The present disclosure relates, in general, to manufacturing processes,
and more specifically, relates to a system and method for automatic detection of defects.
BACKGROUND
[0002] In industrial processes, one of the most important tasks when it comes
to ensuring the proper quality of the finished product is the inspection of the
product's surfaces. During the manufacturing assembly of products, many
opportunities exist for the creation of defects. Defects may be in the form of
misplaced components, faulty or incomplete connections or out of specification
electrical or mechanical features. Often, surface quality control is carried out
manually and workers are trained to identify complex surface defects.
[0003] Typically, after defects are detected, a human user goes through the
identified defects and discerns which of the defects are real and which are false. Real defects are then repaired before the mask is finished and shipped to a customer. Choosing a recipe that produces an excessive number of false detections may unnecessarily increase cycle time and cost money. Such control is, however, very time consuming, inefficient, and can contribute to a serious limitation of the production capacity.
[0004] Therefore, it is desired to develop a means for automatic detection of
defects in the manufacturing process.
OBJECTS OF THE PRESENT DISCLOSURE
[0005] An object of the present disclosure relates, in general, to
manufacturing processes, and more specifically, relates to a system and method for
automatic detection of defects.
[0006] Another object of the present disclosure is to provide a system that
improves product quality.
[0007] Another object of the present disclosure is to provide a system that
performs surface quality control automatically.

[0008] Another object of the present disclosure is to provide a system that
reduces the inspection time.
[0009] Another object of the present disclosure is to provide a system that
optimizes the inspection cost.
[0010] Yet another object of the present disclosure is to provide a system that
is available at an affordable cost.
SUMMARY
[0011] The present disclosure relates, in general, to manufacturing processes,
and more specifically, relates to a system and method for automatic detection of defects.
[0012] The present disclosure relates to a system for detecting defect in a
product, the system includes an image capturing device configured to capture one or more images of the product; and a processor operatively coupled with a memory, the memory storing instructions executable by the processor to receive, from the image capturing device, the one or more images of the product, analyse the received one or more images to extract a set of attributes from the one or more images, classify the extracted set of attributes based on matching of the extracted set of attributes with a reference set of attributes; and extract, from the extracted set of attributes, a set of values for the extracted set of attributes, wherein, based on a combination of classification of the extracted attributes and a deviation of the extracted set of values for the extracted set of attributes from a reference set of values, the processor is configured to determine and segment the product into a set of categories, the set of categories pertaining to any or a combination of normal state and defective state of the product.
[0013] According to an embodiment, the processor is operatively coupled to
a learning engine, the learning engine can be trained to detect normal state and defective state of the product.
[0014] According to an embodiment, the learning engine is trained using a
historical data of correlation of the extracted set of attributes of a received one or

more images of the product with a determination for the product, the determination
pertaining to normal state and defective state of the product.
[0015] According to an embodiment, the learning engine comprises any or a
combination of convolutional neural networks (CNN) and deep neural network
(DNN).
[0016] According to an embodiment, the image capturing device is an X-ray
camera.
[0017] According to an embodiment, the products are vehicle engine,
submersible pumps, motors and any combination thereof.
[0018] The present disclosure relates to a method for detecting defect in a
product, the method includes capturing, by an image capturing device, one or more
images of the product, receiving, at a computing device, from the image capturing
device, the one or more images of the product, analysing, at the computing device,
the received one or more images to extract a set of attributes from the one or more
images, classifying, at the computing device, the extracted set of attributes based
on matching of the extracted set of attributes with a reference set of attributes;
extracting, at the computing device, from the extracted set of attributes, a set of
values for the extracted set of attributes, wherein, based on a combination of
classification of the extracted attributes and a deviation of the extracted set of values
for the extracted set of attributes from a reference set of values, the computing
device is configured to determine and segment the product into a set of categories,
the set of categories pertaining to any or a combination of normal state and
defective state of the product.
[0019] Various objects, features, aspects, and advantages of the inventive
subject matter will become more apparent from the following detailed description
of preferred embodiments, along with the accompanying drawing figures in which
like numerals represent like components.
BRIEF DESCRIPTION OF THE DRAWINGS
[0020] The following drawings form part of the present specification and are
included to further illustrate aspects of the present disclosure. The disclosure may

be better understood by reference to the drawings in combination with the detailed
description of the specific embodiments presented herein.
[0021] FIG. 1A illustrates an exemplary representation of a system for
detecting surface defects on a manufacturing product, in accordance with an
embodiment of the present disclosure.
[0022] FIG. IB illustrates an exemplary schematic view of the system for
detecting surface defects on a manufacturing product, in accordance with an
embodiment of the present disclosure.
[0023] FIG. 2 illustrates a flow chart of the process for detecting surface
defects on a manufacturing product, in accordance with an embodiment of the
present disclosure.
[0024] FIG. 3 illustrates an exemplary computer system in which or with
which embodiments of the present invention can be utilized in accordance with
embodiments of the present disclosure.
DETAILED DESCRIPTION
[0025] The following is a detailed description of embodiments of the
disclosure depicted in the accompanying drawings. The embodiments are in such detail as to clearly communicate the disclosure. If the specification states a component or feature "may", "can", "could", or "might" be included or have a characteristic, that particular component or feature is not required to be included or have the characteristic.
[0026] As used in the description herein and throughout the claims that
follow, the meaning of "a," "an," and "the" includes plural reference unless the context clearly dictates otherwise. Also, as used in the description herein, the meaning of "in" includes "in" and "on" unless the context clearly dictates otherwise.
[0027] The present disclosure relates, in general, to manufacturing processes,
and more specifically, relates to a system and method for automatic detection of defects. The system and method enable to overcome limitations of the prior art by providing an automated model for casting manufacturing defect detection. The

automated model can include a training dataset, trained by the VGG-16 model. The
camera captures the product images and stores in a database. These new images are
testing images. The automated model can apply for the testing process, where the
model can classify the product into two categories as normal and defective.
[0028] The present disclosure can be described in enabling detail in the
following examples, which may represent more than one embodiment of the present disclosure. The description of terms and features related to the present disclosure shall be clear from the embodiments that are illustrated and described; however, the invention is not limited to these embodiments only. Numerous modifications, changes, variations, substitutions, and equivalents of the embodiments are possible within the scope of the present disclosure. Additionally, the invention can include other embodiments that are within the scope of the claims but are not described in detail with respect to the following description.
[0029] FIG. 1A illustrates an exemplary representation of a system for
detecting surface defects on a manufacturing product, in accordance with an embodiment of the present disclosure.
[0030] Referring to FIG. 1A, system 100 configured for detecting surface
defects on a manufacturing product such as vehicle engine, submersible pumps, motors and the likes. The system 100 can be used to conduct automated screening of surface defects of the manufacturing product. The system 100 can include an image capturing device 102, a processor 104, a memory 106 and a learning engine 108.
[0031] The image capturing device 102 can be configured to obtain one or
more images of the product. In an exemplary embodiment, the image capturing device 102 can be an X-ray camera shown in FIG. IB. The product images can be acquired by a high dynamic range camera. The image capturing device 102 is operatively coupled to the processor 104, the processor can be coupled to the memory 106. The memory is configured to store executable instructions configured for execution by the processors.
[0032] In an embodiment, the images captured by camera 102 are transmitted
to processor 104. The image analysis can be performed by utilizing learning engine

108 e.g., convolutional neural networks (CNNs), deep neural network (DNN) and
the likes. The learning engine 108 can be trained to accurately and automatically
perform image processing to detect a particular defect of the product in the digital
image and to classify the products according to the detected attributes.
[0033] The processor 104 is operatively coupled to a learning engine 108,
where the learning engine 108 can be trained to detect defect state and normal state of the product. The learning engine is trained using historical data of correlation of the extracted set of attributes of a received one or more images of the product with a determination for the product, the determination pertaining to a normal state and defective state of the product.
[0034] In an exemplary embodiment, the learning engine 108 can be artificial
intelligence model i.e., visual geometry group from oxford (VGG-16). The model is based on a segmentation-based deep-learning architecture that is designed for the detection and segmentation of manufacturing defects of the product. The gathered images are pre-processed to emphasize features and used for an artificial intelligence model VGG-16 to classify normal and abnormal statuses. In addition, to understand and check the basis of the model's feature learning, a gradient-weighted class activation mapping algorithm is applied to select a model that has the correct judgment criteria.
[0035] In an embodiment, the processor 104 can be configured to analyse the
received images to extract a set of attributes from one or more images. The extracted set of attributes can be classified based on matching of the extracted set of attributes with a reference set of attributes. A set of values can be extracted for the extracted set of attributes, wherein, based on a combination of classification of the extracted attributes and a deviation of the extracted set of values for the extracted set of attributes from a reference set of values, the processor is configured to determine and segment the product into a set of categories. The set of categories pertaining to any or a combination of the normal state and defective state of the product. The reference set of attributes can be a pre-trained dataset.
[0036] For example, the processor configured with a VGG-16 model, a
trained neural network model that facilitates image classification of the captured

images of manufacturing products. The captured images are compared with a pre-
trained dataset of the VGG-16 model to segment the images into two specific
category, normal or defective.
[0037] The computing device can include processor that can be in
communication with each of a memory, and input/output devices. The processor
may include a microprocessor or other devices capable of being programmed or
configured to perform computations and instruction processing in accordance with
the disclosure. In an exemplary embodiment, the processor can be Raspberry-Pi.
Such other devices may include microcontrollers, digital signal processors (DSP),
complex programmable logic device (CPLD), field programmable gate arrays
(FPGA), application-specific assimilated circuits (ASIC), discrete gate logic,
and/or other assimilated circuits, hardware or firmware in lieu of or in addition to a
microprocessor.
[0038] The memory includes programmable software instructions that are
executed by the processor. The processor may be embodied as a single processor or
a number of processors. The processor and a memory may each be, for example
located entirely within a single computer or other computing device. The memory,
which enables storage of data and programs, may include random-access memory
(RAM), read-only memory (ROM), flash memory and any other form of readable
and writable storage medium.
[0039] The embodiments of the present disclosure described above provide
several advantages. The advantages achieved by the system and method of the
present disclosure can be clear from the embodiments provided herein. The system
improves the product quality, performs surface quality control automatically,
reduces the inspection time and optimizes the inspection cost. The system can be
available at an affordable cost.
[0040] FIG. 2 illustrates a flow chart of the process for detecting surface
defects on a manufacturing product, in accordance with an embodiment of the
present disclosure.
[0041] Referring to FIG.2, the method 200 can be implemented using a
computing device, which can include processors. The method 200 incudes, at block

202, the image capturing device, that can capture one or more images of the product. At block 204, the computing device can receive from the image capturing device, the one or more images of the product.
[0042] At block 206, the computing device can analyse the received one or
more images to extract a set of attributes from the one or more images. At block
208, the computing device can classify the extracted set of attributes based on
matching of the extracted set of attributes with a reference set of attributes.
[0043] At block 208, the computing device can extract from the extracted set
of attributes, a set of values for the extracted set of attributes, wherein, based on a combination of classification of the extracted attributes and a deviation of the extracted set of values for the extracted set of attributes from a reference set of values, the computing device is configured to determine and segment the product into a set of categories, the set of categories pertaining to any or a combination of normal state and defective state of the product.
[0044] FIG. 3 illustrates an exemplary computer system in which or with
which embodiments of the present invention can be utilized in accordance with embodiments of the present disclosure.
[0045] As shown in FIG. 3, computer system 300 includes an external storage
device 310, a bus 320, a main memory 330, a read only memory 340, a mass storage device 350, communication port 360, and a processor 370. A person skilled in the art will appreciate that computer system may include more than one processor and communication ports. Examples of processor 370 include, but are not limited to, an Intel® Itanium® or Itanium 2 processor(s), or AMD® Opteron® or Athlon MP® processor(s), Motorola® lines of processors, FortiSOC™ system on a chip processors or other future processors. Processor 370 may include various modules associated with embodiments of the present invention. Communication port 360 can be any of an RS-232 port for use with a modem-based dialup connection, a 10/100 Ethernet port, a Gigabit or 10 Gigabit port using copper or fibre, a serial port, a parallel port, or other existing or future ports. Communication port 360 may be chosen depending on a network, such a Local Area Network (LAN), Wide Area Network (WAN), or any network to which computer system connects.

[0046] Memory 330 can be Random Access Memory (RAM), or any other
dynamic storage device commonly known in the art. Read only memory 340 can be any static storage device(s) e.g., but not limited to, a Programmable Read Only Memory (PROM) chips for storing static information e.g., start-up or BIOS instructions for processor 370. Mass storage 350 may be any current or future mass storage solution, which can be used to store information and/or instructions. Exemplary mass storage solutions include, but are not limited to, Parallel Advanced Technology Attachment (PATA) or Serial Advanced Technology Attachment (SATA) hard disk drives or solid-state drives (internal or external, e.g., having Universal Serial Bus (USB) and/or Firewire interfaces), e.g. those available from Seagate (e.g., the Seagate Barracuda 7200 family) or Hitachi (e.g., the Hitachi Deskstar 7K1000), one or more optical discs, Redundant Array of Independent Disks (RAID) storage, e.g. an array of disks (e.g., SATA arrays), available from various vendors including Dot Hill Systems Corp., LaCie, Nexsan Technologies, Inc. and Enhance Technology, Inc.
[0047] Bus 320 communicatively couples processor(s) 370 with the other
memory, storage, and communication blocks. Bus 320 can be, e.g. a Peripheral Component Interconnect (PCI) / PCI Extended (PCI-X) bus, Small Computer System Interface (SCSI), USB or the like, for connecting expansion cards, drives and other subsystems as well as other buses, such a front side bus (FSB), which connects processor 370 to software system.
[0048] Optionally, operator and administrative interfaces, e.g. a display,
keyboard, and a cursor control device, may also be coupled to bus 320 to support direct operator interaction with computer system. Other operator and administrative interfaces can be provided through network connections connected through communication port 360. External storage device 310 can be any kind of external hard-drives, floppy drives, IOMEGA® Zip Drives, Compact Disc - Read Only Memory (CD-ROM), Compact Disc - Re-Writable (CD-RW), Digital Video Disk - Read Only Memory (DVD-ROM). Components described above are meant only to exemplify various possibilities. In no way should the aforementioned exemplary computer system limit the scope of the present disclosure.

[0049] It will be apparent to those skilled in the art that the system 100 of the
disclosure may be provided using some or all of the mentioned features and components without departing from the scope of the present disclosure. While various embodiments of the present disclosure have been illustrated and described herein, it will be clear that the disclosure is not limited to these embodiments only. Numerous modifications, changes, variations, substitutions, and equivalents will be apparent to those skilled in the art, without departing from the spirit and scope of the disclosure, as described in the claims.
ADVANTAGES OF THE PRESENT DISCLOSURE
[0050] The present disclosure provides a system that improves the product
quality.
[0051] The present disclosure provides a system that performs surface quality
control automatically.
[0052] The present disclosure provides a system that reduces the inspection
time.
[0053] The present disclosure provides a system that optimizes the inspection
cost.
[0054] The present disclosure provides a system that is available at an
affordable cost.

We Claim:

1. A system for detecting defect in a product, the system comprising:
an image capturing device (102) configured to capture one or more images of the product; and
a processor (104) operatively coupled with a memory, said memory storing instructions executable by the processor to:
receive, from the image capturing device (102), the one or more images of the product;
analyse the received one or more images to extract a set of attributes from the one or more images;
classify the extracted set of attributes based on matching of the extracted set of attributes with a reference set of attributes; and
extract, from the extracted set of attributes, a set of values for the extracted set of attributes, wherein, based on a combination of classification of the extracted attributes and a deviation of the extracted set of values for the extracted set of attributes from a reference set of values, the processor is configured to determine and segment the product into a set of categories, the set of categories pertaining to any or a combination of normal state and defective state of the product.
2. The system as claimed in claim 1, wherein the processor is operatively coupled to a learning engine, the learning engine can be trained to detect normal state and defective state of the product.
3. The system as claimed in claim 1, wherein the learning engine is trained using a historical data of correlation of the extracted set of attributes of a received one or more images of the product with a determination for the product, the determination pertaining to the normal state and defective state of the product.

4. The system as claimed in claim 1, wherein the learning engine comprises any or a combination of convolutional neural networks (CNN) and deep neural network (DNN).
5. The system as claimed in claim 1, wherein the image capturing device is an X-ray camera.
6. The system as claimed in claim 1, wherein the products are vehicle engine, submersible pumps, motors and any combination thereof.
7. A method (200) for detecting defect in a product, the method comprising:
capturing (202), by an image capturing device, one or more images of the product;
receiving (204), at a computing device, from the image capturing device, the one or more images of the product;
analysing (206), at the computing device, the received one or more images to extract a set of attributes from the one or more images;
classifying (208), at the computing device, the extracted set of attributes based on matching of the extracted set of attributes with a reference set of attributes;
extracting (210), at the computing device, from the extracted set of attributes, a set of values for the extracted set of attributes, wherein, based on a combination of classification of the extracted attributes and a deviation of the extracted set of values for the extracted set of attributes from a reference set of values, the computing device is configured to determine and segment the product into a set of categories, the set of categories pertaining to any or a combination of normal state and defective state of the product.