Proceedings of the International Conference on Applied Artificial Intelligence and Computing (ICAAIC 2022)

IEEE Xplore Part Number: CFP22BC3-ART; ISBN: 978-1-6654-9710-7

Monitoring Ripeness in Fruits and Vegetables Using

the Raspberry Pi
1 2 3
A. Jayalakshmi L Poojitha Reddy M Srikar Preetham
Assistant Professor,Dept of ECE UG student,Dept of ECE. UG student,Dept of ECE.
Vardhaman College of Engineering Vardhaman College of Engineering Vardhaman College of Engineering
Hyderabad, India Hyderabad, India Hyderabad, India
[email protected] [email protected] srikarpre etha m 23 @ g ma il.c om
2022 International Conference on Applied Artificial Intelligence and Computing (ICAAIC) | 978-1-6654-9710-7/22/$31.00 ©2022 IEEE | DOI: 10.1109/ICAAIC53929.2022.9792876

Abstract—Traditional systems are being phased out in favour of

modern technological systems. Many ripeness detection
instruments for vegetables and fruits exist, but they are inefficient
and costly. The suggested system design intends to develop a low-
cost, high-performance system for detecting ripeness in fruits and
vegetables that will be tremendously beneficial in everyday life.
Fruits and veggies are good for one’s health in general. Today, a
variety of methods are used to determine the maturity level of fruits
and veggies, ranging from simple methods such as having to touch
this same food to feel its lightness and even start to smell the fruit,
to scientific methodology based on the quantitative characteristics
demanded for fresh produce growth and development, such as ionic
strength, compression running tests, greenhouse gases, interior x- Fig.1 .Picking the vegetables and fruits manually
rays, epidermis or pulp colour, and so on. Changes in texture are The use of vision detecting technologies to detect fruit
happening on the crop’s surface. There are destructive sampling
quality has become increasingly appealing. At the moment,
techniques for determining the level of ripeness of a fruit or
vegetable over time, even in real time, by measuring and sensing the majority of the fruit on the market is Quality detection
ripeness, as well as non-destructive sampling techniques for and grading systems have the disadvantages of low efficiency,
determining the level of ripeness of a fruit or vegetable without slow grading speed, high cost, and limited functionality. The
destroying the sample. This work’s sensing elements include a pi amount of work required by humans is reduced to the absolute
camera module, an LCD, and a Raspberry Pi. These sensor
parameters are fed into the Raspberry Pi, which determines
minimum. Climate change has resulted in a major reduction
ripeness detection. When ripeness is detected, an SMS is sent to the in the quantity and quality of agricultural products. Plant
LCD, and an image of ripeness is displayed on the LCD. pathogens Using image processing techniques, certain diseases
Index Terms—Raspberry pi, Ripeness Determination, LCD , can be recognized. In today’s world, people don’t think
pi camera module; about how fresh the end result and greens they’re eating are.
Consuming fresh fruits and vegetables is beneficial to one’s
I. INT RODUCT ION health. Food poisoning occurs as a result of improper food
Agriculture has a significant impact on all of our lives. Agri- handling. This is due to the bacteria’s invisibility. As a result,
culture provides a living for 70 percent of India’s we must devise a method to prevent food poisoning and other
population. Agriculture contributes considerably to diseases caused by overripe fruits and vegetables. We can
economic development by supplying non-agricultural avoid illness by eating fresh fruits and vegetables. As a result,
businesses with food and raw resources. Agriculture
it is critical to grade the quality of vegetables and fruits.
necessitates a significant amount of labour. Farmers spend a
There are numerous traditional and human sorting machines
significant amount of time manually sorting and inspecting
available on the market. But these machines require lot of
their crops from harvest to growth. Manual sorting does not
always yield satisfactory results. As a result, effective smart human effort. Our proposed system will determine ripeness
farming techniques that can be used to increase productivity more effectively, quickly, and accurately, while requiring less
and profitability are required. In order to improve fruit human effort. This device is beneficial to all of us because it
quality and production efficiency while reducing labour promotes health benefits for all of us. Some fruits are picked
intensity, Fruit non-destructive detection is the method of up directly from the parent plant before they are even immature
detecting the quality of fruits on the interior and outside and cannot ripen normally, and these fruits are given at a high
without destroying them, utilizing detecting technology to cost for production and shipment. The fruits and vegetables
make an assessment based on specified criteria. Standard
procedures nowadays, the quality of fruit form, defau lt,
colour, and size, among other things, cannot be assessed on
the internet. It has been easier to do so as image processing
technology, as well as computer software and hardware, has
advanced.

978-1-6654-9710-7/22/$31.00 ©2022 IEEE 1540

Authorized licensed use limited to: BIRLA INSTITUTE OF TECHNOLOGY AND SCIENCE. Downloaded on December 30,2023 at 11:19:38 UTC from IEEE Xplore. Restrictions apply.
 are then stored for an extended period of time to maintain their determined by calculating, and finally this same image’s size
freshness and ripeness. People in the market can access them is determined .
without any loss during their post-harvest processing, which According to I.F.Astuti [5], To identify and display the
includes storing them in supermarkets, importing and exporting freshness of fruit in its entirety,a sensor device was developed
them. We start by feeding the vegetables to the machine, and implemented.
and then we test it using software and ripeness detecting The essential concepts and technologies related with image
algorithms. The machine will accept the input of the fruit or analysis employ Ing a computer vision system and automatic-
vegetable, then send the result to the Raspberry Pi, locate the based technology are introduced by Kritika[6]. The agriculture
ripeness, and show the same immediately on the LCD. industry is in desperate need of development and improved
yields.An effective smart technique is used in this work to
re- store manual sorting, which is time-consuming and yields
insignificant results. The Open CV library installation has
begun. Awate uses the K-means clustering algorithm for image
segmentation. [7]
Hongshe [8] developed a system for recognizing and as -
sessing fruit size based on images. The Raspberry Pi acts as
Fig.2. Block Diagram of the system the system’s processor, and image processing algorithms are
To work on ripeness detection, we require an input sensor, employed to create the QT/Embedded platform’s fruit size
such as a camera. The first step is to use the camera’s slot to detection application.
attach the Pi Camera to the Raspberry Pi board. The program is
[9] developed a fuzzy logic-based system for detecting the size
downloaded and installed on the Raspberry Pi Zero W board. and categorizing various fruits; the author recommended
Raspbian OS is the operating system of choice. A image of MATLAB for feature extraction and GUI design in this
a fruit or vegetable is taken to begin the proposed method. example.
The image is then forwarded to the open CV processing
level, where fruit attributes such as colour, shape, and size Njoroge[10] presented an image-based automated grading
are extracted from fruit samples. In this proposed work, the system that focuses on the fruit’s internal and external faults.
open cv method is used to detect the form, size, and colour The system employs six CCD cameras. The top two cameras
of fruit, and the results produced by combining these three are at the top, the right two are on the right, and the bottom two
aspects are reported. When you offer this machine a fruit or cameras are placed at the bottom.
vegetable, it detects the elegance of ripeness and categorizes Image enhancement has recently emerged as a significant tool
it based on ripening phases. for fruit classification and quality assessment. Fruit quality is
The software element is highly useful for determining an important aspect of the food sector that is often overlooked.
quality by determining ripeness, estimating shape and size, A good degree or value is associated with the degree of
and detecting flaws in fruits and vegies. Class 1: high ripeness excellence. Consumers' perceptions of mango quality are most
class, class 2: medium ripeness class, class 3: poor ripeness influenced by colour (appearance), followed by scent (flavour),
class, and class 4: defected class are the four classes that the firmness (texture), and nutritional value [11].
grading system will assign. The greatest resource in [12] that may be utilized to determine
mango quality is its look. Associated with digital image
II. LIT ERAT URE SURVEY analysis, a non-destructive ripeness stage measurement for
mangoes of the cultivar Harumanis was used in this work.
Chandra Sekhar [1] demonstrated an automated fruit
Mango ripeness is significantly connected with changing
grading method based on machine vision. The mango fruit is
peeling and flesh colour, which can be quantified as a sensory
used in the process. This fruit system based on machine vision
quality metric. Picture analysis technique was used to evaluate
can help you save time and effort while maintaining
the ripeness level, which required attributing domestic and
uniformity and accuracy.
foreign colour features from image segmentation. For colour
Suresh [2] presented”Smart Planting: A Process for Field image segmentation, a multilevel thresholding algorithm is
Monitoring in Agriculture.” They combined GSM and DTMF proposed to recover the mango region from the background,
technologies in this system to control various farming activities using each band of five colour spaces.
via cellphone.
Due to multiple similarities of shape, size, and colour,
[3] N. El-Bendary presented Color characteristics are used classifying distinct fruits and vegetables is a difficult
to categorize tomato ripening stages. In addition to SVM and undertaking [13]. Fruits, flowers, and crops are usually the first
LDA segmentation algorithms, approaches like PCA are used. to be harvested. An inspector inspects the produce after it has
We offer 40 5-second clips for each lesson.Each video frame been harvested and distributed to the market. Personnel who
is transformed to a L*a*b* rgb space using just the a*b* are experts or have been trained.
values, as well as the pixel to be eliminated (noise) and the
Convolutional neural networks have the benefit over artificial
pixel of the fruits were located to use the K mean integration.
neural networks in that they can perform feature selection and
Second, they produce 24 characteristics per sample for
extraction as well as integrate huge values of parameters [14].
regarding the system used all number of sides of a fruit, and
also RGBa*. The advancement of image processing techniques has also
aided the advancement of computer vision procedures. Despite
Our technique has the same number of maturity states as the
technological developments in the farming production,
study [4].The size of the input image is affirmed, the filtration
classification of fruit and veg remains difficult due to the great
for sensing sobel edges is implemented, image character traits
variety, irregularity, and inconsistency in shape, colour, and
like intensity, comparison, entropy, and standard error are
texture [15].
derived, the Distance measure from of the image is
Authorized licensed use limited to: BIRLA INSTITUTE OF TECHNOLOGY AND SCIENCE. Downloaded on December 30,2023 at 11:19:38 UTC from IEEE Xplore. Restrictions apply.
 Related work section to be improved using tabular methods RGB image is taken and it is converted into HSB image. Then,
of comparing existing works. color feature extraction is performed and based on the color of an
RGB image the ripeness is determined and it is classified.
Step 2: Detection in Vegetables and Fruits:
Existing Method Proposed Method By taking the input image from camera, the given fruit
or vegetable is then verified by color feature extraction. Then
1. Readily available 1. The Pic Microcontroller
image analysis is performed the RGB images are converted to
in the marketplace development board, conveyor,
HSV and then the overall upper and lower ranges have been
although systems motors, and Pi camera are all
defined for a given image. The digital images and their ranges
have been part of our system. All of the
are defined for a given vegetable or fruit. To determine the
established, they above sensors will be
threshold range we use HSV color thresholder so that is gives
are practically interconnected, resulting in a
the information about the color of the fruit or vegetable to
extremely costly low-cost integrated solution
determine the ripeness.
for small and for deciding the level of
Step 3: Detection of ripeness in Vegetables and Fruits:
medium-sized fruit ripeness of vegetables and
The ripeness detection is an important step in this proposed
processors. fruits.
system. Here, the RGB images determine the ripeness of the
2. Human specialist’s 2. The shape, size, and vegetables and fruits based on their color. If the color identified
rate farming goods ripeness of the fruit are by the system is Red then it is classified as High ripeness and if
based on vision- estimated using an edge the color identified by the system is Red with black dots
based qualities, detection technique, and the then it is classified as defected fruit or vegetable. Pi camera
which leads to ripeness is determined using a module along with Raspberry Pi with VNC software using
inaccuracy, colour detecting algorithm. python is used to determine the ripeness.
inconsistency, and
inefficiency in I V. SYST EM DESCRIPT ION
defining agriculture A. Raspberry Pi
goods quality. The Raspberry Pi 4, a non-profit organization based in the
United Kingdom dedicated to increasing access to computing
education and educating people about computing, has created a
III. M ET HODOLOGY range of solitary computers known as the Pic Microcontroller.
This proposed system is used to detect the ripeness present Since its first introduction in 2012, the Microcontroller has
in different vegetables and fruits. It detects the ripeness by undergone a lot of changes and enhancements. The first Mi-
using raspberry pi and python libraries. The proposed system controller had a solitary 700MHz processor with 256MB of
consists of pi camera module which takes the input image of RAM, but the most recent model has a 4×4 1.5GHz processor
the fruit and vegetables and gives it to raspberry pi which with 4GB of RAM. The Microcontroller has typically cost
then performs various image processing techniques to find out about 100(approximately35 USD), with Pi Zero becoming the
the ripeness in vegetables and fruits. This electronic method cheapest at just 5.
is effective and requires less human effort. The Raspberry Pi is used by people all around the world to
study programming, create developers can build, manage their
Step 1: Acquiring the input image of vegetable or fruit: houses, run Kubernetes cluster and Computing, and even in
This step involves taking the input image of fruit or veg- industrial settings. The Raspberry Pi is a small microcomputer
eatable for checking the ripeness detection for the system with a number of GPIO ports for editing and experimenting
and given to raspberry pi and digital image is saved in VNC with electronic components.
software. The input image is taken through pi camera and Specifications:
here; we have taken tomato for checking its ripeness and • Broadcom BCM2711 4×4 Cortex-A72 (ARM v8) 64-bit
given to the system. The main process of ripeness SoC @ 1.5GHz Processor: Broadcom BCM2711 4×4 Cortex-
determination consists of 3 processes. A72 (ARM v8) 64-bit SoC
• Memory: LPDDR4-2400 SDRAM, 1GB, 2GB, or 4GB
(depending on model)
• Bluetooth 5.0, BLE Gigabit Ethernet, IEEE 802.11b/g/n/ac
wireless LAN, 2.4 GHz and 5.0 GHz IEEE 802.11b/g/n/ac wifi
LAN 2 USB ports 3.0 interfaces There are two USB 2.0 ports.
• GPIO: A 40-pin GPIO header is standard (fully
backwards-compatible with previous boards)
• 5V DC through USB-C connector as input power (min-
imum 3A1 ) GPIO header with 5V DC (minimum 3A1 )
Enabled for Power over Ethernet (PoE)

Fig. 3. Flow Chart of the System

First, it takes the input of a vegetable or fruit then it applies

image preprocessing. After applying preprocessing, color
feature extraction is done to a vegetable or fruit. Then the fruit is
classified according to its ripeness. In Image preprocessing
Fig. 4. Raspberry Pi 4 Model B
Authorized licensed use limited to: BIRLA INSTITUTE OF TECHNOLOGY AND SCIENCE. Downloaded on December 30,2023 at 11:19:38 UTC from IEEE Xplore. Restrictions apply.
 Selection of raspberry pi : programmed text, digits, and seven-segment screens, such as
We have used the Raspberry Pi to learn programming, those found in digital readouts.
develop our project, to implement ripeness detection in Specifications:
vegetables , fruits and even employ them in commercial • This display’s working voltage varies from 4.7 to 5.3 volts.
applications, Arduino don’t have their own operating
• The bezel around the display measures 72 x 25mm.
systems whereas raspberry pi has and it also supports
internet , that is why we have used raspberry pi • Without a backlight, the operating power is 1mA.
• The module’s PCB measures 80L x gun x 10H mm.
B. Pi Camera Module • The HD47780 is a microcontroller.
An sensor, lens, properly prepare, and a communications • Backlight LEDs come in green or blue colors.
system such as CSI, Internet, or raw reduced differential • There are 16 columns in total.
signaling make up a camera module. When combined
• The number of rows is two.
with the OV5647 camera, this 5 mp sensor can take 1080p
film and still images and connects straight to your Raspberry A wide range of Crystal Display ( lcd Displays employ the
Pi. This is the most latest edition of the Raspbian, which is HD44780 type microcontroller chip. These LCDs are
available in a variety of sizes and configurations, with 8 to
plug-and-play compliant and excellent for applications
80 visible characters organized in 1, 2, or 4 columns.
such as moment photos, recorded video, motion detection,
and security. Connect the cables you’ve been given. Ribbon
you are set to go once you’ve attached the wire to the Pi Pi’s
CSI (Camera Communication Interface) port. The board is
small and lightweight, spanning 25mm x 23wide diameter
9mm and weighing now over 3g, making it perfect either
mobile or otherapplications.
Clarity needed for the CSI port in the paper?
Raspberry Pi Camera is a camera that can snap photos and
record high-definition video. The CSI (Serial Interface)
interface on the Raspberry Pi Board allows us to connect Fig..6 LCD
directly the Pi Camera module. Using a 15-pin ribbon cable,
this Raspberry Camera module may be connected to the
Raspberry Pi's CSI port. D . Image Acquisition
Specifications: The first stage in converting an analogue image to a digital
• In a fixed-focus module, a Hitachi IMX 219 PQ Ccd image. This technique will support scaling and other which was
image sensor is used. before options. Image acquisition is the process of obtain ing a
• 8-megapixel resolution picture from the a resource, usually hardware including such
• 3280 x 2464 pixels (still image) camera, sensors, and so on. Because the system cannot conduct
• Image transmission rate maximu m 30 frames per any analysis without an image, it is the initial and most
second in 1080p (encode and decode) 60 frames per appropriate timeframe in the workflow sequence. Every image
second in 720p captured by system is usually raw. During the picture- taking
• Connection to the specialized 15-pin MIPI Serial process, a set of sensors responsive to that type ofenergy
Interface via the Raspberry Pi cable to connect ribbon converts incoming energy from the sun from such an object
cable (CSI-2). into an electrical signal. Those tiny subsystems operate
together to provide your computer vision algorithm with the
most honest depiction of the item. Those tiny subsystems like
camera, sensors operate together to provide your computer
vision algorithm with the most honest depiction of the item
providing the exact level of ripeness with accuracy. This
technique will support scaling it will resize the digital image
given to it before ripeness
E. Image Pre-processing

The raw image is processed in this technique at the start

of the procedure. Image modification and analytics could be
used to improve image quality by noise removal, scaling a
Fig. 5. Pi Camera Module image, contrast adjustment, sharpening, magnification, and
changing the histogram. Photographic process of improving
C. LCD or extracting information from a photograph by executing
operations on it. It’s a type of signal analysis in which the
A fluid screen (LCD) is a plain screen or other electronic image is the input and the picture or its character traits
control optical device that makes use of polarizers and liquid are the output. Graphics rendering is one of today’s most
crystals’ light-modulating characteristics. Rather than rapidly evolving technologies. It’s also a big deal in computer
producing bright light, liquid crystals create colour or engineering science research. Image modification can help
monochromatic images using a backlight or reflector. [2] you develop the brightness of your image or extract valuable
LCDs can display random graphics (like on a monitor screen) information from it. It's beneficial in a variety of industries,
or static visuals with minimal relevant information that can be including diagnostic imaging, and it could even be used to
Authorized revealed
licensed useor hidden.
limited Devices
to: BIRLA usingOFthese
INSTITUTE displaysAND
TECHNOLOGY include pre-Downloaded
SCIENCE. conceal ondata within
December a picture.
30,2023 at 11:19:38 UTC from IEEE Xplore. Restrictions apply.
 F. Feature Extraction

It’s a method of describing a photograph’s unique qualities

in order to prepare it for future processing. When an image is
retrieved, its representation might be pictorial or non -
pictorial, and it is fed into classification and patterns
recognition algorithms to classify, label, or recognize the
image’s content. Parameters like colour, texture, morphology,
and borders could be used to enhance the output when given
to an image. Using extraction of features to define a huge set
of data saves time and resources. Feature extraction aims to Fig. 8.VNC on PC
reduce the number of features in a dataset by creating new
ones from old ones (and then discarding the original
features). These new, reduced capabilities ought to be able to VI.RESULTS
summarize a lot of information.
Check ripeness of a vegetable or fruit when it is given to the
system consisting of raspberry pi.
Case 1 : If the color of the fruit or vegetable is green then it is
classified as unripe Case 2 : If the color of the fruit or vegetable
is red then it is classified as ripe , based on the ripeness levels it
is again classified into low, medium and high ripeness. Case 3:
If the color of the fruit or vegetable is red and having any black
dots then it will be classified as defected

Fig 7. Working Model of the System

V . SOFTWARE IMPLEMENTATION

Guido van Rossum developed Python in the Dutch’ Re-

search Center for Computer science in the 1980s and 1990s.
Python is a scripting language that is runtime environment, Fig. 9. Vegetable is put into the system for ripeness detection
interactive, and object-oriented. Python is thought to be an
easy-to-understand programming language. Its vocabulary is
restricted when compared to other languages, and it
frequently uses English words instead of grammar. Python
offers object- oriented programming as well as structural and
functional programming methodologies. For the building of
large ap- plications, it will be employed as a
programming language or translated to byte-code. It delivers
data with extremely dynamic frequency types and facilitates
dynamic type validation. It collects garbage in a robotic
method. In C, Objective-C, COM, ActiveX, CORBA, and
Java, it’s simple to integrate. Like any other computer, the
Raspberry Pi requires an operating system to work. In this
paper, the board is run using the official operating system.
The programming language in use is Python 3. The PC must
have VNC installed and be connected to a Wi-Fi or personal
hotspot network. The Raspberry Pi is a single-board Fig.10. Here, The Vegetable is detected as medium ripeness
computer (SBC). A Microcontroller, on the other hand,
connects to same wireless network using a mouse and
keyboard.

Authorized licensed use limited to: BIRLA INSTITUTE OF TECHNOLOGY AND SCIENCE. Downloaded on December 30,2023 at 11:19:38 UTC from IEEE Xplore. Restrictions apply.
 process is efficient and quick. The consumer can use this
approach to determine the condition of a fruit or vegetable,
allowing them to avoid eating ripe fruits or vegetables. This
method is beneficial because it avoids any food wastage. It
also promotes the health of an individual by providing them
with fresh fruits and vegetables. This method can be made
even more extensible by adding cargo methodology, which
can determine the internal structure of a fruit without any
contact, which will make the system even more accurate.

REFERENCES
[1] C. S. Nandi, B. Tudu, and C. Koley, “Machine vision based automatic fruit
Fig. 11. Monitor displaying the ripeness value of the grading system using fuzzy algorithm,” Int. Conf. Control. Instru -
Vegetable mentation, Energy Commun. CIEC 2014, no. February 2014, pp. 26 –30,
2020..
In this example we have taken a tomato for grading and it is [2] R. Suresh Kumar, S. VinuBhagavath K. Muthumeenakshi, K.Sreeram and
classified as medium ripeness .The value of total Redness, S. Radha, “Smart Farming—A Prototype for Field Monitoring and
Greenness and Yellowness of the system is displayed along Automation in Agriculture”, IEEEWiSPNET2017conference.22- 24March
with the ripeness. 2017
[3] N. El-Bendary, E. El Hariri, A. E. Hassanien, and A. Badr, “Using machine
learning techniques for evaluating tomato ripeness,” Expert Syst. Appl.,
vol. 42, no. 4, pp. 1892–1905, 2015.
[4] N. M. S. Iswari, Wella, and Ranny, “Fruitylicious: Mobile application for
fruit ripeness determination based on fruit image,” in HSI. IEEE, 2017
[5] I. F. Astuti, F. D. Nuryanto, P. P. Widagdo, and D. Cahyadi, “Oil palm fruit
ripeness detection using k-nearest neighbour,” Journal of Physics:
Conference Series, vol. 1277, p. 012028, jul 2019.
[6] Krithika Jayasankar, Karthika B, Jayashree T, Deepalakshmi R, Karthika G”
Fruit Freshness detection using Raspberry Pi” International Journal of
Pure and Applied mathematics Volume 119 No.15 2018, 1685-1691
[7] A. Awate, D. Deshmankar, G. Amrutkar, U. Bagul, and S. Sonavane, “Fruit
disease detection using color, texture analysis and ANN,” Proc. 2015 Int.
Conf. Green Comput. Internet Things, ICGCIoT 2015, pp. 970–975, 2016.
[8] H. Sardar, “Quality Analysis in grayscale color using visual appearance of
a guava fruit,” International Journal of Engineering Sciences, pp. 46- 56,
2013.
Fig.12. Fruit is put into the system for ripeness detection [9] Ananthi, S. Vishnu Varthini, Detection And Classification Of Plant Leaf
Diseases International Journal of Research in Engineering Applied
Sciences, Volume 2, Issue 2 (February 2012) ISSN: 2249-3905.
[10 ] Harshavardhan G. Naganur, Sanjeev S. Sannakki, Vijay SRajpurohit,
Arunkumar R, “Fruits Sorting and Grading using Fuzzy Logic,”
International Journal of Advanced Research in Computer Engineering
Technology (IJARCET) Volume 1,Issue 6, August 2012,pp 117-122.
[11 ] Anuja Bhargava, Atul Bansal, Fruits and vegetables quality evaluation
using computer vision: A review, Journal of King Saud University -
Computer and Information Sciences, 2018.
[12 ] M.N Abu Bakar , A.H. Abdullah , N.A. Rahim , H.Yazid , F.S.A. Saad , K.
Ahmad,” Development of Ripeness Indicator for Quality Assessment of
Harumanis Mango by using Image Processing Technique” Conference on
Science, Engineering and Technology (ICSET) 2020.
[13 ] J. Steinbrener, K. Posch, and R. Leitner, “Hyperspectral fruit and
vegetable classification using convolutional neural networks,”
Computers and Electronics in Agriculture. Vol. 162, pp. 364-372, 2019.
[14 ] A. Africa, T. Dolores, M. Lim, L. Miguel, and V. Sayoc. “Understanding
logical reasoning through computer systems.” International Journal of
Fig.13. Monitor Displaying the ripeness value of the fruit Emerging Trends in Engineering Research. Vol. 8, No. 4, pp 1187-1191,
2020.
[15 ] K. Hameed, D. Chai, and A. Rassau, “A comprehensive review of fruit and
The Fruit is put into the system for ripeness detection and it is vegetable classification techniques,” Image and Vision Computing. Vol.
classified as low ripeness. 80, pp. 24-44, 2018.

VII.CONCLUSTION
This study uses RASPBERRYPI/PYTHON to distinguish
between normal and ripe fruits and vegetables depending on
quality. It’s done correctly and successfully Image processing
is employed. Not only can it be used to determine
quality,but it can also be used to determine whether a product
is of good quality. This method can also be used to find out
who’s with greater precision on vegetable quality. As a
result, the technology can be used in a variety of applications,
such as a computer vis ion system that can replace manual
food inspection with a genuine, fair, and non-destructive
1545
Authorized rating. Before
licensed use limitedato:person consumes
BIRLA INSTITUTE a fruit or vegetable,
OF TECHNOLOGY this Downloaded on December 30,2023 at 11:19:38 UTC from IEEE Xplore.
AND SCIENCE. Restrictions apply.