ON SIZE

Field of the Invention

[0001] The present invention relates generally to a packaging facility. More particularly, system and method to identify and remove damaged article (e.g., fruit, vegetable) using machine learning based sorting unit.

Background

[0002] 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.

[0003] Industrial progress has directly or indirectly leveraged the world’s economy and has played a critical role in quenching the need of employment. In order to expedite the industrial production, automation of the various operational functions has substantially aided the motive of meeting demands and henceforth, its routine implementation has resulted into hassle-free systems to secure the produce of an industry such as agriculture.

[0004] Generally, fruits/vegetables are stored in a controlled atmosphere (i.e., cold storage) for better preservation. Usually, 8-25 % of harvested fruits/vegetables are not suitable for marketing as these are defected or of substandard quality. Removal of such defective or inferior fruits/vegetables during packaging is primary requirement as storing defective fruits along with otherwise uncontaminated fruits frequently results in the spread of disease and pests. Early identification and removal of defective fruits significantly reduce postharvest disease/pest problems and amplifies quality.

[0005] Industrial products can encompass a variety of articles such as food, beverages, chemicals, pharmaceuticals, petroleum, ceramics, base metals, coal, plastics, rubber, textiles, tobacco, wood and wood products, paper and paper products. Deployment of manual operation is prone to errors and hence can further slowdown the processing of the industrial produce. For example, sorting a myriad of articles of various types will require immense labour and expertise to identify and systematically arrange it in packets or baskets for further processing to trade and commercialize the produce. Therefore, industries are more focusing upon the automation of sorting process in order to galvanize the conventional processing approach.

[0006] The automation of sorting process is further facilitated using advance machines (e.g., shoe sorters) to segregate various products based on different segregation. Deployment of automated object sorting machine can sort articles by their colour, size and texture using microcontroller and sensors and count the accepted ones after sorting. The computer-controlled pallet handling paraphernalia this allows for more well-organized retail, wholesale, and industrial distribution. It is measured as a labour-saving scheme that allows large dimensions to move rapidly through a process, allowing companies to ship or receive higher volumes with minor storage planetary and with less labour disbursement.

[0007] However, the known method of article sorting associated with hazards such as operational malfunctions of the constituting elements of the system, expensive, cause damage to food article etc. Thus, there remains a need for further contributions in this area of technology. More specifically, a need exists in the area of technology for sorting of food article based on size, which can overcome one or more limitations of known solutions. [0008] All publications herein are incorporated by reference to the same extent as if each individual publication or patent application were specifically and individually indicated to be incorporated by reference. Where a definition or use of a term in an incorporated reference is inconsistent or contrary to the definition of that term provided herein, the definition of that term provided herein applies and the definition of that term in the reference does not apply.

[0009] In some embodiments, the numbers expressing quantities of ingredients, properties such as concentration, reaction conditions, and so forth, used to describe and claim certain embodiments of the invention are to be understood as being modified in some instances by the term “about.” Accordingly, in some embodiments, the numerical parameters set forth in the written description and attached claims are approximations that can vary depending upon the desired properties sought to be obtained by a particular embodiment. In some embodiments, the numerical parameters should be construed in light of the number of reported significant digits and by applying ordinary rounding techniques. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of some embodiments of the invention are approximations, the numerical values set forth in the specific examples are reported as precisely as practicable. The numerical values presented in some embodiments of the invention may contain certain errors necessarily resulting from the standard deviation found in their respective testing measurements.

[00010] 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.

[00011] The recitation of ranges of values herein is merely intended to serve as a shorthand method of referring individually to each separate value falling within the range. Unless otherwise indicated herein, each individual 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 with respect to certain embodiments herein is intended merely to better illuminate the invention and does not pose a limitation on the scope of the invention otherwise claimed. No language in the specification should be construed as indicating any non-claimed element essential to the practice of the invention.

[00012] Groupings of alternative elements or embodiments of the invention disclosed herein are not to be construed as limitations. Each group member can be referred to and claimed individually or in any combination with other members of the group or other elements found herein. One or more members of a group can be included in, or deleted from, a group for reasons of convenience and/or patentability. When any such inclusion or deletion occurs, the specification is herein deemed to contain the group as modified thus fulfilling the written description of all Markush groups used in the appended claims.

Ob jects of the Invention

[00013] An object of the present disclosure is to overcome one or more drawbacks associated with conventional mechanisms.

[00014] An objective of proposed disclosure is to reduce manual intervention during sorting of food article.

[00015] An objective of proposed disclosure is to enable high-throughput segregation of waste food articles.

[00016] Another objective of proposed disclosure is to amplify the production process. [00017] An objective of proposed disclosure is to provide cost-effective, reliable and automated sorting facility.

Summary

[00018] The present invention relates generally to a packaging facility. More particularly, system and method to identify and remove damaged article (e.g., fruit, vegetable) using machine learning based sorting unit.

[00019] In another aspect, the present disclosure provides a A system to sort one or more articles, the system comprises: a conveyor unit is arranged to receive the one or more articles, wherein the conveyor unit comprises: a corrugated sheet that comprises at least three depressions, wherein the each of the depression is arranged to create a queue comprising the one or more articles; a roller conveyor is arranged at a downstream end of the corrugated sheet, wherein the roller conveyor comprises the rotatable roller members, which are arranged to drive the received one or more articles in a conveying direction, wherein the each roller member comprises at least two spaced apart ring members to maintain the created queues; an image sensor is arranged to capture an image of the each of received articles, which are present on the roller conveyor; a separation unit is arranged at a downstream end of the roller conveyor, wherein the separation unit comprises: a bin arrangement; at least three flaps, wherein the each of the flap is arranged to transform between a first position and a second position, wherein: the first position allows passage of the one or more articles over the flap; and the second position allows passage of the one or more articles into the bin arrangement; a motor is arranged to transform, individually, each of the flap between the first position and the second position; and a control unit is configured to: analyse the captured image to identify a damaged article, based on a machine learning model; and activate, the motor to transform the flap from the first position to the second position, to enable transfer of the identified damaged article into the bin arrangement.

[00020] In an aspect, the present disclosure provides a method for sorting one or more articles, the method comprises: receiving, at a conveyor unit, the one or more articles, wherein the conveyor unit comprises: a corrugated sheet comprises at least three depressions, wherein the each of the depression is arranged to create a queue comprising the one or more articles; a roller conveyor is arranged at a downstream end of the corrugated sheet, wherein the roller conveyor comprises the rotatable roller members, which are arranged to drive the received one or more articles in a conveying direction, wherein each roller member comprises at least three spaced apart ring members to maintain the created queues; capturing, through an image sensor, an image of each of the received articles, which are present on the roller conveyor; receiving, at a control unit, the captured image to identify one or more damaged articles, based on a machine learning model; and activating, a motor to transom each of the flap of a transfer unit, from a first position to a second position to allow passage of the one or more articles into a bin arrangement, upon identification of damaged article.

[00021] 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

[00022] Fig 1 illustrates an exemplary architecture of a system to sort one or more articles, in accordance with embodiments of the present disclosure. [00023] FIG. 2 illustrates an exemplary functional module to sort one or more agriculture -based food items (e.g., vegetable, fruit etc.), in accordance with embodiments of the present disclosure.

[00024] Fig 3 illustrates exemplary relationship between the corrugated sheet and roller conveyor, in accordance with embodiment of present disclosure.

[00025] FIG. 4 represents exemplary steps for creating a packaged product, in accordance with embodiments of the present disclosure.

Detailed Description

[00026] The following discussion provides many example embodiments of the inventive subject matter. Although each embodiment represents a single combination of inventive elements, the inventive subject matter is considered to include all possible combinations of the disclosed elements. Thus, if one embodiment comprises elements A, B, and C, and a second embodiment comprises elements B and D, then the inventive subject matter is also considered to include other remaining combinations of A, B, C, or D, even if not explicitly disclosed.

[00027] The present invention relates generally to a packaging facility. More particularly, system and method to identify and remove damaged article (e.g., fruit, vegetable) using machine learning based sorting unit.

[00028] Fig 1 illustrates an exemplary architecture of a system 100 to sort one or more articles 114, in accordance with embodiments of the present disclosure. According to the illustrations made in the architecture of a system 100 to sort one or more articles 114, wherein the term “article” can relate to particular item or object, which can exemplarily include but not restricted to an edible item (a vegetable, a fruit, an egg), non-edible item (naphthalene balls), a package of edible items and non edible items and any other known forms of articles 114. Sorting herein can exemplarily relate to systematic arrangement of one or more articles. For example, one or more vegetables can be sorted, according to their weight, size, texture and any other sorting criteria used thereof.

[00029] According to illustrations made in figure 1, in an exemplary embodiment, the system 100 can comprise a conveyor unit 102, an image sensor 104, a separation unit 106, a motor 108, a control unit 110, a communication network 112 and other known elements of sorting unit. A person ordinarily skilled in art would appreciate that the aforementioned elements of the system 100 can be operationally connected to each other, over the communication network 112.

[00030] In an exemplary embodiment, the conveyor unit 102 can be arranged to receive one or more articles 114, wherein the conveyor unit 102 can comprise a corrugated sheet 102a and a roller conveyor 102b. The conveyor unit can also be comprised, a wire network, which can be arranged to maintain separation of the created queues. The term “corrugated” used herein can relate to, but not limited to ridged, furrowed, channelled, grooved and other known examples thereof.

[00031] The corrugated sheet 102a can comprise at least three depressions, wherein the each of the depression can be arranged to create a queue comprising one or more articles 114. The corrugated sheet 102a can comprise depression (i.e., valley region), which can be formed by two crests (e.g., peak of corrugated surface). The term “queue” can relate to, but not restricted to a line, a sequence, a succession, a stream and other known examples thereof. The corrugated sheet 102a can be arranged a pre-set angle with the roller conveyor 102b (such as 30°, 45°). For example, apples and oranges as the articles 114 can be arranged in a queue, on or more depressions of the corrugated sheet 102a, which can be set at an inclination angle of 45° with the roller conveyor 102b such that each specific article 114 can be separated from each other and aligned or streamlined, one after the other, forming a queue, in accordance to the embodiments of present disclosure. A person ordinarily skilled would appreciate that two separate articles 114 can be arranged in two different queues, thus can be segregated from each other (a queue of one or more oranges and a queue of one or more apples). One or more articles 114 can roll or slide down on the roller conveyor 102b from the corrugated sheet 102a, due to pre-set angle (inclination). The person ordinarily skill in the art can select the corrugated sheet 102a with higher number of depressions such as 5-15, 6-16, 4-20 and like that. The higher number of depressions can enable high throughput sorting of the articles 114.

[00032] The roller conveyor 102b can be arranged at a downstream end of the corrugated sheet 102a, wherein the roller conveyor 102b can comprise a plurality of rotatable roller members, which can be arranged to drive the received one or more articles in a conveying direction. Each of rotatable roller members can comprise at least two spaced apart arranged ring members which can be arranged to align and maintain the created queues. Each ring member can be positioned in a manner such that all the ring members can form a common axis with the respective crest of corrugated sheet 102a. Thus, the depression of the corrugated sheet 102 can be present at a centre of the two successive ring members. The ring members can prevent intermixing of the food articles of different queues. Thus, customized roller members can assist efficient removal of the damaged articles 114. The roller conveyor 102b can be used herein can exemplarily be, but not restricted to a gravity roller conveyor, belt driven roller conveyor, chain driven roller conveyor, vibrator conveyor, vibrator feeder, oscillating conveyor vibrator, heavy duty vibrator conveyor and any other known variants thereof. The conveying direction herein can exemplarily relate to a direction of movements of rotatable roller members. For example, the received one or more article 114 can exemplarily be moved in a forward or backward direction depending upon the anticlockwise or clockwise movements of rotatable roller members, respectively.

[00033] The rotatable roller members can be arranged parallel or transversal manner in the conveyor unit 102, depending upon a shape of the roller conveyor 102b. The conveyor unit 102 can be driven by an AC induction motor in order to rotate the rotatable roller members in forward or backward conveying direction, according the embodiments of the present disclosure. The conveyor unit 102 can be arranged with an exemplary vibrator such as vibrator feeder, oscillating conveyor vibrator, heavy duty vibrator and any other known variants of vibrators used in the conveyor unit 102, wherein the vibrator can unscramble one or more articles 114, from each other and also remove dirt particle/unwanted shells.

[00034] In an exemplary embodiment, the shape of the roller conveyor 102b can be, but not restricted to a linear, curvilinear and other known shapes which can be deployed to convey the articles 114 in the conveying direction. The roller conveyor 102b can exemplarily be divided into a first section and a second section, which can be 2-10 times larger (i.e., length wise) than the first section. Alternatively, the second section can be 5-15 times larger, 8-12 times larger, and 12-20 times larger than the first section. It would be appreciated that the person ordinarily skill in the art can optimize length of the first section and second section to optimize efficiency of the system 100. The rotatable roller members of the first section can be arranged at an equal distance from each other. The rotatable roller members of the second section 106b of the roller conveyor unit 106 can be arranged to grade the received one or more articles 114 according to size. The distance between the rotatable roller members of the second section can be progressively increased at a rate of 5-20% in the conveying direction. For example, the rate of progressive increment in the space between the roller members can be selected from 2-25%, 8-35%, 5-6%, 7- 12%, 9-18%, 10-17%, 6-10%, 10-15%, and 15-20%,

4%, 8%, 12%, 16%, 20% and 24%, preferentially in the range of 5-20% in order to sort one or more articles 114 according to their size. The first section of the roller conveyor 102b can be deployed to align or queue one or more articles 114 and the second section can be deployed to grade or sort one or more articles 114.

[00035] In an exemplary embodiment, the image sensor 104 can be arranged to capture one or more images of each of received articles 114, which can be present on the roller conveyor 102b. The image sensor 104 can be selected from, but not restricted to a charged coupled device, a global or rolling shutter, complementary metal oxide semiconductor image sensor, a colour or monochromatic and other known variants of images sensors. The captured one or more images can exemplary be dependent on resolution, frame rate, pixel size, sensor format and other known attributes of the image sensor 104. A person ordinarily skilled in art would appreciate that the image sensor 104 can capture the images of each article 114 in one, two, three or multidimensional orientations. The image sensor 104 can exemplarily be configured in multiple ways such as an arrangement integrated with the conveyor unit 102 or suspended through a stretchable wire hovering over the conveyor unit 102 or any other possible configurations in order to capture one or more images of the articles 114.

[00036] In an exemplary embodiment, independent image sensor 104 can be arranged for each of the created queue. This independent image sensor 104 can enable ease of image analysis.

[00037] In an exemplary embodiment, the separation unit 106 can be arranged at a downstream end of the roller conveyor 102b, wherein the separation unit can comprise a bin arrangement 106b and at least three flaps 106al, 106a2, and 106a3, respectively. The flaps 106al, 106a2, and 106a3 can be arranged to transform between a first position, which can allow passage of the one or more articles 114 over the flap and a second position, which can allow passage of the one or more article into the bin arrangement. For example, the flaps 106al, 106a2, and 106a3 can transform between a “to and fro” (like a pendulum) position or “up and down” or pop-in or pop-out position to allow a passage of the one or more articles 114 or removal of the one or more articles 114 (which identified as damaged) from the conveyor 102b.

[00038] In an embodiment, each flap, either individually or collectively, can move in plurality of orientations such as back and forth or up and down, perpendicular or parallel to the rotatable roller members. Hence a plurality of other operations can be performed such as inspection, aggregation, unscrambling, segregation, or removal of damaged/waste article 114 into the bin arrangement 106b. The damaged articles 114 can exemplarily be identified by a disfiguration, rotten, sub-standard, scratches, discoloration and other known causes of damage.

[00039] Referring to the separation unit 106 can also be arranged to unit to transfer the one or more articles 114 which can remain on the roller conveyor 102b, after the removal of the one or more damaged articles 114, toward a packaging unit or other downstream transfer unit such as ball transfer unit, a belt transfer unit or any other variants thereof, which can enable transfer of the articles 114 from conveyor 102b to a packaging unit to prepare package.

[00040] Referring to the bin arrangement 106b, the exemplary triplicate of bins can be arranged beneath the roller conveyor 102b. Transfer of the article 114 to bin arrangement 106b can depend on position of flaps (i.e., flaps 106al, 106a2, and 106a3), which can be controlled through the motor 108.

[00041] In an exemplary embodiment, the motor 108 can be arranged to transform, individually, each of the flaps 106al, 106a2, and 106a3 between the first position and the second position. The motor 108 can be selected from a DC shunt motor, AC synchronous motor, universal motor, brushless motor or any other known variants thereof. For example, the motor 108 can cause the flaps 106al, 106a2, and 106a3 to transform between pop-in and pop out position or to and fro position, according to the embodiments of present disclosure.

[00042] In an exemplary embodiment, the control unit 110 can be arranged to analyse one or captured images to identify a damaged article, based on a machine learning model. The control unit 110 can also cause the activation of the motor to transform the flap from the first position to the second position, to enable transfer of the identified damaged article 114 into the bin arrangement 106b. The control unit 110 can exemplarily comprise a storage device (e.g. RAM, ROM or other known form of electronic data storage medium) and a microprocessor (e.g., CPU, ALU etc).

[00043] Referring to the exemplary microprocessor of the control unit 110 which can perform a plurality of functional operations to identify one or more damaged articles 114. The storage device can comprise an exemplary image database comprising one or more images of the damaged article 114 (which can be discarded) and pre-stored sorting criteria. The functional operations performed by microprocessor cannot be restricted to examples such as image processing (noise removal, line detection, background removal), extracting the critical information from the received one or more images of the articles 114, identifying the one or more damaged articles 114 by matching the critical information extracted from the received one or more images of the articles 114 and matching it with the pre stored sorting criteria in the database, causing the exemplary removal of one or more damaged articles 114.

[00044] Referring to the exemplary embodiment, the microprocessor of the control unit 110 which can split images of the image database into a training set (-75-80 %) and a test set (-20-25%). The training set can be used to develop one or more machine learning based model to identify/predict the damaged article 114, based on analysis of captured images. The performance each developed machine learning model can be evaluated by using the test set. The mathematical model having higher classification ability (e.g., lower false prediction) can be used to identify the damaged articles 114. In exemplary embodiment, the processor can extract one or more features (e.g., Harris Comer Detection, Shi-Tomasi Corner Detector, Scale- Invariant Feature Transform (SIFT), Speeded-Up Robust Features (SURF) Features from Accelerated Segment Test (FAST), Binary Robust Independent Elementary Features (BRIEF), Oriented FAST and Rotated BRIEF (ORB), etc.), which can be used to develop the machine learning based model.

[00045] The microprocessor can analyse image of each article 114 of each queue, using previously trained machine learning based model, to identify the damaged article 114. On identification of the damaged articles (which present in respected queue), the control unit can activate the motor 108 to transform the respected flap (from first position to second position) to transfer the identified damaged article into the bin arrangement 106b. Further, motor can retransform the respected flap from second position to the first position. Thus, repeated transformation of flap member can enable efficient removal of the damaged article 114. member

[00046] FIG. 2 illustrates an exemplary functional unit 200 to sort one or more agriculture-based food items (e.g., vegetable, fruit etc.), in accordance with embodiments of the present disclosure. These functional units (e.g., computer executable instructions) can be executed by processor/microprocessor of the control unit 110. As illustrated, the functional unit 200 can comprise a data receive unit 202, an image analysis unit 204, a damaged article identification unit 206, and a motor activation unit 208.

[00047] In an embodiment, the data receive unit 202 can receive the captured one or more images of each article 114, from the image sensor 104, through an exemplary communication network 112 (e.g., WIFI, Bluetooth, telecommunication network, bus etc.). The data receive unit 202 can receive different commands such as an exemplary static or dynamic position of the bin arrangement 106b beneath the roller conveyor 102b which can be used to collect specific kind of article 114, activation/deactivation command, and the like.

[00048] In an embodiment, the image analysis unit 204 can perform various image processing steps such as background removal, noise removal, resolution alteration, object detection, feature extraction and other known image processing steps. The image analysis unit 204 can identify location of each article 114.

[00049] In another embodiment, the damaged article identification unit 206 can deploy machine learning based algorithm (e.g., SVM, CNN, computer vision, deep learning, genetic algorithm, etc.) to generate prediction/classification models, using an image database. The damaged article identification unit 206 can split the image database into a test set (-60-80% data) and a training set (-20-40%). The training set can be used to generate prediction/classification models, which can be evaluated using test set. A best model (which exhibits highest efficiency) can be used to identify the damaged articles 114.

[00050] In another embodiment, the motor activation unit 208 can activate the motor 108 to enable transfer of all the articles 114, which can transform the flaps 106al, 106a2 and 106a3 of the separation unit 106 between first (allowing passage of the one or more articles over the flap) and second position (allowing passage of the one or more article into the bin arrangement 106b). Selective activation of motor 108 can result in improved efficiency of classification/grading of received articles 102, by reducing probability of transfer of the damaged article 114.

[00051] The system 100 can utilize Internet of things (loT) based smart sensing technology so that system 100 can be loTified. Further, the system 100 can also be used from a single remote location to run multiple sorting units, which may be arranged geographically apart.

[00052] Fig 3 illustrates exemplary relationship between the corrugated sheet 102a and roller conveyor 102b, in accordance with embodiment of present disclosure. For ease of depiction, only one rotatable roller member is shown with reference to the corrugated sheet 102a. As illustrated, the corrugated sheet may comprises plurality of depressions (i.e., valley region), wherein the each of the depression can be formed in between two crests (e.g., peak of corrugated surface). Each rotatable roller member of roller conveyor 102b can comprise number of ring members. The number of ring member can be one less than total number of depressions. Each ring member can be positioned in a manner such that all the ring members can form a common axis with the crest of corrugated sheet 102a. Thus, the depression of the corrugated sheet 102 can be present at centre of the two successive ring members. The wire network can additionally configured to maintain separation of the created queues. The wire network can be arranged in a fashion that either of ring member, the rotatable roller member or corrugated sheet 102 cannot touch with the wire network.

[00053] FIG. 3 represents exemplary steps 400 for creating a packaged product, in accordance with embodiments of the present disclosure. The method includes the steps of: at step (402) receiving, at a conveyor unit, one or more articles, wherein the conveyor unit comprises: a corrugated sheet comprises at least three depressions, wherein the each of the depression is arranged to create a queue comprising one or more articles; a roller conveyor is arranged at a downstream end of the corrugated sheet, wherein the roller conveyor comprises the rotatable roller members, which are arranged to drive the received one or more articles in a conveying direction, wherein each roller member comprises at least three spaced apart arranged ring members which arranged to separate the created queues; at step (404), capturing, through an image sensor, an image of each of received articles, which are present on the roller conveyor; at step (406), receiving, at a control unit, the captured image to identify one or more damaged articles; and at step (406), activating, a motor to transom each of the flap of a transfer unit, from a first position to a second position to allow passage of the one or more article into a bin arrangement, upon identification of damaged article

[00054] Throughout the present disclosure, the term ‘processing means’ or ‘microprocessor’ or ‘processor’ or ‘processors’ includes, but is not limited to, a microprocessor, a microcontroller, a complex instruction set computing (CISC) microprocessor, a reduced instruction set (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, or any other type of processing circuit.

[00055] In an aspect, any or a combination of machine learning mechanisms such as decision tree learning, Bayesian network, deep learning, random forest, supervised vector machines, reinforcement learning, prediction models, Statistical Algorithms, Classification, Logistic Regression, Support Vector Machines, Linear Discriminant Analysis, K-Nearest Neighbours, Decision Trees, Random Forests, Regression, Linear Regression, Support Vector Regression, Logistic Regression, Ridge Regression, Partial Least-Squares Regression, Non- Linear Regression, Clustering, Hierarchical Clustering - Agglomerative, Hierarchical Clustering - Divisive, K-Means Clustering, K-Nearest Neighbours Clustering, EM (Expectation Maximization) Clustering, Principal Components Analysis Clustering (PCA), Dimensionality Reduction, Non-Negative Matrix Factorization (NMF), Kernel PCA, Linear Discriminant Analysis (LDA), Generalized Discriminant Analysis (kernel trick again), Ensemble Algorithms, Deep Learning, Reinforcement Learning, AutoML (Bonus) and the like can be employed to learn sensor/hardware components. [00056] 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.

[00057] 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 of the embodiments as described herein.

[00058] It should be apparent to those skilled in the art that many more modifications besides those already described are possible without departing from the inventive concepts herein. The inventive subject matter, therefore, is not to be restricted except in the spirit of the appended claims. Moreover, in interpreting both the specification and the claims, all terms should be interpreted in the broadest possible manner consistent with the context. In particular, the terms “comprises” and “comprising” should be interpreted as referring to elements, components, or steps in a non-exclusive manner, indicating that the referenced elements, components, or steps may be present, or utilized, or combined with other elements, components, or steps that are not expressly referenced. Where the specification claims refer to at least one of something selected from the group consisting of A, B, C . . . . and N, the text should be interpreted as requiring only one element from the group, not A plus N, or B plus N, etc.

Advantages of the Invention

[00059] An advantage of the present disclosure is to overcome one or more drawbacks associated with conventional mechanisms.

[00060] An advantage of proposed disclosure is to reduce manual intervention during sorting of food article.

[00061] An advantage of proposed disclosure is to enable high-throughput segregation of waste food articles.

[00062] Another advantage of proposed disclosure is to amplify the production process.

[00063] An advantage of proposed disclosure is to provide cost-effective, reliable and automated sorting facility.