WO2020202215A1

WO2020202215A1 - A system and method of automated digitization of a product

Info

Publication number: WO2020202215A1
Application number: PCT/IN2020/050323
Authority: WO
Inventors: Eobin Alex George
Original assignee: Perfectfit Systems Private Limited
Priority date: 2019-04-02
Filing date: 2020-04-02
Publication date: 2020-10-08

Abstract

A system of automating digitization of a product to deploy on a media platform that comprises a processor that executes instructions and are configured to generate a media library, determine a system of choice for feature extraction from (i) a rule based engine or (ii) a machine learning model, determine a score of the at least one first feature or the at least one second feature extracted by the rule based engine or the machine learning model; generate a digitalized product by compiling the highest scoring first feature or the highest scoring second feature for each of the plurality of predetermined categories or generate recommendations based on the feature scores of the plurality of categories for the product image and deploy the digitalized product on the media platform. The system further captures performance feedback from the feature categorizing module to further improve performance of the machine learning model.

Description

A SYSTEM AND METHOD OF AUTOMATED DIGITIZATION OF A PRODUCT

BACKGROUND

Technical Field

[0001] The embodiments herein generally relate to computer vision and image processing using a machine learning model, more particularly to an automated product digitization system and method.

Description of the Related Art

[0002] In recent times, there have been many attempts to digitalize object which has numerous advantages. Digitization provides great accessibility of image data to the masses. It reduces cost, time and brings a vast amount of image data to available media platforms. That’s why the process of digitization has gained momentum in recent times. Digitization is used extensively in online retail businesses and digitization of assets in the virtual world. It is important that the consumer has a good experience of the digitalized product. That is ensured by selecting the good quality image and video data of the product. But for product digitization, photo studios and photographers need to be engaged and their cost is high. The whole process traditionally involves a lot of human hours. Also, there is considerable data storage cost involved. Another drawback is that the quality is not assured and it takes a considerable amount of human input to maintain the quality of product image data and it is not easily reproducible. Conventionally, a time taken for digitization, editing and posting on to a web server. There have been attempts to automate the digitization process but they take time or may not be cost-efficient.

[0003] Accordingly, there remains a need for an improved system and method for digitization of products to be made available for consumers.

SUMMARY

[0004] In view of forgoing, the embodiment herein provides a system and method of automating digitization of a product to deploy on a media platform. In an embodiment, the system includes a memory that stores a set of instructions and a processor that executes the set of instructions and is configured to (a) generate a media library of a product, wherein the media library is generated using at least one of a single angle image, multi-angle images or videos of the product wherein, at least one of single angle image, multi-angle images or videos of the product are grouped into a plurality of pixel groups based on hue, illumination and tone; (b) determine a system of choice for feature extraction from (i) a rule based engine or (ii) machine learning model, wherein the rule based engine determines at least one first feature from predetermined features by analysing the media library at each of the plurality of pixel groups, wherein the predetermined features comprise of at least one of a color, a pattern, a shape, a dimension, a noise or an unwanted data, a logo, a text, presence or absence of an object, a texture or a type and wherein, the machine learning model identifies the at least one second feature wherein the machine learning model is trained using a plurality of electronics image data and a plurality of inputs by a user; (c) determine at least one category of the at least one first feature or the at least one second feature from a plurality of predetermined categories by analyzing the at least one first feature or the at least one second feature; (d) determine a score of the at least one first feature or the at least one second feature based on an input received from a user or by analyzing social media electronics data; (e) determine a highest scoring first feature or a highest scoring second feature based on the score for each of the plurality of predetermined categories; (f) generate a digitalized product by compiling the highest scoring first feature or the highest scoring second feature for each of the plurality of predetermined categories or generate recommendations based on the feature scores of the plurality of categories for the product image, and deploy the digitalized product on the media platform.

[0005] In an embodiment, the processor executed set of instructions are configured to identify meta tags from the at least one of single angle image, multi-angle images or videos of the product from the media library at the machine learning model.

[0006] In some embodiments, the system of choice is determined by analyzing at least one of (a) a cost of computation, (b) an economic projection, (c) a total duration or (d) an expected accuracy.

[0007] In some embodiments, the processor executed set of instructions are configured to receive inputs from a user for feature extraction from at least one of single angle image, multi angle images, or videos of the product from the media library at the machine learning model.

[0008] In some embodiments, the processor executed set of instructions are configured to determine score of the at least one first feature or the at least one second feature based from analyzing social media electronics data for at least one of (i) target audience information, (ii) a product category or (iii) a demographic data. [0009] In some embodiments, the machine learning model receives the input from the user to train the machine learning model for subsequent outputs wherein the input from the user, if received, weighs more than the machine learning model output.

[0010] In some embodiments, the machine learning model is trained using data from at least one of (i) a pre-existing visual data generated by the system, (ii) a commercial website, (iii) a social media score, (iv) an e-commerce website or a user input.

[0011] In some embodiments, the system further includes (a) a rotating platform on which the product is placed; (b) a lighting unit that illuminates the product on the rotating platform; (c) a multi- lens camera unit that capture single angle or multi-angle images or videos to generate the media library; and (d) a controller that is communicatively connected to the rotating platform, the camera system, and the lighting unit, wherein the processor executed set of instructions are configured to generate recommendations for the controller to control at least one of (i) at least one of a rotational degree of the rotational platform, wherein the rotating platform rotates along at least one plane in a range of 1 degree to 360 degrees in a clockwise or anti clockwise direction, a sequence of rotation or a rotation speed; (ii) the multi-lens camera unit for at least one of an exposure, position, focus, zoom, aperture size, a flash time, a shutter speed, angle, frames per second (FPS), a lens resolution, an aspect ratio or a camera motion or (iii) the lighting unit for at least one of the settings for an hue, an intensity, a direction or a nature for a predetermined interval.

[0012] In an embodiment, the system further includes a robotic switching arm or at least one degree of freedom articulated arm that is communicatively connected to the controller, wherein the processor executed set of instructions are configured to generate recommendations for the controller to control the robotic switching arm or the at least one degree of freedom articulated arm, wherein the robotic switching arm or the at least one degree of freedom articulated arm swaps a plurality of the products in a successive order.

[0013] In some embodiments, a method of automating digitization of a product to deploy on a media platform is provided. The method comprises the steps of (a) generating a media library of a product using at least one of a single angle image, multi-angle images, or videos of the product, wherein at least one of single angle image, multi-angle images, or videos of the product are grouped into a plurality of pixel groups based on hue, illumination and tone, (b) determining a system of choice for feature extraction from (i) a rule based engine or (ii) a machine learning model, wherein the rule based engine determines at least one first feature from predetermined features by analyzing the media library at each pixel group, wherein the predetermined features comprise of at least one of a color, a pattern, a shape, a dimension, a noise or an unwanted data, a logo, a text, a presence or absence of an object, a texture or a type and wherein the machine learning modelidentifies the at least one second feature wherein the machine learning model is trained using a plurality of electronics image data, (c) determining at least one category of the at least one first feature or the at least one second feature from a plurality of predetermined categories by determining a score of the at least one first feature or the at least one second feature analyzing the at least one first feature or the at least one second feature based on input received from a user or from analyzing social media electronics data, (d) determining a highest scoring first feature or a highest scoring second feature based on the score for each of the plurality of predetermined categories, (e) generating a digitalized product by compiling the highest scoring first feature or the highest scoring second feature for each of the plurality of predetermined categories or generating recommendations based on the feature scores of the plurality of categories for the product image and (f) deploying the digitalized product on the media platform.

[0014] In an embodiment, the product digitization method and system is used for archiving data. For example, in forensic science, animal tagging and monitoring a catch, animal parts, documents or books, archaeological artifacts, crime and objects used in crime archival, perishable objects, human body parts.

[0015] In an embodiment, the product digitization system and method is used for cars, retail products, hand crafted or designed products, food photography, object lookup from database, fashion products, dimension capturing of products, aviation, look of spare parts based on the product in the digitizer, part dimension checking, fashion, shoes, garments, and accessories.

[0016] In an embodiment, images and videos of the digitalized products are used to train artificial intelligence systems.

[0017] These and other aspects of the embodiments herein will be better appreciated and understood when considered in conjunction with the following description and the accompanying drawings. It should be understood, however, that the following descriptions, while indicating preferred embodiments and numerous specific details thereof, are given by way of illustration and not of limitation. Many changes and modifications may be made within the scope of the embodiments herein without departing from the spirit thereof.

BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The embodiments herein will be better understood from the following detailed description with reference to the drawings, in which:

[0019] FIG. 1 illustrates a system view a product digitization system according to an embodiment herein;

[0020] FIG. 2 illustrates an exploded view of a product digitization server of FIG. 1 according to an embodiment herein;

[0021] FIG. 3 illustrates an exemplary view of product digitization according to an embodiment herein;

[0022] FIG. 4 illustrates a flow diagram of a method of product digitization according to an embodiment herein;

[0023] Fig. 5 illustrates an exploded view of the product digitalization server of FIG. 1 according to the embodiments herein; and

[0024] FIG. 6 illustrates a representative hardware environment for practicing the embodiments herein.

DETAIFED DESCRIPTION OF PREFERRED EMBODIMENTS

[0025] The embodiments herein and the various features and advantageous details thereof are explained more fully with reference to the non-limiting embodiments that are illustrated in the accompanying drawings and detailed in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein may be practiced and to further enable those of skill in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.

[0026] As mentioned, there remains a need for an improved system for digitization of products. The products herein also include living and non- living objects. Digitization is a process of converting information into a digital format. In this format, information is organized into discrete units of data (called bits) that can be separately addressed (usually in multiple-bit groups called byte). [0027] Referring now to the drawings, and more particularly to FIGS. 1 through 6, where similar reference characters denote corresponding features consistently throughout the figures, preferred embodiments are shown.

[0028] FIG. 1 illustrates a system view a product digitization system according to an embodiment herein. The product digitization system 100 includes a product digitization server 104 and a machine learning model 106. The product digitization server 104 receives a plurality of two dimensional or three dimensional images or videos of a product to be digitalized. In an embodiment, the plurality of two dimensional or three dimensional images or videos are received from electronics data. The electronics data can be online or offline. In an embodiment, the system further includes a controller 102 that is communicatively coupled with at least one of a lighting unit, a multi-lens camera unit or a rotating platform. The controller 102 receives a set of instructions from the product digitization server 104 to control a lighting unit, a multi -lens camera unit and a rotating platform on which a product to be digitized is placed. In an embodiment, the controller 102 further controls a robotic arm or an at least one degree of freedom articulated arm to swap a plurality of the products in quick succession while the multi - angle camera unit captures a single angle or multi-angle images or a video of the product when it is placed on the rotating table. The controller 102 controls the multi-lens camera unit for at least one of an exposure, position, focus, zoom, aperture size, a flash time, a shutter speed, angle, frames per second (FPS), a lens resolution, an aspect ratio or camera motion. The lighting unit , the rotating degree, rotating speed, sequence, and direction is controlled concurrently with capturing of a visual data of the product by the multi-lens camera unit. The lighting unit is controlled for at least one of the settings for a hue, an intensity, a direction or a nature of the light for a predetermined interval.

[0029] In some embodiments, the machine learning model is a multi-level model. In an embodiment, the machine learning model is convolutional neural net (CNN) model.

[0030] In an embodiment, the product digitization system is used for movies, games, and animations for digitization of assets into the virtual world.

[0031] FIG. 2 illustrates an exploded view a product digitization server 104 of FIG. 1 according to an embodiment herein. The system includes a database 202, a media module 204, a feature categorizing module 210, a scoring module 212, a ranking module 214, a recommendation module 216, a feedback module 218, a digitizer module 220, a rules-based engine 208, the machine learning model 106 and a system evaluation module 206. The database 202 includes electronics image data of a plurality of product images. In an embodiment, the database 202 also maintains the performance logs for the machine learning model 106 and the rules-based engine 208. For a product to be digitized, the media module 204 uses at least one of a single angle image, multi-angle images or videos of the product. The at least one of a single angle image, multi-angle images or videos of the product is analysed and a plurality of pixel groups are determined. The feature categorizing module 210 detects at least one first feature by the rules-based engine 208 or at least one second feature by the machine learning model 106. The scoring module 212 scores the at least one first feature by the rules-based engine 208 or the at least one second feature by the machine learning model 106 based on electronics data. The feedback module 218 includes a user input for training the machine learning model 106. In an embodiment, the user input outweighs the machine learning output and is used to manipulate the output for subsequent machine learning computations. The system evaluation module 206 helps to further improve performance by switching strategies of detection from rule -based to machine learning based and vice-versa based on the performance logs. The ranking module 214 determines the order of the scores and selects a highest scoring first feature or a highest scoring second feature based on the score for each of the plurality of predetermined categories. The recommendation module 216 recommends the higher scoring images or videos from the media library. The digitizer module 220 compiles the highest scoring first feature or the highest scoring second feature for each of the plurality of predetermined categories. The digitalized product is deployed on a media platform.

[0032] In an example, a feature determined is a dimension and a shape. For a retail store, the product digitization server 104 determines an apparel for size and category, and automates classification at the feature categorizing module 210 and deploys the digitized product on the media platform.

[0033] In an example, a feature color is selected and a cost of processing, time taken and accuracy is computed for both of the rule-based engine 208 and the machine learning model 106. based on the results, the system evaluation module 206 determines either the rule-based engine 208 and the machine learning model 106. As shown in the table, the rules based engine 208 is more suited for feature digitization for color and hence it is chosen by the system evaluation module 206. Also, in another example, for a feature‘shape’, a cost of processing, time taken and accuracy is computed for both of the rule based engine 208 and the machine learning model 106. The machine learning module 106 may be determined based on significant improvement on accuracy for the feature‘shape’.

[0034] FIG. 3 illustrates an exemplary view of product digitization according to an embodiment herein. The exemplary view depicts a product on a rotating platform with multi-lens camera unit, and a lighting unit. The product being digitized is a shoe. A robotic arm is also seen in this exemplary view. Enter Basic Details of Model number, Store, etc.

[0035] In an embodiment, following steps are performed for the product digitization, placing the product in the booth, initiate digitization at the product digitization server, in Auto mode Low-resolution images are taken to determine product nature and type, high-resolution images and videos are taken in recommended settings of lighting and camera and position/motion, the media transferred to cloud, the system generates metadata and populates the database 202 with that data corresponding an ID number that maps that information to the corresponding product, product images are processed and cleaned up either manually or automatically, the images are ranked and displayed in the user portal. [0036] FIG. 4 illustrates a flow diagram of a method of product digitization according to an embodiment herein. At step 402, a system of choice from (i) a rule -based engine or (ii) a machine learning model is determined. At step 404, at least one category of the at least one first feature by the rule-based engine or the at least one second feature by the machine learning model from a plurality of predetermined is categorised by analysing the at least one first feature or the at least one second feature. At step 406, a score of the at least first feature or the at least second feature is determined. At step 408, a highest scoring first feature or a highest scoring second feature is selected for each category from the plurality of predetermined categories. At step 410, a digitalized product is generated based on the feature scores and a user input. At step 412, the digitalized product is deployed on a media platform.

[0037] In an embodiment, steps of product digitization method further includes placing the product on the rotating platform, aligning the product as per the required specifications, execute three dimensional scanning of the product, setting multi-lens camera unit, a lens angle, a product angle, saving keyframes for images and videos, capture at least one of a single angle image, multi-angle images or a video. In an embodiment, the whole process takes 60 to 180 seconds for the product from taking images to deploying the digitalized product on media platform.

[0038] In an embodiment, step of product digitization method Creates new record product for a product to be scanned. The values for the record are initially set to null. Get basic product details like a model, product id, store, etc. This is stored locally in the record as a first set of metadata in dictionary format eg. prod[“id”], prod[“model”]. The product details can be entered by the user either manually (or) read from barcode id and pulled from store database using this id. While User placing the object in the booth, two options along with sub-choices are given:

a) For 3D reconstruction,

i) Pre-defined light settings and camera resolutions are set

ii) Rotation of turn table is initiated

iii) Camera photo capture is triggered at every x seconds, where x is set based on product metadata

iv) All photos are stored in new folder called prodid time stamp.

b) For video recording: i) User is allowed to set the light setting and angle required for video. ii) High resolution video is recorded. Few images are taken for feature extraction. iii) All videos and photos are stored in a new folder called prodid time stamp.

The value prodid time stamp is added to the product metadata. The record itself is then pushed to the remote database. The folder prodid time stamp is pushed to the cloud for further processing and the user can repeat this entire process with a new product record. A batch job is setup in the processing machine which processes products one by one. Database lookup is done to identify the next product scan to be processed (scan_done_flag false). Initial outlier cleanup of the 3D mesh is done automatically based on set borders bl. The bl is calculated based on digitizer size, scan data from the training set and prod metadata. Manual cleaning of 3D mesh done if needed. A quick image comparison of the new product scan is done against scans of products with similar metadata. The result is stored in match per.

If match per > 90% (implies feature extracted from an extremely similar product),

i) Add product to User Display portal

ii) Update scan done flag in the database record for this prod scan to true.

Else, feature extraction is initiated.

i) Add product to User Display portal

ii) List of features needed is pulled from the database 202 based on the product metadata, extracted and added to the new local record created.

iii) This is stored in separate feature record prod feature in the database 202 and linked to prodid timestamp in metadata record.

iv) Update scan done flag in the database 202 record for this prod scan to true.

[0039] Fig. 5 illustrates an exploded view of the product digitalization server 104 of FIG. 1 according to the embodiments herein. The product digitalization server 104 having a memory 502 having a set of computer instructions, a bus 504, a display 506, a speaker 508, and a processor 510 capable of processing a set of instructions to perform any one or more of the methodologies herein, according to an embodiment herein. The processor 510 may also enable digital content to be consumed in the form of video for output via one or more displays 506 or audio for output via speaker and/or earphones 508. The processor 510 may also carry out the methods described herein and in accordance with the embodiments herein. [0040] The embodiments herein can take the form of, an entirely hardware embodiment, an entirely software embodiment or an embodiment including both hardware and software elements. The embodiments that are implemented in software include but are not limited to, firmware, resident software, microcode, etc. Furthermore, the embodiments herein can take the form of a computer program product accessible from a computer-usable or computer-readable medium providing program code for use by or in connection with a computer or any instruction execution system. For the purposes of this description, a computer-usable or computer readable medium can be any apparatus that can comprise, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.

[0041] The medium can be an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system (or apparatus or device) or a propagation medium. Examples of a computer-readable medium include a semiconductor or solid state memory, magnetic tape, a removable computer diskette, a random access memory (RAM), a read-only memory (ROM), a rigid magnetic disk and an optical disk. Current examples of optical disks include compact disk - read only memory (CD-ROM), compact disk - read/write (CD-R/W) and DVD.

[0042] A data processing system suitable for storing and/or executing program code will include at least one processor coupled directly or indirectly to memory elements through a system bus. The memory elements can include local memory employed during actual execution of the program code, bulk storage, and cache memories which provide temporary storage of at least some program code in order to reduce the number of times code must be retrieved from bulk storage during execution.

[0043] Input/output (I/O) devices (including but not limited to keyboards, displays, pointing devices, remote controls, etc.) can be coupled to the system either directly or through intervening I/O controllers. Network adapters may also be coupled to the system to enable the data processing system to become coupled to other data processing systems or remote printers or storage devices through intervening private or public networks. Modems, cable modem and Ethernet cards are just a few of the currently available types of network adapters.

[0044] FIG. 6 illustrates a representative hardware environment for practicing the embodiments herein. This schematic drawing illustrates a hardware configuration of an information handling/computer system in accordance with the embodiments herein. The system comprises at least one processor or central processing unit (CPU) 10. The CPUs 10 are interconnected via system bus 12 to various devices such as a random access memory (RAM) 14, read-only memory (ROM) 16, and an input/output (I/O) adapter 18. The I/O adapter 18 can connect to peripheral devices, such as disk units 11 and tape drives 13, or other program storage devices that are readable by the system. The system can read the inventive instructions on the program storage devices and follow these instructions to execute the methodology of the embodiments herein.

[0045] The system further includes a user interface adapter 19 that connects a keyboard 15, mouse 17, speaker 24, microphone 22, and/or other user interface devices such as a touch screen device (not shown) or a remote control to the bus 12 to gather user input. Additionally, a communication adapter 20 connects the bus 12 to a data processing network 25, and a display adapter 21 connects the bus 12 to a display device 23 which may be embodied as an output device such as a monitor, printer, or transmitter, for example.

[0046] The system reduces the cost of digitization through automation, improves quality of the output though a hybrid recommendation system of camera settings, BG, lighting framing settings. A typical photo-studio and the photographer charges a considerable amount. This cost of creative production is reduced by at least 40%, and the data storage costs are reduced by at least 50% because of the reduced number of media files. In the time taken for digitization, editing and posting into the web server, which conventionally takes around a few hours for 5-10 products, the reduction is at least 50% with the automated system. The system also saves time and cost of digitization using a robotic switching system and an automated camera capture unit. The Hybrid system for feature detection has improved the detection algorithm’s speed and cost for some features by at least 40% along with the machine learning system and reduces the cost of training, model deployment, and training data capture. The system further captures performance feedback from the feature categorizing module 210 to further improve performance by switching strategies of detection from rule -based to machine learning based and vice-versa from performance logs.

[0047] The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope.

Claims

CLAIMS We claim:

1. A system of automating digitization of a product to deploy on a media platform, the system comprising:

a memory that stores a set of instructions; and

a processor that executes the set of instructions and is configured to

generate a media library of a product, wherein the media library is generated with at least one of a single angle image, multi-angle images or videos of the product, wherein at least one of single angle image, multi-angle images or videos of the product are grouped into a plurality of pixel groups based on hue, illumination, and tone;

characterized in that

determine a system of choice for feature extraction from (i) a rule-based engine or (ii) a machine learning model (106), wherein the rule-based engine determines at least one first feature from predetermined features of the product by analyzing the media library at each of the plurality of pixel groups, wherein the predetermined features comprise of at least one of a color a pattern a shape, a dimension, a noise or an unwanted data, a logo, a text, presence or absence of an object, a texture or a type, and wherein the machine learning model (106) identifies the at least one second feature, wherein the machine learning model (106) is trained using a plurality of electronic image data and a plurality of inputs by a user;

determine at least one category of the at least one first feature or the at least one second feature from a plurality of predetermined categories by analyzing the at least one first feature or the at least one second feature;

determine a score of the at least one first feature or the at least one second feature based on an input received from a user or by analyzing social media electronics data;

determine a highest scoring first feature or a highest scoring second feature based on the score for each of the plurality of predetermined categories;

generate a digitalized product by compiling the highest scoring first feature or the highest scoring second feature for each of the plurality of predetermined categories or generate recommendations based on the feature scores of the plurality of categories for the product image; and deploy the digitalized product on the media platform.

2. The system as claimed in claim 1, wherein the processor executed set of instructions are configured to identify meta tags from the at least one of single angle image, multi-angle images, or videos of the product from the media library at the machine learning model (106).

3. The system as claimed in claim 1, wherein the system of choice is determined by analyzing at least one of (a) a cost of computation; (b) an economic projection; (c) a total duration or (d) an expected accuracy.

4. The system as claimed in claim 1, wherein the processor executed set of instructions are configured to receive inputs from a user for feature extraction from the at least one of single angle image, multi-angle images or videos of the product from the media library at the machine learning model (106).

5. The system as claimed in claim 1, wherein the processor executed set of instructions are configured to determine score of the at least one first feature or the at least one second feature based from analyzing social media electronics data for at least one of (i) target audience information, (ii) a product category or (iii) a demographic data.

6. The system as claimed in claim 1, wherein the machine learning model (106) receives the input from the user to train the machine learning model for subsequent outputs wherein the input from the user, if received, weighs more than the machine learning model output.

7. The system as claimed in claim 1, wherein the machine learning module (106) is trained using data from at least one of (i) a pre-existing visual data generated by the system, (ii) a commercial website, (iii) a social media score or (iv) an e-commerce website and a user input.

8. The system as claimed in claim 1, wherein the system further comprises (a) a rotating platform on which the product is placed; (b) a lighting unit that illuminates the product on the rotating platform; (c) a multi- lens camera unit that capture single angle or multi-angle images or videos to generate the media library; and (d) a controller (102) that is communicatively connected to the rotating platform, the camera system, and the lighting unit, wherein the processor executed set of instructions are configured to generate recommendations for the controller (102) to control at least one of (i) at least one of a rotational degree of the rotational platform, wherein the rotating platform rotates along at least one plane in a range of 1 degree to 360 degrees in a clockwise or anti-clockwise direction; a sequence of rotation and a rotation speed, (ii) the multi-lens camera unit for at least one of an exposure, position; focus, zoom, aperture size, a flash time, a shutter speed, angle, frames per second (FPS), a lens resolution, an aspect ratio, or a camera motion, (iii) the lighting unit for at least one of the settings for an hue, an intensity, a direction or a nature for an predetermined interval.

9. The system as claimed in claim 8, wherein the system further comprises a robotic switching arm or at least one degree of freedom articulated arm that is communicatively connected to the controller (102), wherein the processor executed set of instructions are configured to generate recommendations for the controller (102) to control the robotic switching arm or the at least one degree of freedom articulated arm, wherein the robotic switching arm or the at least one degree of freedom articulated arm swaps a plurality of the products in a successive order.

10. A method of automating digitization of a product to deploy on a media platform, wherein the method comprises the steps of :

generating a media library of a product using at least one of a single angle image, multi angle images or videos of the product, wherein at least one of single angle image, multi-angle images or videos of the product are grouped into a plurality of pixel groups based on hue, illumination or tone;

characterized in that

determining a system of choice for feature extraction from (i) a rule-based engine or (ii) a machine learning model (106) wherein, the rule-based engine determines at least one first feature from predetermined features by analyzing the media library at each pixel group wherein the predetermined features comprise of at least one of a color, a pattern, a shape, a dimension, a noise or an unwanted data, a logo, a text, presence or absence of an object, a texture, or a type and wherein the machine learning model (106) identifies the at least one second feature, wherein the machine learning model (106) is trained using a plurality of electronic image data;

determining at least one category of the at least one first feature or the at least one second feature from a plurality of predetermined categories by analyzing the at least one first feature or the at least one second feature;

determining a score of the at least one first feature or the at least one second feature based on input received from a user or from analyzing social media electronics data;

determining a highest scoring first feature or a highest scoring second feature based on the score for each of the plurality of predetermined categories;

generating a digitalized product by compiling the highest scoring first feature or the highest scoring second feature for each of the plurality of predetermined categories or generating recommendations based on the feature scores of the plurality of categories for the product image; and

deploying the digitalized product on the media platform.