AN INTEGRATED SYSTEM FOR SMART SHRIMP GRADING AND SORTING

Abstract

ABSTRACT AN INTEGRATED SYSTEM FOR SMART SHRIMP GRADING AND SORTING The invention relates to an automated shrimp grading and sorting system (100) designed to enhance accuracy and efficiency in seafood processing. The system includes a feeder tank (101) for shrimp intake, a conveyor belt (102) for transportation, a drying unit (103), and a singulation unit (104) to ensure individual shrimp processing. Key components include a vision unit (204) with a camera (105) and infrared sensor for image capture and foreign object detection, load cells (106) for weight measurement, and ultrasonic sensors (107) for precise tracking. A controller unit (201) processes data from these sensors and coordinates real-time grading and sorting based on size, weight, and quality, using solenoid-controlled pneumatic pumps (108) to direct shrimp into designated sorting baskets (109). Additionally, a pH sensor in the feeder tank monitors water quality, while data analytics capabilities support inventory and quality management. This system provides a streamlined, accurate, and high-throughput solution for seafood grading and sorting.

Specification

Description:F O R M 2

THE PATENT ACT, 1970
(39 of 1970)
&
THE PATENTS RULES, 2003

COMPLETE SPECIFICATION
(See section 10 and rule 13)



Title of Invention:
"AN INTEGRATED SYSTEM FOR SMART SHRIMP GRADING AND SORTING"


Applicant: RIKSHANA TECHNOLOGIES PRIVATE LIMITED
Nationality: INDIAN
Address: 11086 Prestige Lakeside, Habitat, Varthur Hobli, Gunjur, Bangalore North, Bangalore- 560087, Karnataka



The following specification particularly describes the invention and the manner in which it is to be performed:

FIELD OF THE INVENTION
The present invention relates to the field of automated seafood processing, with a particular focus on the grading and sorting of shrimp. This invention leverages an integration of mechanical systems, advanced sensors, imaging technology, and sophisticated software algorithms, including artificial intelligence (AI) and machine learning (ML), to automate shrimp sorting by weight, size, condition, and other physical attributes.

BACKGROUND OF THE INVENTION
In the shrimp processing industry, grading, sorting, and quality control present substantial challenges due to the natural variability in shrimp size, shape, color, and other distinguishing characteristics. This inherent variability complicates the standardization of grading criteria across shrimp batches, resulting in frequent errors, inconsistencies, and increased rejection rates for shrimp that may still meet specific quality standards. Additionally, physical irregularities such as discoloration, deformities, and shell damage can significantly affect shrimp marketability and consumer acceptance. As a result, shrimp processors often experience disruptions in production efficiency, non-uniform product quality, and economic losses due to high rejection rates.
Beyond size and appearance inconsistencies, processors face the added challenge of meeting stringent quality standards and regulatory requirements enforced by domestic and international markets. These standards define acceptable parameters, including size ranges, appearance criteria, and freshness indicators. Non-compliance with these regulations can result in rejected shipments, loss of market access, and reputational damage. Compounded by the environmental and ethical concerns surrounding waste generated from rejected shrimp, these industry challenges highlight the need for more precise, efficient, and comprehensive grading solutions.
Despite efforts to address grading issues, existing technologies in shrimp processing lack the capabilities to comprehensively handle the full range of quality and grading requirements:

Chinese patent application publication no. CN112841099A, discloses a detection apparatus that uses image analysis to assess shrimp head pathology. Although capable of identifying specific health conditions, this apparatus does not grade or sort shrimp based on quality parameters such as size or weight. As a result, size-discrepant shrimp are often rejected even after processing, leading to waste and inefficiencies.
Chinese patent application publication no. CN108765448A, discloses a method employing image processing techniques, including the TV-L1 model for shrimp seedling counting and enhancement, but lacks the capability to perform grading and sorting based on size, weight, or other quality criteria, limiting its utility in comprehensive shrimp processing.
PCT patent application publication no. WO2017221259A1, discloses a pattern recognition system that identifies Indian prawn species using image segmentation. However, it does not provide a solution for grading and sorting shrimp based on quality metrics like size, weight, or condition, which are crucial for industrial processing requirements.
U.S. patent no. 9,886,752, discloses use of image-based weight approximation to estimate shrimp weight but lacks a direct and precise weight measurement mechanism. In contrast, direct load cell measurements offer more reliable weight data for grading. Moreover, this disclosure does not account for disease detection, which is essential in preventing the spread of viral, bacterial, and fungal infections. Additionally, it does not extend its functionality to peeled or deveined shrimp.
Taiwan patent no. TW I801911 B, describes an underwater biometric identification system for aquatic organisms through image capture and feature extraction, yet it does not address industrial grading or sorting of shrimp according to quality parameters.
Therefore the review of prior art disclosures outlines notable limitations in the existing technologies for shrimp shorting or grading, such as:
- Limited Quality Metrics: Most prior art focuses on specific aspects, such as health assessment or species identification, without providing comprehensive grading capabilities based on weight, size, or condition.
- Lack of Disease Detection: None of the reviewed systems offer mechanisms for predicting or detecting common shrimp diseases such as black spot, yellow head, white spot, or HPV, which are critical for quality control and regulatory compliance.
- Inefficient Weight Measurement: Image-based weight approximation methods lack the precision of direct weight measurement via load cells, which is essential for accurate grading.
- Incomplete Processing Capabilities: Existing systems do not address grading for both head-on and headless shrimp, nor do they accommodate peeled and deveined shrimp, which limits their applicability in modern processing operations.
- Insufficient Data Reporting and Analytics: The prior art lacks mechanisms for comprehensive data collection, grading analysis, and predictive analytics, which are essential for optimizing processing operations and meeting industry standards.
Moreover, shrimp processors must comply with stringent quality standards and regulatory requirements imposed by both domestic and international markets. These regulations often specify the acceptable size ranges, appearance criteria, and freshness indicators that shrimp must meet to be suitable for sale. Non-compliance with these standards can lead to rejected shipments, loss of market access, and reputational damage for shrimp producers. Additionally, shrimp that are rejected after being processed result in unnecessary waste, further exacerbating environmental and ethical concerns.
Given these persistent challenges, there is a clear need for an advanced shrimp grading and sorting system capable of addressing the full spectrum of quality parameters, including size, weight, condition, and disease detection. The present invention fulfils this need by providing an integrated shrimp grading and sorting system that offers comprehensive grading based inherent variability in shrimp size, shape, and quality but also ensures compliance with industry standards.
OBJECT OF THE INVENTION
The primary object of this invention is to provide a fully automated grading and sorting system that significantly reduces human intervention, thereby improving efficiency, accuracy, and consistency in shrimp processing.
Another object of the invention is to achieve accurate shrimp grading through direct weight measurement using advanced load cell sensors, ensuring precise sorting that minimizes errors associated with traditional image-based weight approximation methods.
Yet another object of the invention is to incorporate high-resolution imaging and artificial intelligence (AI) technologies that analyze shrimp characteristics, including size, color, texture, and physical abnormalities, allowing for comprehensive quality assessment based on predefined grading standards.
A further object of the invention is to enable early and accurate detection of common shrimp diseases, such as black spot, yellow head, white spot, and HPV, using image processing and AI algorithms, thus ensuring shrimp health and compliance with regulatory standards.
Another object of the invention is to design a versatile system capable of processing different types of shrimp, including head-on, headless, peeled, and deveined shrimp, for broad functionality across various processing stages.
A further object of the invention is to generate detailed reports on grading, quality metrics, and inventory management that support shrimp processors in business forecasting, inventory control, and strategic pricing, thereby enhancing operational decision-making.
Yet another object of the invention is to address variability in shrimp batches by reducing rejections due to inconsistencies in size, shape, or color, ultimately leading to a more sustainable, waste-reduced approach in shrimp processing.
Further object of the invention is to improve overall processing speed and throughput, making shrimp grading and sorting more profitable by reducing manual labor, improving uniformity, and ensuring compliance with industry standards.
Another object is to integrate a central control unit with a PCB board and specialized software that allows for easy system operation, monitoring, and maintenance, offering shrimp processors a user-friendly and reliable solution.
The above objectives collectively address the primary challenges in shrimp processing and present a robust solution that enhances efficiency, quality control, and sustainability in the seafood industry.

SUMMARY OF THE INVENTION
The present invention relates to a Smart Shrimp Grading and Sorting System, an advanced solution for the automated grading, sorting, and quality assessment of shrimp in seafood processing facilities. It is designed to enhance efficiency and minimize human intervention, this system integrates a combination of high-resolution imaging, artificial intelligence (AI), machine learning (ML), and sensor-based technology to deliver accurate and consistent grading based on various parameters such as weight, size, color, texture, and overall quality.
This grading and sorting system features a robust conveyor belt mechanism that transports shrimp through multiple processing stages. High-resolution cameras and load cell sensors collect data for image analysis and precise weight measurement. Using an onboard central control unit powered by a custom PCB board, the system employs AI and ML algorithms to interpret this data, classifying shrimp according to predefined grading criteria. This technology addresses prevalent challenges in the shrimp industry, including variability in size, color, shape, and quality. Furthermore, it detects physical abnormalities and common diseases, enhancing product uniformity and compliance with market standards.
With comprehensive data reporting capabilities, the system supports shrimp processors in business forecasting, inventory management, and quality control. By automating the grading and sorting process, the Smart Shrimp Grading and Sorting System achieves significant improvements in speed, accuracy, and sustainability, presenting an innovative and scalable solution to meet the demands of global shrimp processing operations.

BRIEF DESCRIPTION OF THE DRAWING:
The invention will be better understood and objects other than those set forth above will become apparent when consideration is given to the annexed drawings wherein:
Fig. 1: Shows system overview of integrated system (100) for smart shrimp grading and sorting with various mechanical components, sensors, actuators, control unit and depicts the flow of the system.
Fig. 2: Shows the block diagram (200) of different units and their connected with the controller unit to perform various tasks for integrated shrimp grading and sorting.

DETAILED DESCRIPTION OF THE INVENTION
Various exemplary embodiments of the present disclosure are described herein below to enable a person of ordinary skill in the art to make and use the present disclosure.
Unless otherwise defined, all the technical terms used herein have the same meaning as commonly understood by one having ordinary skill in the art to which this disclosure belongs.
The terms "comprise" or "comprises" or "comprising", as used throughout this specification and the claims, are used in a non-exclusive sense, except where the context requires otherwise, such that recitation of items in a list is not to the exclusion of other like items that can be substituted or added to the listed items.
The terms "device" or "means" or "product", as used throughout this specification is used interchangeably, and refers to the stirrup making mandrel according to the present invention.
The terms "about", as used throughout this specification is used in front of all numbers expressing quantities of ingredients, reaction conditions, and other properties or parameters used in the specification and claims are to be understood as being modified in all instances by the term "about." Accordingly, unless otherwise indicated, it should be understood that the numerical parameters set forth in the following specification and attached claims are approximations. At the very least, and not as an attempt to limit the application of the doctrine of equivalents to the scope of the claims, numerical parameters should be read in light of the number of reported significant digits and the application of ordinary rounding techniques. For example, the term "about" can encompass variations of ±10%, ± 5%, ± 2%, ± 1%, ± 0.5%, or ± 0.1% of the numerical value of the number which the term "about" modifies.
The term "sorting," as used herein throughout the specification, refers to the systematic classification of shrimp based on distinct physical attributes such as size, weight, shape, and visible quality characteristics. The sorting process uses high-resolution imaging and sensor-based technologies to capture data on each shrimp passing through the conveyor. This data is processed to group shrimp according to predefined categories, ensuring consistent size, weight distribution, and appearance across batches. Sorting is thus a foundational step in organizing shrimp into separate classes, making downstream processing, packaging, and distribution more efficient and uniform.
The term "grading," as used herein throughout the specification, refers to the assessment and classification of shrimp based on quality parameters that determine their market value, safety, and suitability for consumer consumption. This process includes a detailed evaluation of factors such as size, color, texture, weight, and the presence of any physical or health-related abnormalities (e.g., discoloration, shell damage, or disease indicators like black spots or white spots). Grading in this invention is supported by artificial intelligence (AI) and machine learning (ML) algorithms, which analyze sensor data and images to ensure compliance with industry standards and customer requirements. The grading process enables accurate quality assessment and consistent product quality, reducing waste and rejection rates while enhancing the economic value of each batch.
The present invention, a Smart Shrimp Grading and Sorting System, provides a fully automated solution to grade and sort shrimp with minimal human intervention. The system is designed to handle various types of shrimp, both head-on and headless, and operates efficiently across different stages of the processing workflow. It combines mechanical, optical, and electronic components, enhanced by advanced AI and ML algorithms, to deliver precision in classifying shrimp by size, weight, and quality attributes. This broad embodiment covers the fundamental architecture and integrated approach of the invention, aiming to optimize processing speed, reduce waste, and increase quality uniformity.
In one embodiment, the system focuses on high-resolution imaging for quality assessment, specifically targeting visible shrimp characteristics such as color, shell condition, and size uniformity. In another limited embodiment, the system is tailored for use in compliance with specific regulatory standards, ensuring that grading parameters align with industry-required quality and size specifications.
In one aspect of the above embodiment the system may be optimized for high-throughput sorting, applicable in environments where large volumes of shrimp need to be processed rapidly, maintaining a consistent flow without compromising accuracy.
Some of the preferred embodiments and aspects by component and functionality are discussed herein below as:
In one embodiment the system according to the present invention comprises a conveyor belt designed to transport shrimp smoothly and efficiently through the grading and sorting stages. The belt's material is selected for its durability and resistance to moisture, supporting long-term use in seafood processing environments. It operates at a variable speed to accommodate different processing rates.
In one aspect of the above embodiment the belt speed adjusts automatically based on real-time feedback from the imaging and weighing systems, optimizing throughput for shrimp of varying sizes and densities.
In one aspect of the above embodiment the conveyor belt moves shrimp from the initial loading point to various inspection stations, where they undergo imaging, data collection, weighing sensor, IR sensor, moisture sensor, temperature sensor, grading & sorting.
In another aspect, the conveyor includes dividers that guide shrimp into single-file lines to ensure accurate imaging and weighing.
In another embodiment the system incorporates an imaging system comprising high-resolution cameras positioned above and below the conveyor to capture detailed images of each shrimp from multiple angles. These images are processed in real-time to assess parameters such as size, color, shape, and shell condition.
In a related aspect, the imaging system includes infrared or multispectral cameras to detect sub-surface features, enhancing accuracy in identifying abnormalities or early signs of disease.
In another aspect, lighting conditions are automatically adjusted based on shrimp type, ensuring consistent image quality in various processing environments.
In yet another embodiment the system includes a sensor-based weight measurement comprising load cells placed beneath the conveyor measure the weight of each shrimp, providing a critical input for the grading process. The system can differentiate shrimp weights within precise tolerances, ensuring reliable classification.
In a narrower aspect, the system uses a series of miniaturized load cells spaced at intervals to measure shrimp weights even when they vary significantly in size. Additionally, weight data is cross-validated with image-based size estimates, minimizing discrepancies in the grading process.
In one embodiment the system according to the present invention employs AI and ML algorithms that analyze imaging and sensor data to determine the quality grade of each shrimp. The algorithms are trained on extensive datasets to ensure accuracy in recognizing physical characteristics and abnormalities.
In one aspect, the ML models are customized to recognize specific shrimp varieties and associated quality traits, allowing for precise grading based on size, weight, and visual quality criteria.
In yet another aspect the system also includes algorithms for disease prediction, detecting conditions such as black spots or white spots, which trigger automated removal from the sorting line.
In one embodiment the present invention comprises AI-powered image analysis module to detect diseases and irregularities in the shrimp, such as discoloration, shell deformities, or lesions. The module assesses these characteristics to categorize shrimp based on quality standards, meeting both domestic and international regulatory requirements.
In one aspect, the disease detection system includes a database of known shrimp diseases and uses pattern recognition to identify these conditions accurately.
In another related aspect, detected diseases are flagged in the data report, and the shrimp are automatically directed to a rejection channel to maintain quality consistency.
In another embodiment according to the present invention the control unit comprises a PCB board equipped with processors and memory for executing commands and managing data from the imaging, weighing, and sorting modules. The software governs each component's operation, maintaining synchronous performance across the system.
In one aspect, the software includes a user interface for real-time monitoring, allowing operators to adjust grading parameters or inspect the processing flow.
In another aspect, the control unit supports remote connectivity, enabling centralized management and data analysis across multiple processing locations.
In yet another embodiment the system according to the present invention compiles data on graded and sorted shrimp batches, generating reports that shrimp processors can use for forecasting, inventory management, and market analysis. The reporting includes metrics on size distribution, quality grades, and rejected shrimp, allowing for data-driven decision-making.
In an aspect of the above embodiment the reporting module provides predictive insights based on historical processing data, offering suggestions for adjusting grading standards.
Another aspect of the invention includes integration with cloud-based storage, facilitating secure, remote access to processing data and analytics.
In another embodiment the system may include water quality monitoring systems including pH sensors within a feeder tank (101), wherein the controller unit generates alerts when the pH level falls outside of predefined thresholds, ensuring water remains suitable for shrimp processing.
In some embodiments according to the present invention the operation flow of the System comprises:
- Loading the shrimp onto conveyor belt and transportation;
- Capturing detailed image for qualitative assessment;
- Weight determination and analysis for preliminary grading;
- Final grading based on combined information of the image and weight data using AI/ML;
- Collecting the graded shrimps; and data compilation and reporting.
In one aspect of the above embodiment the conveyor loaded shrimps are transported to the imaging and weighing stations. The conveyor may align shrimp in single-file or grouped as necessary for accurate processing.
In another aspect for imaging and quality Analysis, the shrimp pass under the imaging system, the cameras capture detailed images for quality assessment, analyzing size, color, and shell condition using AI-based algorithms. Specific disease markers or abnormalities are flagged during this stage.
In yet another aspect for weight measurement, each shrimp is measured by load cells, and the weight data is synchronized with image-based size information to assign a preliminary grade based on size and weight parameters.
In a further aspect the grading decision is done by AI Algorithms, where the AI and ML algorithms process the aggregated data from the imaging and weight sensors, assigning a grade based on predefined quality and size criteria. Shrimp not meeting the grade standards are flagged for rejection or secondary processing.
In an aspect the sorting and collection step comprises directing the graded shrimp by mechanical gates or diverting into collection bins or channels, each corresponding to a specific grade or quality category. Rejected shrimp are sent to a separate bin for further inspection or disposal.
In another aspect for the data compilation and reporting, a report is generated summarizing the batch's grading distribution, highlighting key data points such as quantity by grade, rejection rates, and detected diseases. The data is stored for immediate review or long-term analysis.
The Smart Shrimp Grading and Sorting System while enabling the integration of specific functionalities tailored to processing environments. The system's flexibility in adjusting to various shrimp qualities and sizes makes it a versatile tool for meeting industry demands and regulatory standards. The critical components as discussed in above embodiments will now be discussed in view of drawings:
The present invention relates to a Smart Shrimp Grading and Sorting System (100), which automates the process of shrimp grading and sorting based on various parameters, including weight, size, and condition. This system (100) utilizes an integration of mechanical components, sensors, actuators, and a control unit to effectively handle, grade, and sort shrimp at a high throughput.
Figures 1 and 2 illustrate the system architecture and component connections, respectively.
Referring to Figure 1 demonstrating the components of the Smart Shrimp Grading and Sorting System (100) along with the process flow that begins with a Feeder Tank (101) as the primary intake point for shrimp (110). Shrimp are gravity-fed onto a Conveyor Belt (102), which serves as the main transportation path throughout the grading and sorting process.
The conveyor system moves shrimp sequentially through different processing units, beginning with a Drying Unit (103), which reduces the moisture content of each shrimp. Following drying, a Singulation Unit (104) ensures that shrimp are separated, preventing clustering as they advance.
A Vision Unit (204) equipped with a Camera (105) and IR sensor is positioned along the conveyor to capture high-resolution images of each shrimp (110), enabling analysis for characteristics such as species, condition, and the presence of foreign objects / non-shrimp (111). The camera distinguishes between shrimp (110) and non-shrimp (111), removing diseased or otherwise unsuitable shrimp from the line.
Next, shrimp pass over a Load Cell (106), which records the weight of each individual shrimp. This weight data, along with positional information from Ultrasonic Sensors (107), is transmitted to a Control Unit (201) for processing. The control unit also manages Solenoid-Controlled Pneumatic Pumps (108) that guide shrimp into designated Sorting Baskets (109) based on weight and other sorting parameters.
Referring to Figure 2, it depicts the block diagram (200) of the interconnected units and components of the system. The Control Unit (201), implemented using an ESP32 microcontroller, coordinates data from the Sensor Unit (203), Vision Unit (204), and Actuator Unit (205) to execute real-time sorting. The Power Supply Unit (202) powers the system, ensuring a continuous and stable operation. Each component connects to the controller, providing specific data or operational feedback necessary for automated grading and sorting.
Component Functionality:
Feeder Tank (101): The Feeder Tank (101) serves as the primary loading station. Shrimp (110) are introduced into the tank, allowing them to be gravity-fed onto the conveyor belt system (102) for processing.
Conveyor Belt System (102): The Conveyor Belt System (102) transports shrimp sequentially through each processing station. It ensures steady movement from the loading point to the different grading stations and ultimately to sorting.
Drying Unit (103): This unit lowers the shrimp's moisture content, improving imaging and weighing accuracy. The drying process also maintains optimal conditions for subsequent sensors and imaging devices.
Singulation Unit (104): The Singulation Unit (104) separates individual shrimp, allowing each to be processed individually. This step is critical for avoiding clustering that could interfere with image and weight accuracy.
Vision Unit (204) with Camera (105) and IR Sensor: The Vision Unit (204) captures high-resolution images via a Camera (105) and detects object type with the IR sensor, distinguishing between shrimp (110) and non-shrimp items (111). Diseased shrimp and foreign objects are removed from the conveyor.
Load Cell (106): The Load Cell (106) records the weight of each shrimp as it moves along the conveyor. This data is stored in the Control Unit (201), which uses it to determine the appropriate sorting destination.
Ultrasonic Sensors (107): Placed near each sorting basket (109), Ultrasonic Sensors (107) detect shrimp presence as they approach their designated basket. The Control Unit (201) relies on this positional data to initiate sorting.
Solenoid-Controlled Pneumatic Pumps (108): Each pneumatic pump (108) is positioned adjacent to a sorting basket (109). When a shrimp arrives at its assigned basket, the solenoid triggers the corresponding pump to direct the shrimp into the correct basket.
Sorting Baskets (109): Sorting Baskets (109) collect shrimp based on weight categories, ensuring accurate grading by pre-set parameters.
Controller Unit (201) ESP32: The Control Unit (201) manages data from sensors and actuators. It uses non-blocking, interrupt-based programming to enable efficient real-time processing and control of the shrimp's movement through the system. It can track multiple shrimp at once and handle different weight sequences arriving at high frequency.

EXAMPLES:
Detailed embodiments of the present invention are disclosed herein with the help of examples with reference to the accompanying drawings; however, it is to be understood that the disclosed embodiments are merely exemplary of the invention, which can be embodied in various forms. These are not the limiting scope of this patent.
Example 1: Working of the integrated shrimp sorting and grading system (100):
In an example operation, shrimp (110) are introduced into the Feeder Tank (101) and proceed along the Conveyor Belt (102). As they pass through the Drying Unit (103) and Singulation Unit (104), the shrimp are prepared for individual processing. The Vision Unit (204) captures images of each shrimp using a Camera (105) and in conjugation with IR Sensors, enabling analysis for species, health, and quality.
Once each shrimp is weighed on the Load Cell (106), the Control Unit (201) stores the weight and positional data, awaiting signals from Ultrasonic Sensors (107) as the shrimp approach sorting baskets. At the designated basket, the Solenoid-Controlled Pneumatic Pump (108) activates, directing the shrimp into the appropriate Sorting Basket (109) according to its weight and quality attributes.
This data-driven, automated grading system enables efficient, accurate sorting for high-throughput shrimp processing. , Claims:We Claim:
1. A shrimp grading and sorting system (100), comprising:
a feeder tank (101) configured to introduce shrimp (110) into the system;
a conveyor belt system (102) to transport shrimp through various processing stages;
a drying unit (103) positioned along the conveyor belt (102) to reduce moisture content of the shrimp;
a singulation unit (104) to separate individual shrimp for processing;
a vision unit (204) comprising a camera (105) and infrared sensor to capture images and detect foreign objects (111) along the conveyor belt (102);
a load cell (106) to measure the weight of each shrimp;
a sensor unit (203) equipped with ultrasonic sensors (107) to detect shrimp location, moisture, and temperature;
a controller unit (201) configured to receive data from the load cell (106), vision unit (204), and sensor unit (203), and to control sorting operations;
an actuator unit (205) comprising solenoid-controlled pneumatic pumps (108) to direct shrimp into designated sorting baskets (109) based on weight and size data; and
a power supply unit (202) to power the system components; wherein the controller unit (201) coordinates real-time grading and sorting of shrimp (110) by processing data received from the camera (105), load cell (106), and sensors (107), and by activating the actuator unit (205) to direct shrimp into respective sorting baskets (109) based on grading criteria.
2. The system as claimed in claim 1, wherein the controller unit (201) comprises an ESP32 microcontroller, capable of non-blocking operation and enabling real-time processing and analysis of data for simultaneous control of multiple shrimp (110) passing through the system.
3. The system as claimed in claim 1, wherein the vision unit (204) with the camera (105) captures high-resolution images of each shrimp (110) to detect characteristics such as length, color, and presence of disease, enabling precise grading based on physical attributes.
4. The system as claimed in claim 1, wherein the load cell (106) records the weight of each shrimp (110) as it moves along the conveyor belt (102), and the weight data is stored in the controller unit (201) along with a timestamp to ensure accurate tracking and sorting.
5. The system as claimed in claim 1, wherein the singulation unit (104) is configured to isolate each shrimp (110) from any clumps, allowing individual shrimp to be processed separately for enhanced accuracy in imaging, weighing, and grading.
6. The system as claimed in claim 1, wherein the actuator unit (205) further comprises solenoid-controlled pneumatic pumps (108) that activate when the shrimp (110) reaches the corresponding sorting basket (109), as detected by ultrasonic sensors (107) placed near each basket.
7. The system as claimed in claim 1, wherein the controller unit (201) uses input from the vision unit (204), load cell (106), and ultrasonic sensors (107) to identify and remove non-shrimps or foreign objects (111) detected on the conveyor belt (102) before they reach the sorting stage.
8. The system as claimed in claim 1, further comprising a pH level sensor within the feeder tank (101) to monitor water quality, wherein the controller unit (201) generates alerts when the pH level falls outside of predefined thresholds, ensuring water remains suitable for shrimp (110) processing.
9. The system as claimed in claim 1, wherein the vision unit (204) is configured to leverage artificial intelligence (AI) and machine learning (ML) algorithms to improve the classification of shrimp (110) based on disease detection, physical characteristics, and weight distribution.
10. The system as claimed in claim 1, wherein the controller unit (201) generates real-time data reports on shrimp quantities, grading accuracy, and sorting efficiency, providing analytics to improve inventory management, operational planning, and quality control.

Dated this 13th day of November 2024

BISWAJIT BISWAL
[IN/PA-2659]
AGENT FOR THE APPLICANT

Documents