A Study on Technology-LED Solutions for Fruit Grading to Address Post-Harvest Handling Issues of Horticultural Crops

The reduction of post-harvest losses and value addition of the horticultural corps has attained the higher priority of the current research works. Grading is the major phase in post-harvest handling. Presently grading is done on the basis of observation and through experience. Various drawbacks associated with such manual grading are subjectivity, tediousness, labor requirements, availability, inconsistency, etc. Such problems can be alleviated by incorporating automation in the process. Researchers round the clock are working towards the development of technology-driven solutions in order to grade/sort/classify various agricultural and horticultural produce. With the motto of helping the researchers in the field of grading and quality assessment of fruits and other horticulture products, the present work endeavors the following major contributions: (1) a precise and comprehensive review on technology-driven solutions for grading/sorting/classification of fruits, (2) major research gaps addressed by the researchers, and (3) research gaps to be addressed.

Deep Learning and Computer Vision in Smart Agriculture

The exponential growth in the world population has led to an ever-increasing demand for food supplies. This has led to the realization that conventional and traditional methods alone might not be able to keep up with this demand. Smart agriculture is being regarded as one of the few realistic ways that, together with the traditional methods, can be used to close the gap between the demand and supply. Smart agriculture integrates the use of different technologies to better monitor, operate, and analyze different activities involved in different phases of the agricultural life cycle. Smart agriculture happens to be one of the many disciplines where deep learning and computer vision are being realized to be of major impact. This chapter gives a detailed explanation of different deep learning methods and tries to provide a basic understanding as to how these techniques are impacting different applications in smart agriculture.

Automatic Data Acquisition and Spot Disease Identification System in Plants Pathology Domain

Plants play one of the main roles in our ecosystem. Manual identification for the leaves sometimes leads to greater difference due to look alike. People often get confused with lookalike leaves which mostly end in loss of life. Authentication of original leaf with look-alike leaf is very essential nowadays. Disease identification of plants are proved to be beneficial for agro-industries, research, and eco-system balancing. In the era of industrialization, vegetation is shrinking. Early detection of diseases from the dataset of leaf can be rewarding and help in making our environment healthier and green. Implementation involves proper data acquisition where pre-processing of images is done for error correction if present in the raw dataset. It is followed by feature extraction stage to get the best results in further classification stage. K-mean, PCA, and ICA algorithms are used for identification and clustering of diseases in plants. The implementation proves that the proposed method shows promising result on the basis of histogram of gradient (HoG) features.

Computer Vision for Green Plant Segmentation and Leaf Count

Image-based plant phenotyping plays an important role in productive and sustainable agriculture. It is used to record the plant traits such as chlorophyll fluorescence, plant growth, yield, leaf area, width and height of plants frequently and accurately. Among these plant traits, plant growth is an important trait to be analyzed that directly depends on leaf area and leaf count. Taking benign conditions of quick advancement in computer vision and image processing algorithms, many methods have been developed in recent days to find the leaf area and leaf count accurately. In this chapter, the recent techniques in image-based plant phenotyping and their limitations are discussed. Also, this chapter discusses a new plant segmentation method based on wavelet and leaf count methods based on Circular Hough Transform and deep learning model, which overcomes the drawbacks of recent methods. These methods are experimented with Computer Vision Problems in Plant Phenotyping (CVPPP) benchmark datasets.

Image Processing Techniques Aiding Smart Agriculture

With the ever-increasing load of satiating the agricultural demands, the transition of the orthodox methods into smart ones is inevitable. The agriculture sector for long has served as a momentous source of livelihood for many globally. It is arguably a major topic for nations of the development spectrum, contributing towards their export earnings and aiding in their GDP assessment. Thus, it is quite conspicuous that nations would work towards its expansion. In congruence, the burgeoning population and its demands have posed a threat to the environment due to extensive exploitation of resources, which in turn is escalating towards the downfall of the quality and quantity of agricultural produces requiring a 70% increment in the produces by 2050 for sustainability. To combat such hurdles, developed techniques are being employed. Through a survey of existing literature, this chapter provides a comprehensive overview of various image processing means that could come in handy for ameliorating the present scenario and shows their implied extension in the smart farming world.

Agro Guardian

The mechanization of the process creates agriculture-based jobs for farmers, providing financial support and facilitating affordable agriculture equipment and machineries. Fruits markets are subject of opportunity and it is important to the suppliers to identify the quality of fruits based on the ripeness level of fruits before selling out in order to get higher level of profit. The proposed framework is an Android application in native language of the farmer to help the jobless farmers to find agriculture-based jobs suitable to their skill set and receive investments from various investors across the country. Further, it finds investment for the needy farmers and create suitable agricultural employment for jobless farmers so that there is an increase in the progress in the field of agriculture. It also facilitates the farmers with advanced equipment for performing various agricultural tasks, obtains the land on lease, and determines various stages of ripeness of fruit and provides the information about the government project and funding facilities.

Applications of Data Mining Techniques in Smart Farming for Sustainable Agriculture

Smart farming is a development that highlights the use of technologies such as the internet of things, cloud computing, machine learning, and artificial intelligence in the farm management cycle. For sustainable agriculture to adapt the ongoing change in climate and social structure is a major challenge for scientists and researchers. The approach needs information from various sources and its use in the relevant field, which lead to a growing interest in knowledge discovery from large data. Data mining techniques provide effective solutions for this problem as it supports the automation of extracting significant data to obtain knowledge and trends, the elimination of manual tasks, easier data extraction directly from electronic sources, and transfer to secure electronic system of documentation, which will increase the agriculture productions from same limited resources. In a nutshell, the aim of this chapter is to gain insight into the applications of data mining techniques in smart farming, which direction to employ sustainable agriculture and identify the challenges to be addressed.

Expert System Design for Diagnosis of Diseases for Paddy Crop

India has the second largest area of arable (agricultural) land on this earth with heterogeneous agroclimatic regions across the country. India has the potential to grow a wide range of agricultural crops and varied raw material base for food processing industry. The paddy crop yield/hector of land is highest in Egypt is 9.5, while India is producing only 2.9. India's lower paddy crop productivity/hector and higher cost of production is a major concern for farmers. There are various reasons for India's low paddy crop yield, such as lack of mechanization, not adopting to modern method of farming, small land holdings, poor pests, and disease management. The recent survey discovered that there is huge gap in demand and supply in crop production and is likely to hit more than 15% by 2020, with the gap worsening to 20-25% by 2025. Researchers aimed to address this low crop yield issue by designing an expert system. This expert system helps the farmers by identifying and predicting the diseases for paddy crop to enhance crop yield and to reduce the supply and demand gap.

Issues and Challenges in Smart Farming for Sustainable Agriculture

Sustainable agriculture helps to promote farming practices and methods in order to sustain farmers and resources. It is economically viable, socially supportive, and economically sound. It assists to maintain soil quality, reduce soil erosion and degradation, and also save water resources. Sustainable agriculture improves the biodiversity of the land and thus leads to the healthy and natural environment. The sustainable agriculture is very essential to ordinate with the increasing demand for the food, climate change, and degradation of the ecosystem in future. It plays a major role for preserving natural resources, reducing greenhouse gas emissions, halting biodiversity loss, and caring for valued landscapes. Sustainable agriculture is applied to farming in order to preserve the nature without compromising the quality of the future generation basic needs and thus enable to make smartness in farming. The common practices included in smart farming for sustainable agriculture are crop rotations that mitigate weeds, disease, insect, and other pest problems.

Optimized Data Mining Techniques for Outlier Detection, Removal, and Management Zone Delineation for Yield Prediction

Enormous agricultural data collected using sensors for crop management decisions on spatial data with soil parameters like N, P, K, pH, and EC enhances crop growth for soil type. Spatial data play vital role in DSS, but inconsistent values leads to improper inferences. From EDA, few observations involve outliers that deviates crop management assessments. In spatial data context, outliers are the observations whose non-spatial attributes are distinct from other observations. Thus, treating an entire field as uniform area is trivial which influence the farmers to use expensive fertilizers. Iterative-R algorithm is applied for outlier detection to reduce the masking/swamping effects. Outlier-free data defines interpretable field patterns to satisfy statistical assumptions. For heterogeneous farms, the aim is to identify sub-fields and percentage of fertilizers. MZD achieved by interpolation technique predicts the unobserved values by comparing with its known neighbor-points. MZD suggests the farmers with better knowledge of soil fertility, field variability, and fertilizer applying rates.