Tea industries face the challenge of foreign substances, both organic and inorganic, contaminating their processed tea. These materials can enter the tea during various stages, posing risks to customers and the company's reputation. Manual sorting, the traditional method for removing foreign matter, is time-consuming, labor-intensive, and prone to errors. To address this problem, this paper proposes a machine vision-based solution. It involves capturing continuous images of processed tea as it moves through a vibratory bed. These images are analyzed using a single board computing device to detect visible foreign matter on the tea. When foreign substances are identified, pneumatic valves in the vibratory bed open a small window, allowing the contaminated tea leaves to be released, while the clean tea continues to pass through and collect in a storage container at the end. The solution employs a modular approach, enabling multiple vision inspection modules to be controlled through a single graphical user interface (GUI) on a desktop, meeting the high throughput requirements of tea industries. Experiments conducted on Orthodox tea varieties confirm the proposed solution meets industry standards for accuracy and throughput. By implementing this machine vision-based approach, tea processing companies can enhance customer safety, maintain loyalty, and prevent recalls or rejections, while significantly reducing labor and time involved in manual sorting processes.

The quality estimation of chili plays a crucial role in the spice market industry. This research paper introduces an innovative method for chili quality estimation using the YOLOv8 architecture, a cutting-edge object detection model. By leveraging deep learning techniques, the proposed method offers an automated and efficient solution to accurately assess the quality of chili. Traditional methods of quality estimation heavily rely on subjective assessment or time-consuming manual processes. In contrast, the proposed approach utilizes the YOLOv8 model, which combines advanced convolutional neural networks and object detection algorithms to achieve precise and fast chili quality estimation. To train the YOLOv8 model, a comprehensive dataset of annotated chili images has been curated, encompassing various quality attributes such as “Broken Chili”, “Damaged Chili”, “Good Chili”, “Loose Seed”, and “Stalk”. Through extensive experiments and fine-tuning, the model’s performance has been optimized to achieve high accuracy in chili quality estimation. The experimental findings illustrate the effectiveness of our approach, with the YOLOv8 model achieving a mean Average Precision (mAP) of 75

Feature detection and description algorithms are the most widely used techniques in various computer vision works such as panorama image stitching, object tracking, and object detection. This study brings a novel method to compare algorithm’s accuracy to detect and describe features. Computational efficiency of the algorithms is also determined. Feature detection algorithms that are analyzed in this study are SIFT, BRISK, ORB, KAZE and AKAZE. In this analysis, five datasets have been considered: built-up area, mountain, forest, water body and barren land. In order to analyze the robustness of these algorithms, every second image of these datasets are distorted by creating noise and features are determined. Noises created are the visual and viewpoint changes on the image; such as radiance change, scale change and orientation change. Algorithms differ in their functionality, SIFT linearly diffuse entire image while KAZE and AKAZE performs nonlinear diffusion. Whereas BRISK and ORB algorithms differ in features description by using binary descriptors. The result obtained from the research shows that ORB is the most accurate and computationally efficient algorithm to determine the features.

Sorghum is a critical staple crop in many parts of the world, including India, where it serves as a primary source of nutrition and income for millions of small-scale farmers. The efficient trading of sorghum through platforms like the Electronic National Agriculture Market (e-NAM) requires rigorous quality control measures to ensure fair pricing and food safety. This research paper presents the development and evaluation of a machine-based system for the comprehensive analysis of physical purity and quality assessment of sorghum grains, aimed at improving the efficiency of the e-NAM.

The Indian agriculture market, or “mandis,” is important to the economy of that nation. It is crucial to maintain customer confidence, maximize market effectiveness, and protect the interests of both farmers and consumers by ensuring the quality and purity of crop grains. In this study, we suggest a novel method for dealing with the difficulty of precise and effective purity examination of various crop grains utilizing an automated machine-based system. We want to transform the quality evaluation process in Indian agricultural markets by utilizing cutting-edge technologies like computer vision and machine learning, allowing informed decision-making and improving overall market efficiency.

Field Programmable Gate Arrays (FPGAs) have emerged as powerful hardware accelerators for deep learning applications due to their reconfigurable nature and parallel processing capabilities. Among FPGA development platforms, Python Productivity for Zynq (PYNQ) stands out as a notable option, providing a Python interface to program Xilinx Zynq FPGA SoCs. This paper presents a comprehensive review of research papers focusing on FPGA-based real-time deep learning applications developed within the PYNQ framework. It delves into the advantages of utilizing FPGAs for deep learning, the seamless integration of deep learning models into PYNQ platforms, and a detailed analysis of the performance enhancements achieved through FPGA acceleration. Furthermore, challenges and opportunities in the agriculture domain have been discussed for future research in this evolving domain. Deep learning in agriculture, leveraging FPGA and PYNQ, may revolutionize the development of real-time applications.

E-tongue, machine vision and NIR systems were used to standardize the quality measurements in twenty rice genotypes grown in Highland Himalayan regions of Kashmir, in order to overcome the constraints of manual measurements. IRCTN-312 showed highest amylose content of 20.74 % and 20.70 % using iodometric method and NIR tester, which was validated by the highest norm value of 34.158 by E-tongue. From these results, genotypes such as GSR-43, GS-103, GSR-23B, GSR-60, SR-4, GSR-46, Koshihikari, GSR-64, GSR-32, GSR-49, GSR-4, GSR-42, GS-459, SKUA-494 and SKUA-540 were classified as low amylose and C-3, K-332, M4-22 and IRCTN-312 were classified as intermediate amylose in the present study. Lowest percentage of damaged grains and chalk ratio was found in GSR-23B. SKUA-494 recorded highest L/W ratio using both the systems. Highest head rice yield and elongation ratio was found in GSR-23B and SKUA-494 genotypes respectively. Highest lightness (L*) value was recorded for Koshihikari genotype.

Segmentation of hyperspectral images can be achieved by utilizing the abundance map. Before generating an abundance map, endmember detection is necessary. The algorithms for endmember detection are Pixel Purity Index (PPI), N-FINDR, Automatic Target Generation Process (ATGP), and Fast Iterative Pixel Purity Index (FIPPI). Based on the spectral signature of the extracted endmembers, the abundance map can be generated using Fully Constrained Least Squares (FCLS), Non-negative Constrained Least Squares (NNLS), and Unconstrained Least Squares (UCLS) algorithms. This paper proposes to explore the possible combinations of endmember detection and abundance map generation algorithms. A comparative study was conducted on the combination of algorithms, and it was discovered that FIPPI and UCLS together take the least amount of time to execute, whereas PPI and FCLS take the most time to execute. Though, the trade-off analysis shows that ATGP and NNLS could be an optimum option for this case study of segmentation of watery low land area.

Acoustic system and machine vision were used to evaluate the effects of different harvest dates on the quality and sensory attributes of exotic apple varieties of North Western Himalayan. Gala Redlum (V1) was harvested at 110 (H1), 120 (H2) and 130 (H3) Days from Full Bloom (DFFB); Red Velox (V2) and Super Chief (V3) were harvested at 130 (H1), 140 (H2) and 150 (H3) DFFB. Highest acoustic coefficient (21.13) and firmness (20.72 lbs) recorded at first harvest date (H1) decreased significantly (p ≤0.05) (19.86 to 17.90 lbs) at second harvest (H2) and (17.77 to 16.80 lbs) at third harvest date. Highest starch iodine rating (3.72); anthocyanin content (24.81 mg/100 g); total soluble solids (12.10 %); total sugars (8.75 %) were recorded at H3 in all the varieties. For Gala Redlum (V1) 130 DFFB and for Red Velox (V2) and Super Chief (V3) 150 DFFB were predicted as suitable harvesting dates for table consumption.

This research introduces a new dynamic thresholding method, designed for changing illumination conditions in image processing. Traditional fixed thresholds struggle with varying light due to factors like voltage changes, LED aging, etc. The proposed technique adapts thresholds using background image intensity as a reference, employing a supervised approach with polynomial curve fitting via Python's numpy library. This innovative dynamic thresholding, combining supervised learning, enhances object detection and segmentation in machine vision systems, aiding tasks like foreign matter removal in tea, grain quality monitoring, etc.

The “Protection of Plant Varieties and Farmers' Rights Act. (PPBFRA)” recognizes and protects the rights for the development of new plant varieties for a set duration. Only if a variety satisfies the requirements of distinctness, uniformity, and stability (DUS), can be registered and preserved. It means the new variety's characteristics must be distinct, uniform, and stable. The DUS protocol's test recommendations are a collection of characteristics determined by the national authority. The major part of these recommendations is the measurement of the morphological and color-based characteristics of different plant parts. Manually measuring these characteristics in the field is subjective and vulnerable to human error. The derivation of DUS-defined physiological and color characteristics of Okra stem, flower, and seed are proposed in this article using machine vision technology. To capture pictures of Okra stem, flower, and seed after harvesting from the field, a dark room imaging system was built utilizing a DSLR camera. The same setup was used to acquire all of the pictures following the designed protocol for each plant part. To obtain the necessary morphological and color-based DUS features, digital image processing and analysis methods were used. With fewer human interventions in comparison with conventional techniques, the proposed methodology precisely provides the DUS-defined features. The accuracy of the methodology, when compared to manual measurement, justifies its applicability for objectively assessing the DUS-defined features.

This paper proposes real-time inspection of the paddy field using robotic vision technology. Chlorophyll content in the plant is the measure of sufficient or deficit amount of nutrients in the field as well as the health condition of the plant. The proposed work estimates the chlorophyll content of the plant while navigating the robotic vehicle in the field. An image acquisition arrangement has been mounted facing the ground on the robotic vehicle which captures on-field images. Color information from these images is compared with the digitized reference leaf color chart. Mahalanobis distance has been calculated from the extracted color with all colors in the reference color chart. Using the minimum Mahalanobis distance the best match with the reference chart has been decided. The robotic vehicle has the provision of spraying fertilizer if the matched color is the last two colors (e.g. having a light green shade) from the reference color chart. The result of this chlorophyll estimation approach is encouraging and the accuracy is to the tune of 92%.

A novel plant variety can be registered and protected for a fixed period under the “Protection of Plant Varieties and Farmers’ Rights Act.” A variety can only be registered and protected if it meets the criteria of distinctness, uniformity, and stability (DUS). It signifies that the new variety’s features must be distinct-uniform-stable (DUS). The test recommendations in the DUS protocol are the set of characteristics chosen by the national authority. The characteristics could be morphological, biochemical, molecular, or of any other kind. Measuring these parameters manually on the field can be subjective and prone to human error. This paper proposes a machine vision technology for the derivation of DUS-defined physiological and color features of okra fruit. A dark room imaging setup was developed using a DSLR camera to capture the images of okra fruit after harvesting from the field. All the images of okra fruit were captured using the same setup. Digital image processing and analysis technologies have been applied to derive the specified morphological and color-based DUS characteristics. The proposed methodology is objectively providing the DUS characteristics with fewer human interventions. The accuracy of this technique in comparison with manual measurement justifies its utility for the objective assessment of DUS features.

In the era of fourth industrial revolution or Industry 4.0, Computational Intelligence, Data Science and smart Information and Communication technology (ICT) are gaining huge importance in our society.Governments around the world started relying heavily on information and communication technologies to build smart and hyper-connected infrastructures that allow cities to provide better services to people and reduce energy consumption, as the global urban population is growing substantially.These intelligent technologies allow cities to introduce new ways of monitoring the atmosphere, buildings, street lighting, traffic, crowds, crime, etc.In building a smarter and more intelligent city around the world, Computational intelligence and ICT are the underlying technologies; but if not wisely applied, ICT can be a major environmental problem.At present, about 2 percent of global greenhouse gas (GHG) emissions are accounted for by the global ICT industry.This footprint is expected to increase dramatically to about 14 percent by 2040, according to a recent report.Intelligent use of advances in ICT will assist in minimizing GHG while still achieving its goals.ICT is theoretically able to reduce the carbon footprint in other fields by a factor of 10, based on the Global e-Sustainability Initiative (GeSI) report.ICT technologies such as Green ICT, the Internet of Things (IoT) and Artificial Intelligence (AI) can play important roles, not just in making our environment smarter, but also greener and more sustainable.

Acetylcholinesterase (AChE), a widely used enzyme for inhibition-based biosensors in pesticide residues detection, lags due to multiple-step operation, time-consuming incubation and reactivation/regeneration steps. Herein, this endeavour reports the development of Organophosphate Hydrolase (OPH), which has functional superiority over the AChE and explored in on-spot biosensing device for organophosphate pesticide residue detection in fruits and vegetables. The organophosphate degrading enzyme OPH is expressed from the 'opd' gene through biotechnological tools. The OPH exhibited its best activity at pH 8.0 and subsequently thermal inactivation over 37 degrees C. The activity of the purified OPH enzyme was found 2.75 U mL(-1) at lambda(max) 410 nm. Furthermore, the developed OPH is integrated into 96 well plate format with our previously reported UIISScan 1.1, an advanced imaging array technology based field-portable high-throughput sensory system. The developed biosensor revealed a linear range from 100 ng mL(-1) to 0.1 ng mL(-1) for detection of organophosphate pesticide residues with a negative slope i.e. y = 235.678x (ng mL(-1)) - 62.8725 with R-2 = 0.99991 and n = 23. Moreover, the applicability of the developed biosensor was tested for market available fruits and vegetables. This is the first-ever reported OPH mediated on-spot biosensing device for pesticide residue detection in fruits and vegetables to the best of our knowledge.

In the era of fourth industrial revolution or Industry 4.0, Computational Intelligence, Data Science and smart Information and Communication technology (ICT) are gaining huge importance in our society.Governments around the world started relying heavily on information and communication technologies to build smart and hyper-connected infrastructures that allow cities to provide better services to people and reduce energy consumption, as the global urban population is growing substantially.These intelligent technologies allow cities to introduce new ways of monitoring the atmosphere, buildings, street lighting, traffic, crowds, crime, etc.In building a smarter and more intelligent city around the world, Computational intelligence and ICT are the underlying technologies; but if not wisely applied, ICT can be a major environmental problem.At present, about 2 percent of global greenhouse gas (GHG) emissions are accounted for by the global ICT industry.This footprint is expected to increase dramatically to about 14 percent by 2040, according to a recent report.Intelligent use of advances in ICT will assist in minimizing GHG while still achieving its goals.ICT is theoretically able to reduce the carbon footprint in other fields by a factor of 10, based on the Global e-Sustainability Initiative (GeSI) report.ICT technologies such as Green ICT, the Internet of Things (IoT) and Artificial Intelligence (AI) can play important roles, not just in making our environment smarter, but also greener and more sustainable.

In the era of fourth industrial revolution or Industry 4.0, Computational Intelligence, Data Science and smart Information and Communication technology (ICT) are gaining huge importance in our society.Governments around the world started relying heavily on information and communication technologies to build smart and hyper-connected infrastructures that allow cities to provide better services to people and reduce energy consumption, as the global urban population is growing substantially.These intelligent technologies allow cities to introduce new ways of monitoring the atmosphere, buildings, street lighting, traffic, crowds, crime, etc.In building a smarter and more intelligent city around the world, Computational intelligence and ICT are the underlying technologies; but if not wisely applied, ICT can be a major environmental problem.At present, about 2 percent of global greenhouse gas (GHG) emissions are accounted for by the global ICT industry.This footprint is expected to increase dramatically to about 14 percent by 2040, according to a recent report.Intelligent use of advances in ICT will assist in minimizing GHG while still achieving its goals.ICT is theoretically able to reduce the carbon footprint in other fields by a factor of 10, based on the Global e-Sustainability Initiative (GeSI) report.ICT technologies such as Green ICT, the Internet of Things (IoT) and Artificial Intelligence (AI) can play important roles, not just in making our environment smarter, but also greener and more sustainable.

In the era of fourth industrial revolution or Industry 4.0, Computational Intelligence, Data Science and smart Information and Communication technology (ICT) are gaining huge importance in our society.Governments around the world started relying heavily on information and communication technologies to build smart and hyper-connected infrastructures that allow cities to provide better services to people and reduce energy consumption, as the global urban population is growing substantially.These intelligent technologies allow cities to introduce new ways of monitoring the atmosphere, buildings, street lighting, traffic, crowds, crime, etc.In building a smarter and more intelligent city around the world, Computational intelligence and ICT are the underlying technologies; but if not wisely applied, ICT can be a major environmental problem.At present, about 2 percent of global greenhouse gas (GHG) emissions are accounted for by the global ICT industry.This footprint is expected to increase dramatically to about 14 percent by 2040, according to a recent report.Intelligent use of advances in ICT will assist in minimizing GHG while still achieving its goals.ICT is theoretically able to reduce the carbon footprint in other fields by a factor of 10, based on the Global e-Sustainability Initiative (GeSI) report.ICT technologies such as Green ICT, the Internet of Things (IoT) and Artificial Intelligence (AI) can play important roles, not just in making our environment smarter, but also greener and more sustainable.

Physical and biochemical attributes are commonly used for characterization of rice. The physical attributes are related to the quantification of size, shape, colour and texture of the rice grains. Biochemical attributes are assessed from cooking and eating characteristics of rice and are termed like alkali spreading value (ASV), amylose content (AC), gel consistency (GC), grain elongation etc. Estimation of biochemical attributes are often time consuming and require meticulous effort for sample preparation, storage and manual measurement. The gelatinization temperature (GT) is related to Alkali spreading value of rice and is partly associated with the amylose content of the starch. GT has a negative correlation with cooking temperature of rice. In this paper image analysis technique has been proposed for discrimination of rice. A portable flat bed scanner has been used as the imaging device and image analysis software has been developed to measure the rate of dispersion during ASV testing. This machine vision technique is a faster and effective way to determine the ASV. The results obtained are promising towards this new approach for objective estimation of ASV.

The paper has examined on the non destructive assessment of potatoes using a piezo based sensor. In assessing the freshness of the product, there are different research reports, but surface firmness is an excellent indicator and is used extensively in practice. The sensor is used as a vibration sensor where the vibration patterns are recorded and analyzed in frequency domain and then the quality parameters are displayed accordingly. It is found that dry matter is related with the firmness of potato tubers which also converts itself to starch content depending on time and storage of potato tubers as firmness is very useful for processing industry. With some minor software modifications it can be adopted for other vegetables as well.