Scribd
Upload
19 views3 pages

Black Pepper Harvester Using Image Processing

Uploaded by

Raiza Borreo
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
19 views3 pages

Black Pepper Harvester Using Image Processing

Uploaded by

Raiza Borreo
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/ 3

Black Pepper Harvester using Image Processing

Raiza Dimapilis-Borreo

Abstract

With a vision to replace farm workers with robots as to improve agricultural sectors, many scientific research are focused on
developing technologies that will boost.. agribots. Agribots are more efficient and can work longer hours compared to humans.
These agribots can As the food demand increases, enhanced agribots are

Introduction results of the study showed a 91.3% success rate in spotting


the salient regions with pepper and 84.35% in the contour
Smart farming involves the integration of extraction.
technology to an existing farming methods (Brown, 2018).
Meanwhile, in 2017, Choudhary used edge-based
Image processing is probably the most influential and color based detection methods to segment images of
field of artificial intelligence because of its vast utilization. mango fruit where the color based algorithm was able to
In the field of medicine, it can be used to diagnose some detect mangoes with 85-90% accuracy. Occlusion and
disorders associated with the face. (Dimapilis-Borreo, illumination are the mitigating factors why the color based
2017)In agriculture, imagery of plants are being subjected algorithm was not applicable on all cases.
to digital processing to determine its characteristics such as
its variant, growth level or any disease that it has. Another method to detect the features of a fruit is
the scale invariant feature transform (SIFT).
Considered as a tropical country, the Philippines is
well-known for its natural resources that is one of the main Classification
source of income of local farmers. These natural resources
can be In classifying phase, K-NN algorithm can be used

From growing to harvesting, farmers are


continuously challenged to improve quality of life for Segmentation
farmers with reduced heavy labor.
Recognition of fruits in the natural environment
In this research, a new method of harvesting black becomes challenging due to the involvement of complex
pepper corn is introduced eliminating the tedious and backgrounds. This problem has also been addressed in the
lengthy way of manual collection. The plant is subjected to literature. A K-means clustering algorithm is applied to
image processing that will determine if the corns are ready segment fruits from the background (Jana, 2017).
for harvesting already. Moreover, the
GrabCut is an efficient and interactive
algorithm for foreground/background segmentation
Related Literature from still images proposed by Rother et al. of
Microsoft Research Cambridge, UK. he algorithm
Countries that produces black pepper use manual makes use of two components: a hard-labeling
method of harvesting where laborers climb up to the trees scheme defined for image pixels and a
side (Rahul, 2012). According to 2017 statistics, the foreground/background classifier based on Gaussian
Philippines ranked 22nd with only 1,369 tons in world share Mixture Model (GMM) that takes RGB pixel values as
of black pepper production (FAOSTAT, 2017). A very input features (Jana, 2017).
small production compared to Vietnam at 1 st rank with
252,576 tons.
Cutting Tool
Black peppercorns are harvested once a part of the
black pepper corn becomes reddish in color.

Feature Extraction

In 2013, Lim used robotic vision system to locate


the coordinates of the black pepper corn in the tree. The
Proposed Method
method is composed of three stages namely salient point
localization, contour extraction and pepper verification. The
Using the raspberry pi and an attached camera to References
it, the harvester will detect black pepper corns and
estimating the number of group of corns in a tree. At a
center distance, the harvester will identify the color of the
corn, if there is an existing red or orange corns detected,
that means the device can now harvest.

Corn Detection

Segmentation/
Edge Detection

Distance Calculation

Cutting

Detection

Segmentation

Distance Calculation

Cutting

Results

Conclusion

King Hann Lim, A. A. (2013). Robotic vision system design for black pepper harvesting. 2013 IEEE International Conference of
IEEE Region 10 (TENCON 2013).

Pradeepkumar Choudhary, R. K. (2017). Image Processing Algorithm for Fruit Identification. International Research Journal of
Engineering and Technology (IRJET), 2741-2743.
Rahul M., P. V. (2012). Design and Development of a Pepper Plucking Equipment to Facilitate Pepper Harvesting. SASTech, 74-
81.

Sawe, Benjamin Elisha. (2019, June 7). The World's Top


Black Pepper Producing Countries. Retrieved from
https://www.worldatlas.com/articles/the-world-s-top-black-
pepper-producing-countries.html

http://www.factfish.com/statistic/pepper%2C
%20production%20quantity FAOSTAT

Jana, Susovan & Basak, Saikat & Parekh, Ranjan. (2017).


2017 : Automatic Fruit Recognition from Natural Images
using Color and Texture Features.
10.1109/DEVIC.2017.8074025.

Dimapilis-Borreo, R., & Ambat, S. C. (2017). Detecting


Temporomandibular Joint Disorder (TMJD) Using
Modified Euler Angle in Image Processing With
Application. International Journal of Computer
Engineering and Information Technology, 9(8), 176.

You might also like