area of the linear light source is superposed with the imaging area of the linear array industrial camera; a calibration object is arranged in the darkroom and on the side edge of the conveyor belt; the rotary encoder and the conveyor belt keep synchronous motion, the photoelectric switch is installed in the darkroom, and the rotary encoder and the photoelectric switch are respectively connected with the linear array industrial camera.
In order to solve all or part of the problems, the invention also provides a tile self-adaptive color separation device which comprises an image processing device, wherein the image processing device comprises an image preprocessing unit, a tile plate separating unit, a tile color separation unit and a result output unit which are sequentially connected. Wherein:
the image pre-processing unit is configured to: preprocessing an input tile image and outputting a tile area image;
the tile split unit is configured to: performing version division on the tile area image based on the texture of the tile area image;
the tile color separation unit is configured to: respectively carrying out color separation on the tile area images of each format, wherein the color separation comprises two processes of color separation and color separation; wherein:
color development process: counting the color feature distribution of a preset number of tile area images from an input first tile area image to determine the feature center and the distribution range of the color feature of the current color number, and reserving the color feature of a preset proportion range close to the feature center as the feature distribution range of the current color number;
color separation process: in the color feature space corresponding to the format, judging whether the color feature of the current tile area image falls into the feature distribution range of the recorded color number, if so, taking the color number corresponding to the falling feature distribution range as the color number corresponding to the current tile area image, otherwise, adding the color feature of the current tile area image as a new color number, and determining the feature center and the feature distribution range of the new color number by the following method: and counting the color feature distribution of the images in the preset number of tile areas to determine the feature center and the distribution range of the color feature of the new color number, and reserving the color feature with a preset proportion depending on the feature center as the feature distribution range of the new color number.
Further, the tile separating unit is configured to: adding the first tile area image and the corresponding texture features thereof into a template library, wherein the steps comprise retention degree, rotation and rotation degree of the tile area image, and extracting the corresponding texture features respectively; extracting texture features of the subsequent tile area images, performing relevant filtering operation of space-time constraint on the extracted texture features in a feature space of the template library, and searching a position with the maximum response value; and then carrying out similarity evaluation on the detected tile area image and the template in the matched template library, if the evaluated similarity is above a given threshold value, taking the version number corresponding to the matched template as the version number corresponding to the current tile area image, and otherwise, adding the current tile area image and the corresponding texture features thereof into the template library.
Further, the template library is provided with an upper limit of the number of templates; and if the similarity between the texture features of the current tile area image and the texture features of the templates in the template library is smaller than a given threshold value and the templates in the template library reach the upper limit of the number, taking the version number corresponding to the maximum position of the response value when the space-time constrained related filtering operation is performed in the feature space of the current tile area image and the template library as the version number corresponding to the current tile area image.
Further, the image preprocessing unit preprocesses the input tile image by gray value correction, foreground segmentation and geometric transformation; the process of gray value correction includes: and carrying out gray value correction on the whole tile image according to the three channel values in the calibration area in the tile image.
Furthermore, the device also comprises a ceramic tile image acquisition device, wherein the ceramic tile image acquisition device comprises a ceramic tile transmission device, an image acquisition device and a rack; the ceramic tile conveying device comprises a correcting device and a conveying belt, wherein the correcting device is arranged at the front end of the conveying belt; the image acquisition device comprises a darkroom, a linear light source, a rotary encoder, a photoelectric switch and a linear array industrial camera; the darkroom cover is arranged on the conveyor belt; the linear light source and the linear array industrial camera are both arranged in the darkroom and above the conveyor belt, and the illumination area of the linear light source is overlapped with the imaging area of the linear array industrial camera; a calibration object is arranged in the darkroom and on the side edge of the conveyor belt; the rotary encoder and the conveyor belt keep synchronous motion, the photoelectric switch is installed in the darkroom, and the rotary encoder and the photoelectric switch are respectively connected with the linear array industrial camera; the linear array industrial camera is connected with the image processing device.
In summary, due to the adoption of the technical scheme, the invention has the beneficial effects that:
1. according to the invention, standard templates do not need to be configured in advance, and the plate division of each batch of ceramic tiles is automatically completed according to the characteristics of the ceramic tile production process.
2. According to the invention, the template library is configured in the edition splitting link, and images and characteristics of the template at 4 angles are respectively stored, so that matching operation between the template library and the template is facilitated, and the accuracy and convenience of characteristic matching can be improved. Meanwhile, the fuzzy matching process is set without calculating the similarity one by one, and the matching efficiency is greatly improved.
3. The method can be suitable for the number of the patterns of the ceramic tiles to divide the tiles, and can ensure the accuracy of the division.
4. The invention can adaptively finish the coloring of each color number without configuring a standard color number, and leads the coloring and color separation result to be more accurate along with the increase of the detection quantity.
5. The device can finish the partition and same-direction sorting of the tiles with the same type and color number.
Drawings
The invention will now be described, by way of example, with reference to the accompanying drawings, in which:
fig. 1 is a flow chart of a tile adaptive color separation method.
Fig. 2 is a flow chart of a tile color separation process.
Figure 3 is a flow diagram of one embodiment of a tile split stage.
Fig. 4 is a flow chart of another embodiment of the tile splitting stage.
Fig. 5 is a flow chart of a tile image preprocessing stage.
Figure 6 is a top view of the tile image capture device.
Figure 7 is a side view of the tile image capture device.
Detailed Description
All of the features disclosed in this specification, or all of the steps in any method or process so disclosed, may be combined in any combination, except combinations of features and/or steps that are mutually exclusive.
Any feature disclosed in this specification (including any accompanying claims, abstract) may be replaced by alternative features serving equivalent or similar purposes, unless expressly stated otherwise. That is, unless expressly stated otherwise, each feature is only an example of a generic series of equivalent or similar features.
Example one
A tile adaptive color separation method, as shown in fig. 1, comprising:
A. and preprocessing the input tile image to obtain a tile area image.
For the preprocessing step of the tile image, as shown in fig. 5, the flow includes the processes of gray value correction, foreground segmentation and geometric transformation. Firstly, carrying out gray value correction on the whole tile image according to three channel values in a calibration area in the tile image so as to eliminate image gray value change caused by light source brightness and camera response. The position of the tile region is then determined by foreground segmentation and the interference region is removed using morphological processing. And finally, positioning four corner points of the tile area, correcting the azimuth through geometric transformation, eliminating deflection angles, and extracting an image of the tile area.
The calibration area is a reference area designed in the tile image, and in some embodiments, in the tile image capturing step, the calibration object set near the tile corresponds to an area in the tile image. And calibrating three channel values in the area as reference values, and performing color correction on the tile images to correct the image gray scale of each tile image to the truest state so as to eliminate the influence of noise brought by the external environment on the version result.
The tile image is collected by a tile image collecting device. In some embodiments, as shown in fig. 6 and 7, the tile image collecting device includes a frame 201, a tile conveying device 101 is mounted on the frame 201, an image collecting device 102 is disposed on a conveying path of the tile conveying device 101, the tile conveying device 101 includes a guiding device 203 and a conveyor belt 202, and the guiding device 203 is disposed at a front end of the conveyor belt 202; the image acquisition device 102 comprises a darkroom 204, a line light source 205, a rotary encoder 206, a photoelectric switch 207 and a line industrial camera 210. The darkroom 204 is covered on the conveyor belt 202 of the tile conveying device 101 and used for shielding ambient light to keep the brightness of the image acquisition consistent and shielding dust to ensure the cleanness of the internal equipment. The linear light source 205 and the line industrial camera 210 are both arranged in the darkroom 204 and above the conveyor belt 202, and the illumination area of the linear light source 205 and the imaging area of the line industrial camera 210 are overlapped (for example, the imaging area is aligned with the illumination area); preferably, the line industrial camera 210 has a field of view perpendicular to the direction of advancement of the conveyor belt 202. Inside the dark room 204, at the side of the conveyor belt 202, a calibration object 208 (corresponding to the calibration area in the image) is provided. The line light source 205 may be constantly on, or may be turned on when the tile image is captured. The rotary encoder 206, which moves synchronously with the conveyor belt 202, may be mounted on the frame 201 below the conveyor belt 202 where it contacts the conveyor belt 202, or on the motor shaft of the conveyor belt 202. The photoelectric switch 207 is installed in the dark room 204 and can be installed at the side, above or below the conveyor belt 202 according to the type. The rotary encoder 206 and the photoelectric switch 207 are respectively connected to a line industrial camera 210. Placing the ceramic tiles at the front end of the conveyor belt 202, driving the ceramic tiles to move by the conveyor belt 202, and guiding the pose of the ceramic tiles under the action of the guiding device 203; the rotary encoder 206 rotates with the driving of the conveyor belt 202 to output a row trigger signal, and the photoelectric switch 207 outputs a frame trigger signal when sensing that the tile reaches the field of view of the linear array industrial camera 210, so as to realize the acquisition of the tile image. The image collected by the line industrial camera 210 is transmitted to the image processing device 103 for storage and processing, for example, processing of plate separation and color separation.
In practical applications, the rotary encoder 206 and the photoelectric switch 207 have noise in output signals due to jitter of the apparatus and the like, and therefore, it is preferable that the rotary encoder 206 and the photoelectric switch 207 are respectively connected to the line industrial camera 210 via a jitter elimination circuit 209 to perform jitter elimination processing on the line trigger signal and the frame trigger signal, respectively. The debouncing circuit 209 may be fabricated as an interface circuit board configuration, i.e., configured with an interface, to facilitate a plug-in connection, in some embodiments, the debouncing circuit 209 may be mounted on the rack 201 (e.g., below the conveyor 202), or in the dark room 204.
The above tile image capturing device can be further extended to a tile sorting system, where a sorting device 105 is provided at the rear end of the conveyor belt 202, the sorting device 105 is connected to the image processing device 103, and sorts the corresponding tiles to corresponding positions according to the results of the plate/color separation by the image processing device 103. To facilitate the differentiation of the tile categories, it is possible to choose to mark the tiles, on the basis of which, optionally, between the tile image acquisition device and the sorting device 105, a marking device 104 is provided, the marking device 104 being arranged laterally to the conveyor belt 202. The marking device 104 is connected to the image processing device 103, and marks the side of the tile running on the conveyor belt with the content of the corresponding mark according to the plate/color separation result of the image processing device, for example, by spraying the mark (such as color number, plate number, order, etc.) on the side of the tile.
B. And a step of separating the tile area image based on the texture of the tile area image.
And after the tile area image is obtained from the tile image, classifying the tile area image according to the texture characteristics of the tile area image. As shown in fig. 3, a template library is first constructed, and at the beginning, no template exists in the template library, and for the first tile area image, the template library is added as the first template by default, and the corresponding texture feature is generated, and the version number corresponding to the first tile area image is set (for example, the serial number in the feature space of the template library is used as the version number). Because the directions of the tiles are different and the texture features are also different, when the texture features are added to the template library, the texture features of four angles of 0 degree, 90 degree rotation, 180 degree rotation and 270 degree rotation are reserved, namely, the tile area image is reserved for 0 degree, 90 degree rotation, 180 degree rotation and 270 degree rotation respectively, and the corresponding texture features are extracted respectively.
And for the subsequently detected tile area images, extracting texture features of the tile area images, performing relevant filtering operation of space-time constraint on the extracted texture features in a feature space of a template library, and searching a position with the maximum response value. And correspondingly obtaining the suspected version number and the rotation position of the current tile area image according to the position with the maximum response value. And then, carrying out similarity evaluation on the detected tile area image and a template in a matched template library, generally the similarity evaluation between texture features, if the evaluated similarity is smaller than a given threshold (or the similarity distance is larger than a corresponding given threshold), indicating that the current tile area image is not in the template library, adding the current tile area image and the corresponding texture features thereof into the template library, if the evaluated similarity is above the given threshold, indicating that the same version exists in the template library in the current tile area image, and taking the version number corresponding to the matched template as the version number corresponding to the current tile area image. Preferably, when outputting the version number of the detected tile (i.e., the current tile), the rotation angle of the tile with respect to the form is also output to facilitate sorting arrangement.
In some embodiments, the above process comprises:
and (3) constructing a template library: and respectively reserving four angles of 0 degree, 90 degrees, 180 degrees and 270 degrees for the first tile area image to obtain 4 images, respectively extracting the texture features of each image, adding the texture features corresponding to each image into a template library, and obtaining templates with the sequence numbers of 1, 2, 3 and 4 respectively.
And extracting the texture features of the newly input tile area image, performing space-time constraint related filtering operation on the extracted texture features and the feature space of the template library, and searching the position with the maximum response value so as to preliminarily determine the version number and the rotation angle of the tile area image. And then calculating the similarity between the texture features of the newly input tile area image and the texture features at the position with the maximum response value. When the similarity is smaller than a given threshold, adding the newly input tile area image under 4 angles (0 degree is reserved, 90 degrees is rotated, 180 degrees is rotated, and 270 degrees is rotated) and the corresponding texture features (4 feature vectors) into the template library to serve as a new template, for example, when the second tile area image serves as the new template, templates with the sequence numbers of 5, 6, 7, and 8 are obtained. And when the similarity is above a given threshold, taking the version number corresponding to the matched template as the version number corresponding to the newly input tile area image.
The template-corresponding plate numbers may be the number of the template, or the same plate number may be set for each template of the same tile, for example, the above-mentioned template numbers 1, 2, 3, and 4 correspond to the first plate number, and the template numbers 5, 6, 7, and 8 correspond to the second plate number.
For the split result of the tile, the number of versions may be defined. For example, the tile type may be limited, such as solid page, lined tile, or infinite lined tile. In the corresponding plate dividing result, the fixed plate surface can limit and output a plate type; a continuous grain tile with n (n is a positive integer) patterns (layouts) can be limited to outputting up to n layouts. In the actual plate dividing process, because tiles with the same plate type are produced, deviation is inevitable, and machine plate dividing can be regarded as a new plate type for the tiles in the condition. In this regard, especially for the continuous grain tiles, as shown in fig. 4, on the premise of limiting the upper limit of the number of output versions (which can be realized by limiting the upper limit of the number of templates in the template library), if the similarity between the texture features of the newly input (current) tile area image and the texture features of each template in the template library is smaller than a given threshold, and the template in the template library has reached the upper limit of the number, that is, the newly input tile area image cannot be regarded as a new version any more, then, as for the newly input tile area image, the version number corresponding to the position where the response value is maximum when the newly input tile area image is subjected to the spatio-temporal constraint correlation filtering operation in the feature space of the template library is taken as the version number corresponding to the newly input tile area image.
C. And respectively carrying out color separation on the tiles of each format (corresponding to one format number).
As shown in fig. 2, the step C includes two processes of color separation and color separation.
Color development process:
starting from the first tile area image (for each layout), for the input tile area image, a certain number of (settable) color feature distributions are counted, and the color feature distribution center and range of the current color number are determined. This process is based on the following assumptions: the color of the front part of the manufactured ceramic tile tends to be stable, namely the color of the part of the ceramic tile belongs to the same color number, and the feature center and the feature distribution range of the color number can be determined by counting the color features of the part of the ceramic tile.
The color feature extraction is as follows: and in a preset color space, counting the color average value of the tile area image. The preset color space includes: RGB (red green blue), HSV (hue, saturation, lightness), YUV (lightness, blue component, red component), lab (lightness, green red component, blue Huang Fenliang). The color feature extracted from the tile region image may be performed in a certain color space (e.g., RGB), or may be performed in multiple color spaces, and the color feature value of each channel may be assigned with weights of different sizes to balance the role of each channel in color separation.
For the current color number, in the statistical process, the positions where the color features of the tile region image are gathered in the space by a predetermined proportion (e.g. 70% -95%, e.g. 80%) of the feature centers are searched, and singular value points of a certain proportion (i.e. other data except the predetermined proportion) are filtered accordingly, so that more accurate feature centers and feature distribution ranges of the current color number are obtained. The characteristic center and the characteristic distribution range of the color number can be adjusted in a self-adaptive mode along with the increase of the input quantity of the tile area images of the corresponding type, and the characteristic center and the characteristic distribution range are more accurate. When a new color number is added, the characteristic center and the characteristic distribution range of the new color number are obtained by statistics according to the same method. This avoids the situation of too many or too few color separations due to manual intervention. And if the color features of the tile area image fall into the feature distribution range of a certain color number, determining the tile area image as the color number.
Color separation process:
the online color separation is to find, for each format, a color number corresponding to a feature center, to which the color feature of the current tile area image is closest, as the color number of the current tile area image in a color feature space corresponding to the format (the color feature of the current tile area image is inevitably within a feature distribution range of the color feature of the color number corresponding to the feature center, that is, the color number corresponding to the feature distribution range in which the color feature of the current tile area image falls). If the color feature of the current tile area image is not in the feature distribution range of the counted color number, or the distance between the color feature of the current tile area image and the centers of all the counted color number features exceeds the color separation threshold, adding the color feature of the current tile area image into a new color number, and further determining the feature center and the feature distribution range of the new color number through subsequent statistics, namely obtaining the color number by the online color separation process in a self-adaptive mode: counting the color feature distribution of a preset number of tile area images (from the current tile area image) to determine the feature center and the distribution range of the color feature of the new color number, and reserving the color feature with a preset proportion close to the feature center as the feature distribution range of the new color number. The color separation threshold is determined by utilizing a feature distribution range calculated in an adaptive mode in the online color opening process.
Example two
A ceramic tile self-adaptive color separation device comprises an image processing device, wherein the image processing device comprises an image preprocessing unit, a ceramic tile plate separating unit, a ceramic tile color separation unit and a result output unit which are sequentially connected. Wherein:
the image preprocessing unit is configured to: and preprocessing the input tile image and outputting a tile area image.
As shown in fig. 5, the preprocessing includes processes of gray value correction, foreground segmentation, and geometric transformation. The grey value correction is to perform grey value correction on the whole tile image according to three channels in a calibration area in the tile image so as to eliminate image grey value changes caused by light source brightness and camera response. And performing foreground segmentation on the image to determine the position of the tile area, and removing the interference area by using morphological processing. The geometric transformation process is the process of correcting the image azimuth, and the correction of the tile area azimuth is completed by positioning four corner points of the tile area and then carrying out geometric transformation, so that the deflection angle is eliminated, and the tile area image is extracted.
The calibration area is a reference area designed in the tile image, and in some embodiments, in the tile image capturing step, the calibration object set near the tile corresponds to the area in the tile image. And calibrating three channel values in the area as reference values, and performing color correction on the tile images to correct the image gray scale of each tile image to the truest state so as to eliminate the influence of noise brought by the external environment on the version result.
A tile tiling unit configured to: and performing plate division on the input tile area image according to the texture characteristics of the tile area image.
The tile layout unit is provided with a template library, the template library takes the input first tile area image and the corresponding texture characteristics as templates, and the templates in the template library are set with layout numbers. Specifically, as shown in fig. 3, when the tile area image is added to the template library as a template, the tile area image is respectively retained by 0 degree, rotated by 90 degrees, rotated by 180 degrees, and rotated by 270 degrees, and the corresponding texture features are respectively extracted. For example, the first tile area image is respectively reserved with four angles of 0 degree, 90 degrees, 180 degrees and 270 degrees to obtain 4 images, the texture features of each image are respectively extracted, the texture features corresponding to each image are added into a template library, and templates with the sequence numbers of 1, 2, 3 and 4 are obtained. The template number may be set as a plate number, or one plate number may be set for templates corresponding to the same tile, for example, the template corresponding to the plate number one of the above-mentioned numbers 1, 2, 3, and 4.
And extracting the texture features of the subsequently input tile region images, performing space-time constrained correlation filtering operation on the extracted texture features in a feature space of a template library, and searching a position (such as a sequence number of a template) with the maximum response value. And correspondingly obtaining the suspected version number and the rotation position (angle) of the current tile area image according to the position with the maximum response value. Performing similarity evaluation on the input tile area image and a template in a matched template library, if the evaluated similarity is smaller than a given threshold value, indicating that the current tile area image is not in the template library, and adding the current tile area image and corresponding texture features thereof into the template library (similarly, adding an image of a newly input tile area image under 4 angles (0 degree is reserved, 90 degrees is rotated, 180 degrees is rotated, and 270 degrees is rotated) and corresponding texture features (4 feature vectors) into the template library); and if the evaluated similarity is above a given threshold, the same version exists in the template library of the current tile area image of the specification, and the version number corresponding to the matched template is used as the version number corresponding to the current tile area image.
Generally, tiles have a more versatile classification, such as solid-layout, lined tiles, and endless lined tiles. The results of the plate can be defined for different types (which can be achieved by defining the number of templates in the template library). In the corresponding plate dividing results, the fixed plate surface can limit to output one type of plate; a continuous grain tile with n (n is a positive integer) patterns (layouts) can be limited to outputting up to n layouts.
In the actual plate dividing process, because tiles with the same plate type are produced, deviation is inevitable, and machine plate dividing can be regarded as a new plate type for the tiles in the condition. On the contrary, as shown in fig. 4, on the premise of limiting the upper limit of the number of output versions, if the similarity between the texture features of the newly input tile region image and the texture features of each template in the template library is smaller than a given threshold, and the version number corresponding to the template in the template library has reached the upper limit of the number of output versions, that is, the newly input tile region image cannot be regarded as a new version any more, then, as for the input tile region image, the version number corresponding to the position where the response value is maximum when performing the spatio-temporal constraint correlation filtering operation in the feature space of the template library is taken as the version number corresponding to the newly input tile region image.
A tile color separation unit configured to: and respectively carrying out color separation on the tile area images of all the formats. The process includes two flows of color separation and color separation, as shown in fig. 2.
And (3) a color development process:
and for the input tile area image, counting a certain amount of color characteristic distribution, and determining the center and the range of the color characteristic distribution of the current color number. This process is based on the following assumptions: the color of the part of the manufactured ceramic tile close to the front part tends to be stable, namely the color of the part of the ceramic tile belongs to the same color number, and the feature center and the feature distribution range of the color number can be determined by counting the color features of the part of the ceramic tile. The characteristic center and the characteristic distribution range of the color number can be adjusted in a self-adaptive mode along with the increase of the input quantity of the tile area images of the corresponding type, the characteristic center and the characteristic distribution range are more accurate, and the situation that the number of color separations is too large or too small due to manual intervention can be avoided.
The color feature extraction is as follows: and in a preset color space, counting the average value of the colors of the images of the tile area. The preset color space includes: RGB (red green blue), HSV (hue, saturation, lightness), YUV (lightness, blue component, red component), lab (lightness, green red component, blue Huang Fenliang). The color feature extracted from the tile region image may be performed in a certain color space (e.g., RGB), or may be performed in multiple color spaces, and the color feature value of each channel may be assigned with weights of different sizes to balance the role of each channel in color separation.
In the statistical process, the positions where the color features of the tile region image are gathered in the space are searched for in a predetermined proportion (e.g. 70% -95%, e.g. 80%), and singular value points in a certain proportion (i.e. other data except the predetermined proportion) are filtered accordingly, so that a more accurate feature center and feature distribution range of the current color number are obtained. When a new color number is added, the characteristic center and the characteristic distribution range of the new color number are obtained by statistics according to the same method. And if the color features of the tile area image fall into the feature distribution range of a certain color number, determining the tile area image as the color number.
Color separation process:
the online color separation is to find, for each format, a color number corresponding to a feature center, to which the color feature of the current tile area image is closest, as the color number of the current tile area image in a color feature space corresponding to the format (the color feature of the current tile area image is inevitably within a feature distribution range of the color feature of the color number corresponding to the feature center, that is, the color number corresponding to the feature distribution range in which the color feature of the current tile area image falls). And if the color features of the current tile area image are not in the feature distribution range of the counted color numbers, adding the color features of the current tile area image into the new color numbers, and further determining the feature centers and the feature distribution range of the new color numbers through subsequent statistics, namely obtaining the color numbers in a self-adaptive manner through the online color-developing process.
A result output unit configured to: and outputting the version number and/or the color number of the corresponding ceramic tile. Or also the rotation angle of the tiles with respect to the template to facilitate alignment during sorting.
EXAMPLE III
As shown in fig. 6 and 7, the embodiment discloses a tile image collecting device, which includes a frame 201, a tile conveying device 101 is installed on the frame 201, an image collecting device 102 is installed on a conveying path of the tile conveying device 101, the tile conveying device 101 includes a guiding device 203 and a conveyor belt 202, and the guiding device 203 is installed at the front end of the conveyor belt 202; the image acquisition device 102 comprises a darkroom 204, a line light source 205, a rotary encoder 206, a photoelectric switch 207 and a line industrial camera 210. The darkroom 204 is covered on the conveyor belt 202 of the tile conveying device 101 and used for shielding ambient light to keep the brightness of the image acquisition consistent and shielding dust to ensure the cleanness of the internal equipment. The linear light source 205 and the linear array industrial camera 210 are both arranged in the darkroom 204 and above the conveyor belt 202, and the illumination area of the linear light source 205 and the imaging area of the linear array industrial camera 210 are overlapped (for example, the imaging area is aligned with the illumination area); preferably, the line industrial camera 210 has a field of view perpendicular to the direction of advancement of the conveyor belt 202. Inside the dark room 204, at the side of the conveyor belt 202, a calibration object 208 (corresponding to the calibration area in the image) is provided. The line light source 205 may be constantly on, or may be turned on when a tile image is captured. The rotary encoder 206, which moves synchronously with the conveyor belt 202, may be mounted on the frame 201 below the conveyor belt 202 where it contacts the conveyor belt 202, or on the motor shaft of the conveyor belt 202. The photoelectric switch 207 is installed in the dark room 204 and can be installed at the side, above or below the conveyor belt 202 according to the type. The rotary encoder 206 and the photoelectric switch 207 are respectively connected to the line industrial camera 210. Placing the ceramic tiles at the front end of the conveyor belt 202, driving the ceramic tiles to move by the conveyor belt 202, and guiding the pose of the ceramic tiles under the action of the guiding device 203; the rotary encoder 206 rotates with the driving of the conveyor belt 202 to output a row trigger signal, and the photoelectric switch 207 outputs a frame trigger signal when sensing that the tile reaches the field of view of the linear array industrial camera 210, so as to realize the acquisition of the tile image. The image acquired by the line industrial camera 210 is transmitted to the image processing device 103 for storage and processing, for example, the above-mentioned processing of plate separation and color separation is performed.
In practical applications, the rotary encoder 206 and the photoelectric switch 207 have noise in output signals due to jitter of the apparatus, interference of external signals, and the like, and therefore, it is preferable that the rotary encoder 206 and the photoelectric switch 207 are respectively connected to the line industrial camera 210 through the jitter elimination circuit 209 to respectively perform jitter elimination processing on the line trigger signal and the frame trigger signal. The debounce circuit 209 may, in some embodiments, be fabricated as an interface circuit board configuration, i.e., configured with an interface to facilitate a plug-in connection, and the debounce circuit 209 may, in some embodiments, be mounted on the rack 201 (e.g., below the conveyor 202) or in the dark room 204.
On the basis of the ceramic tile image acquisition device, the embodiment also provides a ceramic tile sorting system, the rear end of the conveyor belt 202 of the ceramic tile image acquisition device is provided with the sorting device 105, the sorting device 105 is connected to the image processing device 103, corresponding ceramic tiles are sorted to corresponding positions according to the plate dividing/color separation results of the image processing device 103, the angles of the ceramic tiles are correspondingly adjusted according to the rotation angles calculated during plate dividing during sorting, and the ceramic tile angles of the same plate type/color number are unified. To facilitate the differentiation of the tile categories, it is possible to choose to mark the tiles, on the basis of which, optionally, between the tile image acquisition device and the sorting device 105, a marking device 104 is arranged, which marking device 104 is arranged at the side of the conveyor belt 202. The marking device 104 is connected to the image processing device 103, and marks the side surfaces of the tiles running on the conveyor belt with the content of the corresponding marks according to the plate/color separation result of the image processing device, for example, by means of jet printing, the marks (such as color numbers, plate numbers, orders, etc.) are jet printed on the side surfaces of the tiles.
The invention is not limited to the foregoing embodiments. The invention extends to any novel feature or any novel combination of features disclosed in this specification and any novel method or process steps or any novel combination of features disclosed.
Claims (10)
1. A tile adaptive color separation method is characterized by comprising the following steps:
A. preprocessing an input tile image to obtain a tile area image;
B. a step of separating the tile area image based on the texture thereof;
C. the step of color separation is carried out on the ceramic tiles of each format respectively, and comprises two processes of color separation and color separation:
color development process:
counting the color feature distribution of a preset number of tile area images from an input first tile area image to determine the feature center and the distribution range of the color feature of the current color number, and reserving the color feature of a preset proportion range close to the feature center as the feature distribution range of the current color number;
color separation process:
in the color feature space corresponding to the format, judging whether the color feature of the current tile area image falls into the feature distribution range of the recorded color number, if so, taking the color number corresponding to the falling feature distribution range as the color number corresponding to the current tile area image, otherwise, adding the color feature of the current tile area image as a new color number, and determining the feature center and the feature distribution range of the new color number by the following method:
and counting the color feature distribution of the images in the preset number of tile areas to determine the feature center and the distribution range of the color feature of the new color number, and reserving the color feature with a preset proportion depending on the feature center as the feature distribution range of the new color number.
2. The tile adaptive color separation method of claim 1, wherein the step B comprises:
adding the first tile area image and the corresponding texture features thereof into a template library, wherein the steps of keeping the tile area image at four angles of 0 degree, rotating 90 degrees, rotating 180 degrees and rotating 270 degrees, and respectively extracting the corresponding texture features;
extracting texture features of subsequent tile region images, performing space-time constrained correlation filtering operation on the extracted texture features in a feature space of the template library, and searching a position with a maximum response value; and then carrying out similarity evaluation on the detected tile area image and the template in the matched template library, if the evaluated similarity is above a given threshold value, taking the version number corresponding to the matched template as the version number corresponding to the current tile area image, and otherwise, adding the current tile area image and the corresponding texture features thereof into the template library.
3. The tile adaptive color separation method according to claim 2, wherein the template library is set with an upper limit on the number of templates;
and if the similarity between the texture features of the current tile area image and the texture features of all templates in the template library is smaller than a given threshold value and the templates in the template library reach the upper limit of the number, regarding the current tile area image, taking the version number corresponding to the maximum position of the response value when the current tile area image and the feature space of the template library are subjected to the relevant filtering operation of space-time constraint as the version number corresponding to the current tile area image.
4. A tile adaptive color separation method according to any one of claims 1~3 wherein the preprocessing in step a includes gray value correction, foreground segmentation and geometric transformation processes; wherein the process of gray value correction comprises: and carrying out gray value correction on the whole tile image according to the three channel values in the calibration area in the tile image.
5. The tile adaptive color separation method according to claim 4, wherein the tile image is captured by a tile image capturing device, the tile image capturing device comprises a tile conveying device (101), an image capturing device (102) and a frame (201), the tile conveying device (101) is mounted on the frame (201), and the image capturing device (102) is arranged on a conveying path of the tile conveying device (101); the tile conveying device (101) comprises a guide device (203) and a conveying belt (202), wherein the guide device (203) is arranged at the front end of the conveying belt (202); the image acquisition device (102) comprises a darkroom (204), a line light source (205), a rotary encoder (206), a photoelectric switch (207) and a line industrial camera (210); the darkroom (204) is covered on the conveyor belt (202); the linear light source (205) and the linear array industrial camera (210) are both arranged in the darkroom (204) and above the conveyor belt (202), and the illumination area of the linear light source (205) is superposed with the imaging area of the linear array industrial camera (210); a calibration object (208) is arranged in the darkroom (204) and at the side edge of the conveyor belt (202); the rotary encoder (206) and the conveyor belt (202) keep synchronous movement, the photoelectric switch (207) is installed in the darkroom (204), and the rotary encoder (206) and the photoelectric switch (207) are respectively connected with the line industrial camera (210).
6. A ceramic tile self-adaptive color separation device is characterized by comprising an image processing device, wherein the image processing device comprises an image preprocessing unit, a ceramic tile plate separating unit, a ceramic tile color separation unit and a result output unit which are sequentially connected; wherein:
the image pre-processing unit is configured to: preprocessing an input tile image and outputting a tile area image;
the tile split unit is configured to: performing version division on the tile area image based on the texture of the tile area image;
the tile color separation unit is configured to: respectively carrying out color separation on the tile area images of all the formats, wherein the color separation comprises two processes of color separation and color separation; wherein:
and (3) a color development process:
counting the color feature distribution of a preset number of tile area images from an input first tile area image to determine the feature center and the distribution range of the color feature of the current color number, and reserving the color feature of a preset proportion range close to the feature center as the feature distribution range of the current color number;
color separation process:
in the color feature space corresponding to the format, judging whether the color feature of the current tile area image falls into the feature distribution range of the recorded color number, if so, taking the color number corresponding to the falling feature distribution range as the color number corresponding to the current tile area image, otherwise, adding the color feature of the current tile area image as a new color number, and determining the feature center and the feature distribution range of the new color number by the following method:
and counting the color feature distribution of the images in the preset number of tile areas to determine the feature center and the distribution range of the color feature of the new color number, and reserving the color feature with a preset proportion depending on the feature center as the feature distribution range of the new color number.
7. The tile adaptive color separation apparatus of claim 6, wherein the tile imposition unit is configured to: adding the first tile area image and the corresponding texture features thereof into a template library, wherein the steps of keeping the tile area image at four angles of 0 degree, rotating 90 degrees, rotating 180 degrees and rotating 270 degrees, and respectively extracting the corresponding texture features; extracting texture features of the subsequent tile area images, performing relevant filtering operation of space-time constraint on the extracted texture features in a feature space of the template library, and searching a position with the maximum response value; and then carrying out similarity evaluation on the detected tile area image and the template in the matched template library, if the evaluated similarity is above a given threshold value, taking the version number corresponding to the matched template as the version number corresponding to the current tile area image, and otherwise, adding the current tile area image and the corresponding texture features thereof into the template library.
8. The tile adaptive color separation apparatus of claim 7, wherein the template library is provided with an upper limit on the number of templates; and if the similarity between the texture features of the current tile area image and the texture features of the templates in the template library is smaller than a given threshold value and the templates in the template library reach the upper limit of the number, taking the version number corresponding to the maximum position of the response value when the space-time constrained related filtering operation is performed in the feature space of the current tile area image and the template library as the version number corresponding to the current tile area image.
9. A tile adaptive color separation device according to 6~8 wherein the pre-processing of the input tile image by the image pre-processing unit comprises the processes of gray value correction, foreground segmentation and geometric transformation; the process of gray value correction includes: and correcting the gray value of the whole tile image according to the three channel values in the calibration area in the tile image.
10. The tile adaptive color separation device of claim 9, further comprising a tile image capturing device comprising a tile transport device (101), an image capturing device (102), and a frame (201), the tile transport device (101) being mounted on the frame (201), the image capturing device (102) being disposed on a transport path of the tile transport device (101); the tile conveying device (101) comprises a guide device (203) and a conveying belt (202), wherein the guide device (203) is arranged at the front end of the conveying belt (202); the image acquisition device (102) comprises a darkroom (204), a line light source (205), a rotary encoder (206), a photoelectric switch (207) and a line industrial camera (210); the darkroom (204) is covered on the conveyor belt (202); the linear light source (205) and the linear array industrial camera (210) are both arranged in the darkroom (204) and above the conveyor belt (202), and the illumination area of the linear light source (205) is superposed with the imaging area of the linear array industrial camera (210); a calibration object (208) is arranged in the darkroom (204) and on the side edge of the conveyor belt (202); the rotary encoder (206) and a conveyor belt (202) keep synchronous motion, the photoelectric switch (207) is installed in the darkroom (204), and the rotary encoder (206) and the photoelectric switch (207) are respectively connected with the line industrial camera (210); the line industrial camera (210) is connected with the image processing device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011591277.8A CN112798108B (en) | 2020-12-29 | 2020-12-29 | Ceramic tile self-adaptive color separation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011591277.8A CN112798108B (en) | 2020-12-29 | 2020-12-29 | Ceramic tile self-adaptive color separation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112798108A CN112798108A (en) | 2021-05-14 |
| CN112798108B true CN112798108B (en) | 2023-03-21 |
Family
ID=75805484
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011591277.8A Active CN112798108B (en) | 2020-12-29 | 2020-12-29 | Ceramic tile self-adaptive color separation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112798108B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20230222766A1 (en) * | 2022-01-12 | 2023-07-13 | Standard Stone, Inc. | System and method for capturing consistent standardized photographs and using photographs for categorizing products |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102095499A (en) * | 2009-12-09 | 2011-06-15 | 程好学 | Method for automatic color separation of ceramic tiles |
| CN111998945A (en) * | 2020-08-21 | 2020-11-27 | 北京理工大学重庆创新中心 | Full-polarization hyperspectral image compression reconstruction method based on Stokes parameter blocking |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE3371693D1 (en) * | 1983-12-14 | 1987-06-25 | Hell Rudolf Dr Ing Gmbh | Method of and circuit arrangement for the recognition of chrominances and colours |
| WO2011049582A1 (en) * | 2009-10-23 | 2011-04-28 | Hewlett-Packard Development Company, L.P. | Raman spectroscopy light amplifying structure |
| CN103324759B (en) * | 2013-07-05 | 2016-05-18 | 易翔 | A kind of ceramic tile intelligent identification equipment |
| CN111160476A (en) * | 2019-12-31 | 2020-05-15 | 佛山喀视科技有限公司 | Color difference detection model generation method, tile color separation method and device |
| CN110947637A (en) * | 2019-12-31 | 2020-04-03 | 佛山喀视科技有限公司 | Ceramic tile sorting system |
-
2020
- 2020-12-29 CN CN202011591277.8A patent/CN112798108B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102095499A (en) * | 2009-12-09 | 2011-06-15 | 程好学 | Method for automatic color separation of ceramic tiles |
| CN111998945A (en) * | 2020-08-21 | 2020-11-27 | 北京理工大学重庆创新中心 | Full-polarization hyperspectral image compression reconstruction method based on Stokes parameter blocking |
Non-Patent Citations (2)
| Title |
|---|
| Automatic classification of granite tiles through colour and texture features;Francesco Bianconi 等;《Expert Systems with Applications》;第39卷(第12期);第11212-11218页 * |
| 陶瓷墙地砖生产管理与品质管理;王银川;《陶瓷》(第5期);第28-31页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112798108A (en) | 2021-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106570511B (en) | Keyboard character defect online detection system and method based on computer vision | |
| CN106127780B (en) | A kind of curved surface defect automatic testing method and its device | |
| CN107486415B (en) | Thin bamboo strip defect online detection system and detection method based on machine vision | |
| CN111709935B (en) | Real-time coal gangue positioning and identifying method for ground moving belt | |
| CN107944504B (en) | Board recognition and machine learning method and device for board recognition and electronic equipment | |
| CN110766702B (en) | Agaricus bisporus grading judgment method | |
| CN109520706B (en) | Screw hole coordinate extraction method of automobile fuse box | |
| CN111242896A (en) | Color printing label defect detection and quality rating method | |
| CN107301634A (en) | A kind of robot automatic sorting method and system | |
| CN102706274A (en) | System for accurately positioning mechanical part by machine vision in industrially-structured scene | |
| CN112798108B (en) | Ceramic tile self-adaptive color separation method and device | |
| CN107240112A (en) | Individual X Angular Point Extracting Methods under a kind of complex scene | |
| CN111161295A (en) | Background stripping method for dish image | |
| CN108830908A (en) | A kind of magic square color identification method based on artificial neural network | |
| CN109583306B (en) | Bobbin residual yarn detection method based on machine vision | |
| CN108765426A (en) | automatic image segmentation method and device | |
| CN112633393B (en) | Automatic classification method and device for ceramic tile textures | |
| CN113252103A (en) | Method for calculating volume and mass of material pile based on MATLAB image recognition technology | |
| CN111739003A (en) | Machine vision algorithm for appearance detection | |
| CN109829496B (en) | Physical measurement classification method and equipment | |
| CN110614232A (en) | Agaricus bisporus grading system | |
| CN111141741A (en) | Detection apparatus capable of identifying label defects of printer | |
| CN113705487B (en) | Precision workpiece identification and technological parameter association system and identification method | |
| CN111161215B (en) | Detection apparatus capable of identifying color of printer | |
| CN111652055B (en) | Intelligent switch instrument identification method based on two-stage positioning |
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 |