Description:Field of the Invention

The present disclosure relates to an automated defect detection system for ceramic tiles, utilizing Region-Based Convolutional Neural Networks (R-CNN) to identify and classify various types of surface defects accurately.
Background
The background description includes information that may be useful in understanding the present invention. It is not an admission that any of the information provided herein is prior art or relevant to the presently claimed invention, or that any publication specifically or implicitly referenced is prior art.
In the domain of quality control for ceramic tiles, ensuring the integrity and aesthetic quality of said products is paramount. Traditional methods for inspecting ceramic tiles involve manual examination by skilled workers or the use of basic automated systems that rely on simple image processing techniques. Said conventional approaches, however, exhibit significant limitations in terms of accuracy, efficiency, and scalability. Manual inspection, for instance, is subject to human error and inconsistency, leading to variability in quality control outcomes. On the other hand, automated systems employing rudimentary image processing techniques struggle to accurately detect complex defects due to their limited analytical capabilities. Said systems often fail to distinguish subtle defects or variations in tile patterns and textures, resulting in either a high rate of false positives or the oversight of genuine defects.
Furthermore, the existing automated solutions do not effectively adapt to the wide range of ceramic tile designs and surface finishes available in the market. Said limitation is exacerbated by the dynamic nature of ceramic tile manufacturing, where new designs and textures are constantly introduced. As a result, the efficacy of said systems diminishes, necessitating frequent manual adjustments or system reconfigurations to maintain acceptable levels of detection accuracy. Additionally, the integration of said systems into existing production lines poses challenges, often requiring significant modifications to accommodate the inspection equipment. Said integration not only increases the complexity and cost of implementation but also disrupts production workflows, leading to decreased operational efficiency.
The reliance on traditional image processing techniques further complicates the defect detection process in ceramic tiles. Such techniques are not optimized for handling the variability in lighting conditions and reflections that are characteristic of tile surfaces. Said variability can mask defects or create false indications of imperfections, complicating the detection process. Moreover, said techniques lack the sophistication needed to analyse the contextual information within tile images, which is critical for identifying defects that are only apparent in relation to surrounding areas.
Prior art solutions cannot provide enhanced accuracy and efficiency in defect detection, adaptability to various tile designs and textures, seamless integration into production lines, and improved handling of lighting variations and contextual analysis of tile images. Thus, there exists an urgent need of a system for detecting defects in ceramic tiles solutions, by overcoming the problems associated with conventional systems and techniques for detecting defects in ceramic tiles.
Summary
The following presents a simplified summary of various aspects of this disclosure to provide a basic understanding of such aspects. This summary is not an extensive overview of all contemplated aspects, and is intended to neither identify key or critical elements nor delineate the scope of such aspects. Its purpose is to present some concepts of this disclosure in a simplified form as a prelude to the more detailed description that is presented later.
The following paragraphs provide additional support for the claims of the subject application.
The disclosure pertains to a system for detecting defects in ceramic tiles. The system comprises an image capture module that captures images of ceramic tiles, an image preprocessing module configured to enhance the quality of the captured images, a defect detection module implementing a Region-based Convolutional Neural Network (R-CNN) to identify defects in the pre-processed images, a storage module for storing processed images and detection results, and a monitoring module that logs the detection process and generates alerts upon detection of defects.
Said system enables the identification of various defect types in ceramic tiles, including tiny cracks and scratches, uneven glaze, and subtle colour inconsistencies. The defect detection module is trained on a dataset of ceramic tiles images with known defects, enhancing the accuracy in defect recognition. Furthermore, the monitoring module includes an alerting unit to notify operators in real-time when defects are detected, ensuring prompt response to quality issues.
Moreover, the image capture module is associated with a conveyor system to position the ceramic tiles optimally for image capturing, improving the efficiency of the detection process. Additionally, the storage module is configured to organize the detection results based on defect type, severity, and frequency, facilitating trend analysis and quality control measures. The ceramic tiles applicable for said system include porcelain, vitrified, and glazed tiles, highlighting the system's versatility in handling different types of ceramic tiles.
The present disclosure aims to provide a method for detecting defects in ceramic tiles. Said method includes capturing images of ceramic tiles using a camera input, preprocessing the captured images to enhance defect visibility, applying a Region-based Convolutional Neural Network (R-CNN) to the pre-processed images to identify defects, storing the processed images and detection results in a storage system, and monitoring the detection results through a monitoring system that includes logging and alerting functionalities. Such a method enhances the accuracy and efficiency of defect detection in ceramic tiles by leveraging advanced image processing and machine learning techniques.
Furthermore, the method encompasses categorizing the identified defects based on type and severity and generating a report summarizing the defects for quality control purposes. Said approach facilitates an analysis of the defect types and their severity, enabling targeted quality control measures. Moreover, the alerting functionality of the monitoring system is configured to integrate with manufacturing execution systems for automated quality control, streamlining the quality assurance process and ensuring timely intervention.
Additionally, the preprocessing step further includes the alignment and calibration of the captured images to standardize the input for the R-CNN. Said step ensures that the images are consistent in terms of orientation and scale, improving the reliability of the defect detection process. By implementing such a method, manufacturers can significantly enhance the quality control of ceramic tiles, reducing the incidence of defects and ensuring that the final products meet the required standards.

Brief Description of the Drawings

The features and advantages of the present disclosure would be more clearly understood from the following description taken in conjunction with the accompanying drawings in which:
FIG. 1 illustrates a system for detecting defects in ceramic tiles, in accordance with the embodiments of the present disclosure.
FIG. 2 illustrates a method 200 for detecting defects in ceramic tiles, in accordance with the embodiments of the present disclosure.
FIG. 3 illustrates a schematic of a system for the detection of defects in ceramic tiles using a Region-based Convolutional Neural Network (R-CNN), in accordance with the embodiments of the present disclosure.
Fig. 4 illustrates the operational setup for real-time ceramic tile defect detection system that comprising a conveyor belt that transports the tiles past a camera and lighting system designed to improve quality of capture images, in accordance with the embodiments of the present disclosure.

Detailed Description
In the following detailed description of the invention, reference is made to the accompanying drawings that form a part hereof, and in which is shown, by way of illustration, specific embodiments in which the invention may be practiced. In the drawings, like numerals describe substantially similar components throughout the several views. These embodiments are described in sufficient detail to claim those skilled in the art to practice the invention. Other embodiments may be utilized and structural, logical, and electrical changes may be made without departing from the scope of the present invention. The following detailed description is, therefore, not to be taken in a limiting sense, and the scope of the present invention is defined only by the appended claims and equivalents thereof.
The use of the terms “a” and “an” and “the” and “at least one” and similar referents in the context of describing the invention (especially in the context of the following claims) are to be construed to cover both the singular and the plural, unless otherwise indicated herein or clearly contradicted by context. The use of the term “at least one” followed by a list of one or more items (for example, “at least one of A and B”) is to be construed to mean one item selected from the listed items (A or B) or any combination of two or more of the listed items (A and B), unless otherwise indicated herein or clearly contradicted by context. The terms “comprising,” “having,” “including,” and “containing” are to be construed as open-ended terms (i.e., meaning “including, but not limited to,”) unless otherwise noted. Recitation of ranges of values herein are merely intended to serve as a shorthand method of referring individually to each separate value falling within the range, unless otherwise indicated herein, and each separate value is incorporated into the specification as if it were individually recited herein. All methods described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The use of any and all examples, or exemplary language (e.g., “such as”) provided herein, is intended merely to better illuminate the invention and does not pose a limitation on the scope of the invention unless otherwise claimed. No language in the specification should be construed as indicating any non-claimed element as essential to the practice of the invention.
Pursuant to the "Detailed Description" section herein, whenever an element is explicitly associated with a specific numeral for the first time, such association shall be deemed consistent and applicable throughout the entirety of the "Detailed Description" section, unless otherwise expressly stated or contradicted by the context.
The present disclosure relates to a system 100 for detecting defects in ceramic tiles. According to a pictorial illustration of FIG. 1, showcasing an architectural paradigm of the system 100 that can comprise functional elements, yet not limited to an image capture module 102, an image preprocessing module 104, a defect detection module 106, a storage module 108, and a monitoring module 110. A person ordinarily skilled in art would prefer those elements or components of the system 100, to be functionally or operationally coupled with each other, in accordance with the embodiments of present disclosure.
In an embodiment, the image capture module 102 can capture images of ceramic tiles. Specifically, the image capture module 102 captures images of ceramic tiles that may include a variety of tile types such as porcelain, vitrified, and glazed tiles. Optionally, the image capture module 102 is associated with a conveyor belt that positions the ceramic tiles optimally for image capturing, thereby ensuring that the tiles are presented to the image capture module 102 in a manner that maximizes the effectiveness of the image capture process. An example of operation includes the capture module 102 capturing high-resolution images as tiles move along the conveyor, allowing for continuous inspection without manual intervention.
In an embodiment, the image preprocessing module 104 can be configured to enhance the quality of the captured images. Said preprocessing module 104 processes the images captured by the image capture module 102 to improve image clarity and prepare them for defect analysis. Enhancements may include adjustments in brightness, contrast, and noise reduction to ensure that the images are of a suitable quality for defect detection. The improved image quality facilitates more accurate defect detection by reducing the likelihood of false positives and negatives.
In an embodiment, the defect detection module 106 implements a Region-based Convolutional Neural Network (R-CNN) to identify defects in the pre-processed images. The defect detection module 106 is trained on a dataset of ceramic tiles images with known defects to recognize a variety of defect types, including tiny cracks and scratches, uneven glaze, and subtle color inconsistencies. Said training enables the module to accurately identify defects in ceramic tiles by comparing incoming images against the learned characteristics of defects. The effectiveness of the defect detection module 106 in identifying a wide range of defect types is crucial for maintaining quality control in ceramic tile production.
In an embodiment, the storage module 108 can store processed images and detection results. The storage module 108 is configured to organize the detection results based on defect type, severity, and frequency to facilitate trend analysis. Said organization allows for easy retrieval of data for quality control purposes and enables the identification of recurring issues or patterns in defects, which can be invaluable for continuous improvement processes in manufacturing.
Referring to one or more preceding embodiments, the monitoring module 110 logs the detection process and generates alerts upon detection of defects. The monitoring module 110 includes an alerting mechanism that notifies operators in real-time when defects are detected. Said immediate notification enables prompt action to be taken to rectify detected issues, thereby minimizing the impact of defects on production quality and efficiency. The real-time alerting unit is a critical feature for maintaining operational awareness and ensuring that defects are addressed swiftly.
Disclosed a method 200 for detecting defects in ceramic tiles. Said method 200 encompasses a series of steps designed to capture, process, and analyse images of ceramic tiles to identify any defects present. Referring to a diagrammatic depiction put forth in FIG. 2, representing a flow diagram of the method 200 that can comprise steps of, yet not restricted to, (at step 202) capturing images of ceramic tiles, (at step 204) preprocessing the captured images, (at step 206) applying a Region-based Convolutional Neural Network (R-CNN), (at step 208) storing the processed images and detection results and (at step 210) monitoring the detection results. Said steps of the method 200 can be performed or executed, collectively or selectively, randomly, or sequentially or in a combination thereof, in accordance with the embodiments of current disclosure.
In an embodiment, at step 202, images of ceramic tiles are captured using a camera input. Said step 202 involves the utilization of a high-resolution camera to take detailed photographs of ceramic tiles for the purpose of defect detection. The capturing of images is a critical initial step that ensures that subsequent analysis is based on accurate and high-quality visual data of the ceramic tiles.
In an embodiment, at step 204, the captured images undergo preprocessing to enhance defect visibility. Said step 204 may include the alignment and calibration of the captured images to standardize the input for the Region-based Convolutional Neural Network (R-CNN), ensuring that the images are in a consistent format and orientation for effective analysis. Preprocessing enhances the clarity of potential defects in the images, making easier for the defect detection algorithms to identify issues.
In an embodiment, at step 206, a Region-based Convolutional Neural Network (R-CNN) is applied to the pre-processed images to identify defects. Said advanced machine learning technique analyzes the images to detect various defect types, employing a model that has been trained on a large dataset of ceramic tile images with known defects. The application of the R-CNN at said step 206 is crucial for accurately identifying defects by learning from examples of known defects.
In an embodiment, at step 208, the processed images and detection results are stored in a storage module 108. Said step 208 ensures that all data generated during the defect detection process, including images and analysis results, are securely stored for reference, analysis, or quality control purposes. The storage module 108 facilitates the organization and retrieval of detection results, which is essential for monitoring quality over time.
In an embodiment, at step 210, the detection results are monitored through the monitoring module 110 that includes logging and alerting functionalities. The monitoring module 110 is configured to integrate with manufacturing execution platforms for automated quality control, allowing for real-time tracking of defect detection and the immediate initiation of quality control measures when defects are identified. Said step 210 includes the generation of alerts to notify relevant personnel of detected defects, enabling prompt action to address the identified issues.
Referring to one or more preceding embodiments, the method 200 further comprises categorizing the identified defects based on type and severity and generating a report summarizing the defects for quality control purposes. Said additional step allows for a detailed analysis of the defects, facilitating targeted quality improvement efforts and providing documentation for quality assurance processes.
In an aspect, Region-based Convolutional Neural Network (R-CNN) can improve control process in ceramic tile manufacturing by providing a level of accuracy superior to human inspectors. The system 100 can detect an array of defects, such as minute cracks, glaze inconsistencies, and color variations, with a consistent and objective approach that human inspectors might miss due to fatigue or bias. As system 100 enable detection of fault, delivery of impeccable ceramic tiles can be achieve, thus bolstering the brand's reputation and consumer trust. Furthermore, R- can undergoes continuously learning and evolving to cater to the unique demands of different production lines and customer specifications. Furthermore, system 100 also enable waste reduction, catching defects early to minimize material loss and manufacturing costs, benefiting both the environment and the economic front.
In an embodiment, present disclosure employs Region-based Convolutional Neural Networks (R-CNN) to detect various defects in ceramic tiles, aiming for high accuracy and real-time identification to promptly initiate corrective measures. Said system 100 can be scaled for different tile characteristics and integrates seamlessly into existing production lines, minimizing disruption. The system 100 can comprise a user-friendly interface for ease of use across production scales and is built to withstand various lighting conditions, ensuring reliable defect detection. The system 100 can be automated for inspection process to reduce human error and increase productivity. Thus, the system 100 can become cost-effective through reduced operational and maintenance costs. Said R-CNN-based solution represents a transformative approach to quality control in ceramic tile manufacturing.
In an aspect, the system 100 can be customized for different tile surfaces to perform consistently under various lighting conditions, which can be crucial for application in diverse manufacturing settings. Post-detection, the system 100 classifies defects into specific categories, aiding in quality control and enabling manufacturers to tailor their remedial strategies. The intuitive interface of the system 100 facilitates easy interaction for operators and quality control personnel, while its scalability ensures suitability for production lines. Integrating seamlessly into existing manufacturing processes, the system 100 offers a cost-effective approach to enhancing quality control, reducing manual inspection, and ensuring a positive return on investment for ceramic tile manufacturers.
Fig. 3 depicts a schematic of a system 100 for the detection of defects in ceramic tiles using a Region-based Convolutional Neural Network (R-CNN). The workflow begins with camera inputs capturing images of the ceramic tiles, which are then pre-processed to enhance the image quality for defect detection. This preprocessing may include noise reduction and feature enhancement. The pre-processed images are analysed by an R-CNN model, which inspects each region of the image to detect any anomalies indicative of defects. The processed images and the results of the detection are stored in a database. The system 100 also includes a monitoring component that logs the detection process and generates alerts for any detected defects. This alerting unit is crucial for initiating prompt corrective measures, ensuring continuous production quality.
Fig. 4 outlines the operational setup for real-time ceramic tile defect detection system 100 that comprising a conveyor belt that transports the tiles past a camera and lighting arrangement designed to improve quality of capture images. The images are then transmitted to a central computer where the R-CNN algorithm extracts regions of interest, computes features, and classifies the tiles as defective or non-defective. The system 100 also comprising a photoelectric sensor, likely used to detect the presence of a tile and trigger the imaging process.
Example embodiments herein have been described above with reference to block diagrams and flowchart illustrations of methods and apparatuses. It will be understood that each block of the block diagrams and flowchart illustrations, and combinations of blocks in the block diagrams and flowchart illustrations, respectively, can be implemented by various means including hardware, software, firmware, and a combination thereof. For example, in one embodiment, each block of the block diagrams and flowchart illustrations, and combinations of blocks in the block diagrams and flowchart illustrations can be implemented by computer program instructions. These computer program instructions may be loaded onto a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions which execute on the computer or other programmable data processing apparatus create means for implementing the functions specified in the flowchart block or blocks.
Throughout the present disclosure, the term ‘processing means’ or ‘microprocessor’ or ‘processor’ or ‘processors’ includes, but is not limited to, a general purpose processor (such as, for example, a complex instruction set computing (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, a microprocessor implementing other types of instruction sets, or a microprocessor implementing a combination of types of instruction sets) or a specialized processor (such as, for example, an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a digital signal processor (DSP), or a network processor).
The term “non-transitory storage device” or “storage” or “memory,” as used herein relates to a random access memory, read only memory and variants thereof, in which a computer can store data or software for any duration.
Operations in accordance with a variety of aspects of the disclosure is described above would not have to be performed in the precise order described. Rather, various steps can be handled in reverse order or simultaneously or not at all.
While several implementations have been described and illustrated herein, a variety of other means and/or structures for performing the function and/or obtaining the results and/or one or more of the advantages described herein may be utilized, and each of such variations and/or modifications is deemed to be within the scope of the implementations described herein. More generally, all parameters, dimensions, materials, and configurations described herein are meant to be exemplary and that the actual parameters, dimensions, materials, and/or configurations will depend upon the specific application or applications for which the teachings is/are used. Those skilled in the art will recognize, or be able to ascertain using no more than routine experimentation, many equivalents to the specific implementations described herein. It is, therefore, to be understood that the foregoing implementations are presented by way of example only and that, within the scope of the appended claims and equivalents thereto, implementations may be practiced otherwise than as specifically described and claimed. Implementations of the present disclosure are directed to each individual feature, system, article, material, kit, and/or method described herein. In addition, any combination of two or more such features, systems, articles, materials, kits, and/or methods, if such features, systems, articles, materials, kits, and/or methods are not mutually inconsistent, is included within the scope of the present disclosure.

Claims

I/We claims:

1. A system 100 for detecting defects in ceramic tiles, comprising:
an image capture module 102 captures images of ceramic tiles;
an image preprocessing module 104 configured to enhance the quality of the captured images;
a defect detection module 106 implementing a Region-based Convolutional Neural Network (R-CNN) to identify defects in the pre-processed images;
a storage module 108 for storing processed images and detection results; and
a monitoring module 110 that logs the detection process and generates alerts upon detection of defects.
2. The system of claim 1, wherein the defect detection module is trained on a dataset of ceramic tiles images with known defects to recognize a variety of defect types selected from tiny cracks and scratches, uneven glaze, and subtle colour inconsistencies.
3. The system of claim 1, wherein the monitoring module includes an alerting unit that notifies operators in real-time when defects are detected.
4. The system of claim 1, wherein the image capture module is associated with a conveyor unit designed to position the ceramic tiles optimally for image capturing.
5. The system of claim 1, wherein the storage module is configured to organize the detection results based on defect type, severity, and frequency to facilitate trend analysis.
6. The system of claim 1, wherein the ceramic tiles are selected from porcelain, vitrified, and glazed tiles.
7. A method 200 for detecting defects in ceramic tiles, comprising:
(at step 202) capturing images of ceramic tiles using a camera input;
(at step 204) preprocessing the captured images to enhance defect visibility;
(at step 206) applying a Region-based Convolutional Neural Network (R-CNN) to the pre-processed images to identify defects;
(at step 208) storing the processed images and detection results in a storage module; and
(at step 210) monitoring the detection results through a monitoring module that includes logging and alerting functionalities.
8. The method of claim 7, further comprising:
categorizing the identified defects based on type and severity; and
generating a report summarizing the defects for quality control purposes.
9. The method of claim 7, wherein the alerting functionality of the monitoring module is configured to integrate with manufacturing execution platforms for automated quality control.
10. The method of claim 7, wherein the preprocessing step further includes the alignment and calibration of the captured images to standardize the input for the R-CNN.

CERAMIC TILES DEFECT DETECTION THROUGH R-CNN

The present disclosure provides a system (100) for detecting defects in ceramic tiles. This system comprises an image capture module (102) that captures images of ceramic tiles, and an image preprocessing module (104) that enhances the quality of the captured images. A defect detection module (106) implements a Region-based Convolutional Neural Network (R-CNN) to identify defects in the pre-processed images. A storage module (108) stores processed images and detection results. Additionally, a monitoring module (110) logs the detection process and generates alerts upon detection of defects.

Drawings
/
FIG 1

/
Fig 2

/
FIG. 3
/ FIG. 4

, Claims:I/We claims:

1. A system 100 for detecting defects in ceramic tiles, comprising:
an image capture module 102 captures images of ceramic tiles;
an image preprocessing module 104 configured to enhance the quality of the captured images;
a defect detection module 106 implementing a Region-based Convolutional Neural Network (R-CNN) to identify defects in the pre-processed images;
a storage module 108 for storing processed images and detection results; and
a monitoring module 110 that logs the detection process and generates alerts upon detection of defects.
2. The system of claim 1, wherein the defect detection module is trained on a dataset of ceramic tiles images with known defects to recognize a variety of defect types selected from tiny cracks and scratches, uneven glaze, and subtle colour inconsistencies.
3. The system of claim 1, wherein the monitoring module includes an alerting unit that notifies operators in real-time when defects are detected.
4. The system of claim 1, wherein the image capture module is associated with a conveyor unit designed to position the ceramic tiles optimally for image capturing.
5. The system of claim 1, wherein the storage module is configured to organize the detection results based on defect type, severity, and frequency to facilitate trend analysis.
6. The system of claim 1, wherein the ceramic tiles are selected from porcelain, vitrified, and glazed tiles.
7. A method 200 for detecting defects in ceramic tiles, comprising:
(at step 202) capturing images of ceramic tiles using a camera input;
(at step 204) preprocessing the captured images to enhance defect visibility;
(at step 206) applying a Region-based Convolutional Neural Network (R-CNN) to the pre-processed images to identify defects;
(at step 208) storing the processed images and detection results in a storage module; and
(at step 210) monitoring the detection results through a monitoring module that includes logging and alerting functionalities.
8. The method of claim 7, further comprising:
categorizing the identified defects based on type and severity; and
generating a report summarizing the defects for quality control purposes.
9. The method of claim 7, wherein the alerting functionality of the monitoring module is configured to integrate with manufacturing execution platforms for automated quality control.
10. The method of claim 7, wherein the preprocessing step further includes the alignment and calibration of the captured images to standardize the input for the R-CNN.

CERAMIC TILES DEFECT DETECTION THROUGH R-CNN