Scribd
Upload
8 views5 pages

Literature Survey

This literature survey presents various studies focused on agricultural technology, including deep learning frameworks for fruit classification, image analysis for estimating vegetable shelf life, and IoT systems for monitoring produce. Key findings highlight significant accuracy improvements in classification tasks and the potential for real-time applications to enhance agricultural efficiency and reduce food waste. The research collectively emphasizes the integration of machine learning and image analysis in modern agricultural practices.

Uploaded by

Arun
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
8 views5 pages

Literature Survey

This literature survey presents various studies focused on agricultural technology, including deep learning frameworks for fruit classification, image analysis for estimating vegetable shelf life, and IoT systems for monitoring produce. Key findings highlight significant accuracy improvements in classification tasks and the potential for real-time applications to enhance agricultural efficiency and reduce food waste. The research collectively emphasizes the integration of machine learning and image analysis in modern agricultural practices.

Uploaded by

Arun
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 5

LITERATURE SURVEY

1. Title: Automating Fruit Classification Using Deep Learning Techniques

Authors: Alice Johnson, Mark Thompson

This paper presents a deep learning framework for the automated classification
of fruits using convolutional neural networks (CNNs). Developed a dataset
consisting of over 10,000 annotated images of various fruits, which were used
to train our model. The proposed method achieved an accuracy of 95% on a
validation set, significantly improving over traditional image processing
techniques. The results demonstrate the potential for real-time applications in
agricultural settings, enabling more efficient sorting and quality control
processes.

2. Title: Estimating the Shelf Life of Vegetables Through Image Analysis

Authors: Robert Wilson, Emma Lewis

This study focuses on developing a model to estimate the remaining shelf life of
vegetables using image analysis and machine learning techniques. High-
resolution images were captured and analyzed using a CNN-based approach to
classify maturity levels. The model predicted the remaining shelf life with an
accuracy of 92%. Our findings indicate that image-based assessments can
significantly enhance the monitoring of produce freshness and contribute to
reducing food waste in supply chains.
3. Title: IoT-Based System for Real-Time Monitoring of Agricultural
Produce

Authors: David Miller, Laura Garcia

This paper introduces an Internet of Things (IoT) system designed for real-time
monitoring of agricultural produce. The system integrates various sensors to
collect data on temperature, humidity, and soil moisture levels, which are then
analyzed using machine learning algorithms. Our case studies in crop
management demonstrate improved yield prediction and resource management
efficiency. The proposed system provides farmers with actionable insights,
facilitating data-driven decision-making in agriculture.

4. Title: Mobile Application for Assessing Fruit Ripeness Using Deep


Learning

Authors: Sarah Martinez, Kevin Chen

This research describes the development of a mobile application that leverages


deep learning to assess the ripeness of fruits. Utilizing the transfer learning
architecture, the app classifies fruits into different maturity levels based on
images taken by users. The model was trained on a diverse dataset, achieving a
classification accuracy of 90%. This innovative tool aims to assist consumers
and retailers in making informed decisions about fruit purchases, enhancing the
quality of produce in the market.
5. Title: Predicting Nutrient Content in Vegetables Using Machine
Learning Models

Authors: James Anderson, Michelle Taylor

This paper explores the use of machine learning models to predict the nutrient
content of vegetables based on physical characteristics and weight
measurements. We employed regression algorithms, including random forests
and support vector machines, to analyze a dataset containing various vegetable
types and their corresponding nutrient profiles. Our best model achieved an R²
score of 0.85, demonstrating that machine learning can effectively estimate
nutritional values, providing valuable information for both consumers and
producers in the agricultural sector.

6. Date Fruit Classification for Robotic Harvesting in a Natural


Environment Using Deep Learning

Authors: H. Altaheri, M. Alsulaiman and G. Muhammad

An accurate vision system to classify and analyze fruits in real time is critical
for harvesting robots to be cost-effective and efficient. However, practical
success in this area is still limited, and to the best of our knowledge, there is no
research in the area of machine vision for date fruits in an orchard environment.
In this work, we propose an efficient machine vision framework for date fruit
harvesting robots. The framework consists of three classification models used to
classify date fruit images in real time according to their type, maturity, and
harvesting decision. In the classification models, deep convolutional neural
networks are utilized with transfer learning and fine-tuning on pre-trained
models. To build a robust vision system, we create a rich image dataset of date
fruit bunches in an orchard that consists of more than 8000 images of five date
types in different pre-maturity and maturity stages. The dataset has a large
degree of variations that reflects the challenges in the date orchard environment
including variations in angles, scales, illumination conditions, and date bunches
covered by bags. The proposed date fruit classification models achieve
accuracies of 99.01%, 97.25%, and 98.59% with classification times of 20.6,
20.7, and 35.9 msec for the type, maturity, and harvesting decision classification
tasks, respectively.

7. Non-destructive method for monitoring tomato ripening based on


chlorophyll fluorescence induction

Authors: Abdelhamid, M. A., Sudnik, Y., Alshinayyin, H. J., & Shaaban, F

Maturity is one of the most important factors in the assessment of tomato


quality. The aim of this study is to develop a new device to measure the degree
of tomato ripeness based on chlorophyll fluorescence. The results of this
method in terms of chlorophyll fluorescence were compared with those from the
most widely used colorimeter. The botanical variety of tomatoes
‘Alkazar’ was used at different stages of maturity: green, breakers,
turning, pink, light red, and red. The results indicated that specific parameters of
slow induction of chlorophyll fluorescence, such as maximum chlorophyll
fluorescence (Fm) and the coefficient of specific photosynthetic activity (Rfd),
can be used to classify tomatoes according to their maturity stage as efficiently
as with the hue angle parameter of color measurements. The correlation
coefficient between the hue angle and the slow induction of chlorophyll
fluorescence parameters was 0.96 with Fm, and 0.97 with Rfd. Using the hue
angle or Fm, tomatoes of all six-maturity stages were accurately classified. In
conclusion, this new measurement method is a nondestructive, innovative and
convenient approach, which is less time-consuming than the colour-based
method.

You might also like