scispace - formally typeset
Search or ask a question
Proceedings Article•DOI•

Durian Species Recognition System Based on Global Shape Representations and K-Nearest Neighbors

Xin Yi Nyon1, Mas Rina Mustaffa1, Lili Nurliyana Abdullah1, Nurul Amelina Nasharuddin1•
Universiti Putra Malaysia1
26 Mar 2018-pp 1-6
TL;DR: This work aims to contribute to an automatic content-based durian species recognition that will be able to assist users in differentiating various species of durian.
Abstract: Many fruit recognition systems today are designed to classify different type of fruits but there is no content-based fruit recognition system focuses on durian species. Durian, known as the king of tropical fruits, have few similar characteristics between different species where the skin have almost the same color from green to yellowish brown with slightly different shape of thorns and it is hard to differentiate them with the current methods. Sometimes it is even hard for general consumers to differentiate durian species by themselves. This work aims to contribute to an automatic content-based durian species recognition that will be able to assist users in differentiating various species of durian. Few global contour-based and region-based shape descriptors such as area, perimeter, and circularity are computed as feature vectors and K-Nearest Neighbors algorithm is used to classify the durian based on the extracted features. 10-fold cross-validation is used to evaluate the proposed system. Experimental results have shown that the proposed feature extraction method for the durian species recognition system has successfully obtained a positive recognition rate of 100%.

Summary (1 min read)

Jump to:  and [Summary]

Summary

  • Many fruit recognition systems today are designed to classify different type of fruits but there is no content-based fruit recognition system focuses on durian species.
  • Durian, known as the king of tropical fruits, have few similar characteristics between different species where the skin have almost the same color from green to yellowish brown with slightly different shape of thorns and it is hard to differentiate them with the current methods.
  • Sometimes it is even hard for general consumers to differentiate durian species by themselves.
  • This work aims to contribute to an automatic content-based durian species recognition that will be able to assist users in differentiating various species of durian.
  • Few global contour-based and region-based shape descriptors such as area, perimeter, and circularity are computed as feature vectors and K-Nearest Neighbors algorithm is used to classify the durian based on the extracted features.
  • 10-fold cross-validation is used to evaluate the proposed system.
  • Experimental results have shown that the proposed feature extraction method for the durian species recognition system has successfully obtained a positive recognition rate of 100%.

Did you find this useful? Give us your feedback

Content maybe subject to copyright    Report

Durian species recognition system based on global shape representations and k-nearest
neighbors
ABSTRACT
Many fruit recognition systems today are designed to classify different type of fruits but there
is no content-based fruit recognition system focuses on durian species. Durian, known as the
king of tropical fruits, have few similar characteristics between different species where the
skin have almost the same color from green to yellowish brown with slightly different shape
of thorns and it is hard to differentiate them with the current methods. Sometimes it is even
hard for general consumers to differentiate durian species by themselves. This work aims to
contribute to an automatic content-based durian species recognition that will be able to assist
users in differentiating various species of durian. Few global contour-based and region-based
shape descriptors such as area, perimeter, and circularity are computed as feature vectors and
K-Nearest Neighbors algorithm is used to classify the durian based on the extracted features.
10-fold cross-validation is used to evaluate the proposed system. Experimental results have
shown that the proposed feature extraction method for the durian species recognition system
has successfully obtained a positive recognition rate of 100%.
Keyword: Durian; Content-based; Shape feature; K–nearest neighbors; Recognition rate; 10-
fold cross validation
Citations
More filters
Journal Article•DOI•
Exploring the chemical composition, emerging applications, potential uses, and health benefits of durian: A review

[...]

Maimunah Mohd Ali1, Norhashila Hashim1, Samsuzana Abd Aziz1, Ola Lasekan1•
Universiti Putra Malaysia1
01 Jul 2020-Food Control
TL;DR: In this paper, a review on the chemical composition, potential uses, health benefits, and emerging technologies for the quality evaluation of durian, with the goal of providing information for its exploitation.

19 citations

Proceedings Article•DOI•
A Durian Variety Identifier Using Canny Edge and CNN

[...]

Julie N. Uy1, Jocelyn Flores Villaverde2•
University of Mindanao1, Mapúa Institute of Technology2
30 Jul 2021
TL;DR: In this paper, a Raspberry Pi was used to implement image processing algorithms and to create a portable device to identify the fruit's variety, which can be used in today's modern technology like in medicine, media or the like, and devices are portable for accessibility.
Abstract: Durian belongs to the genus Durio and a native fruit in tropical countries in the regions of Southeast Asia such as Malaysia, Indonesia, Thailand, and the Philippines. Durian can be easily recognized by its spiky husk and pungent aroma. There are plenty of varieties of Durian which are hard to differentiate by someone who is even an expert of the said fruit. This study is conducted to utilize Raspberry Pi. It will be used to implement image processing algorithms and to create a portable device to identify the fruit’s variety. Image Processing has been used in today’s modern technology like in medicine, media, or the like, and devices are portable for accessibility. The researcher has considered the usefulness of this study and to further understand and acquire useful information of the portable device that will be created to identify Durian variants. Due to the multiple numbers of Durian varieties, the researcher has to determine 6 variants. As the study focused on the unknown variant, the researcher will use a guide on the datasets that will be needed for the training and testing phase of the software. The whole device would then be inspected and would document the accuracy of each variant. The data that the researcher will need to determine the quality and the accuracy of the software, further training and more testing will be needed to get the required acceptable accuracy percentage.

15 citations

Journal Article•DOI•
Durian recognition based on multiple features and linear discriminant analysis

[...]

Mas Rina Mustaffa1, Nyon Xin Yi1, Lili Nurliyana Abdullah1, Nurul Amelina Nasharuddin1•
Universiti Putra Malaysia1
28 Dec 2018-Malaysian Journal of Computer Science
TL;DR: This work aims to contribute to a new representation method based on multiple features for effective durian recognition, and two features based on shape and texture is considered in this work.
Abstract: Many fruit recognition approaches today are designed to classify different type of fruits but there is little effort being done for content-based fruit recognition specifically focuses on durian species. Durian, known as the king of tropical fruits, have few similar characteristics between different species where the skin have almost the same colour from green to yellowish brown with just slightly different shape and pattern of thorns. Therefore, it is hard to differentiate them with the current methods. It would be valuable to have an automated content-based recognition framework that can automatically represent and recognise a durian species given a durian image as the input. Therefore, this work aims to contribute to a new representation method based on multiple features for effective durian recognition. Two features based on shape and texture is considered in this work. Simple shape signatures which include area, perimeter, and circularity are used to determine the shape of the fruit durian and its base while the texture of the fruit is constructed based on Local Binary Pattern. We extracted these features from 240 durian images and trained this proposed method using few classifiers. Based on 10-fold cross validation, it is found that Logistic Regression, Gaussian Naive Bayesian, and Linear Discriminant Analysis classifiers performed equally well with 100% achievement of accuracy, precision, recall, and F1-score. We further tested the proposed algorithm on larger dataset which consisted of 42337 fruit images (64 various categories). Experimental results based on larger and more general dataset have shown that the proposed multiple features trained on Linear Discriminant Analysis classifier able to achieve 72.38% accuracy, 73% precision, 72% recall, and 72% F1-score.

7 citations

Cites background or methods from "Durian Species Recognition System B..."

  • ...We are extending the work done in [29] to include texture feature so that more effective method can be developed for durian representation....

    [...]

  • ...Experiments conducted on two image dataset (240 durian images and 42337 fruit images) have shown that image descriptor of multiple features (shape-texture) performed better in comparison to shape-only [29] and texture-only descriptors....

    [...]

  • ...Shape-only descriptor on the other hand performed better than texture-only descriptor....

    [...]

  • ...2 Shape Feature Extraction based on Shape Signature The shape signature was adopted from our previous work [29]....

    [...]

  • ...Method / Classifier SVM (%) LR (%) GNB (%) LDA (%) Shape-only [29] 95....

    [...]

Journal Article•DOI•
Recent advances in automatic feature detection and classification of fruits including with a special emphasis on Watermelon (Citrillus lanatus): A review

[...]

Danilo Caceres Hernandez, Ricardo Alonso Sánchez Gutiérrez, Kelvin Kung, Juan Eduardo Godina Rodríguez, Oscar Lao, Kenji Contreras, Kang-Hyun Jo, Javier E. Sanchez-Galan 
01 Jan 2023-Neurocomputing
TL;DR: In this paper , an overview of advances in the task of automatic feature detection and classification of fruits, with and special interest in watermelon (Citrillus lanatus), is provided.
Proceedings Article•DOI•
An Introduction to A Smart Durian Musang King and Durian Kampung Classification

[...]

Nik Mohd Zarifie Hashim, Muhammad Hafizul Azfar Khairil Bahri, Siti Mariam Abd Ghani, Mahmud Dwi Sulistiyo, Khairul Amzar Mohd Kassim, Nik Adilah Hanin Zahri 
24 Jun 2022
TL;DR: In this paper , a simple idea employing CNN to classify the local Durian in Malaysia, Durian Kampung, and the well-known durian, Musang King, was introduced.
Abstract: Fruit classification is a crucial implementation process for identifying the types of fruit in the agricultural field. Traditionally the identifying of the fruit was conducted manually using human power. Classification with the manual method requires a systematic, continuous, and even human eye recognition technology to maintain quality consistency. However, this process and step are considered repetitious and uninteresting for the worker, which infringes a prone to human mistakes. In Malaysia's local exercises, The Malaysian Federal Agricultural Marketing Authority (FAMA) controls a set of six indexes for categorizing various types and categories of tropical fruit available locally. Although a reference for classifying the tropical fruit is available here, a method and reliable classifier that could be implemented universally are still desired for the agricultural player. This paper introduces a simple idea employing CNN to classify the local Durian in Malaysia, Durian Kampung, and the well-known durian, Musang King. Although the work is still in progress, we produced a comparable and reliable result with 80% classification accuracy utilizing the Deep Learning approach.
References
More filters
Book•
Image Processing: Analysis and Machine Vision

[...]

Milan Sonka, Václav Hlaváč, Roger Boyle
01 Jan 1993
TL;DR: The digitized image and its properties are studied, including shape representation and description, and linear discrete image transforms, and texture analysis.
Abstract: List of Algorithms. Preface. Possible Course Outlines. 1. Introduction. 2. The Image, Its Representations and Properties. 3. The Image, Its Mathematical and Physical Background. 4. Data Structures for Image Analysis. 5. Image Pre-Processing. 6. Segmentation I. 7. Segmentation II. 8. Shape Representation and Description. 9. Object Recognition. 10. Image Understanding. 11. 3d Geometry, Correspondence, 3d from Intensities. 12. Reconstruction from 3d. 13. Mathematical Morphology. 14. Image Data Compression. 15. Texture. 16. Motion Analysis. Index.

5,451 citations

"Durian Species Recognition System B..." refers background in this paper

  • ...Image recognition is a process of identifying an object in a digital image [1]....

    [...]

Fruit Recognition using Color and Texture Features

[...]

R. Newlin Shebiah, Alagappa Chettiar
01 Jan 2010
TL;DR: An efficient fusion of color and texture features for fruit recognition is proposed based upon the statistical and co-occurrence features derived from the Wavelet transformed sub- bands.
Abstract: The computer vision strategies used to recognize a fruit rely on four basic features which characterize the object: intensity, color, shape and texture. This paper proposes an efficient fusion of color and texture features for fruit recognition. The recognition is done by the minimum distance classifier based upon the statistical and co-occurrence features derived from the Wavelet transformed sub- bands. Experimental results on a database of about 2635 fruits from 15 different classes confirm the effectiveness of the proposed approach.

159 citations

"Durian Species Recognition System B..." refers background in this paper

  • ...[7] S. Arivazhagan, R. Shebiah, S. Nidhyanandhan, and L. Ganesan, “Fruit recognition using color and texture features,” Journal of Emerging Trends in Computing and Information Sciences, vol. 1, no. 2, pp. 90-94, 2010....

    [...]

  • ...Arivazhagan, Shebiah, Nidhyanandhan, Selva and Ganesan [7] proposed a fruit recognition through the fusion of color and texture features....

    [...]

Journal Article•DOI•
Olive Fruits Recognition Using Neural Networks

[...]

C. Gabriel Gatica1, S. Stanley Best, Jose A. Ceroni1, Gaston Lefranc1•
Pontifical Catholic University of Valparaíso1
01 Jan 2013-Procedia Computer Science
TL;DR: A new method for olive fruit recognition by analyzing RGB images taken from olive trees using a neural networks solution approach for estimating the best harvesting moment of olive trees.

36 citations

"Durian Species Recognition System B..." refers background in this paper

  • ...Previously, there are many existing fruit recognition systems such as mandarin recognition [4] and olive fruits recognition [5]....

    [...]

A Completion on Fruit Recognition System Using K-Nearest Neighbors Algorithm

[...]

Pragati Ninawe
01 Jan 2014
TL;DR: New fruits recognition techniques which combines four features analysis method shape, size and color, texture based method to increase accuracy of recognition and nearest neighbor classification algorithm is introduced.
Abstract: Recognition of several fruit images is major challenges for the computers. Mostly fruit recognition techniques which combine different analysis method like color-based, shaped-based, size-based and texture-based. Different fruit images color and shape values are same, but not robust and effective to recognize and identify the images. We introduce new fruits recognition techniques. This combines four features analysis method shape, size and color, texture based method to increase accuracy of recognition. Proposed method used is nearest neighbor classification algorithm. These methods classify and recognize the fruit images from the nearest training fruit example. In this paper it takes the fruit images as input and then recognition system shows the fruit name. Proposed fruit recognition system analyses, classifies and identifies the Fruit recognition system improves the educational learning purpose sharply for small kids and used grocery store to automate labeling and computing the price.

22 citations

"Durian Species Recognition System B..." refers background or methods or result in this paper

  • ...[6] P. Ninawe and M. S. Pandey, “A completion on fruit recognition system using k-nearest neighbors algorithm,” International Journal of Advanced Research in Computer Engineering & Technology (IJARCET), vol. 3, no. 7, pp. 2352-2356....

    [...]

  • ...We compared our proposed work with the method done by [6]....

    [...]

  • ...Ninawe & Pandey [6] proposed a fruit recognition system using combination of color, shape, texture and size-based features to perform classification of fruit images....

    [...]

  • ...Table 1 shows the summary of the individual accuracy value for 10 folders for our proposed work and the method done by [6]....

    [...]

  • ...This resulted to the achievement of a mean accuracy rate of 100% for the proposed method in comparison to a mean accuracy rate of 95% for the method by [6]....

    [...]

Book Chapter•DOI•
Durian—Durio zibethinus

[...]

Saichol Ketsa1, Saichol Ketsa2•
Royal Society1, Kasetsart University2
01 Jan 2018
TL;DR: Duran is a climacteric fruit that undergoes rapid postharvest changes resulting in a short shelf life at ambient temperature, which is essential for a good quality for consumption.
Abstract: Durian is a famous and popular native fruit of Southeast Asia, known as the King of Fruit. It is considered exceedingly delicious. Durian is a climacteric fruit that undergoes rapid postharvest changes resulting in a short shelf life at ambient temperature. These changes are essential for a good quality for consumption. The fruit is usually consumed fresh, but it can be processed into different products. Nowadays both fresh and processed durians have become popular in both local and export market, possibly because new ways of eating the fruit have been so well received. In addition, a huge amount of inedible husk left has created biomass that can be developed into many innovative products.

13 citations

"Durian Species Recognition System B..." refers background in this paper

  • ...Most of the local fruits are available all year around in the market but some are seasonal such as Durian (Durio zibethinus) [2-3]....

    [...]

Related Papers (5)
Durian recognition based on multiple features and linear discriminant analysis

[...]

28 Dec 2018-Malaysian Journal of Computer Science
Mas Rina Mustaffa, Nyon Xin Yi, Lili Nurliyana Abdullah, Nurul Amelina Nasharuddin 
A new method for fruits recognition system

[...]

22 Sep 2009
Woo Chaw Seng, Seyed Hadi Mirisaee
Fruit Detection with Multiple Features using Fuzzy Logic

[...]

01 Jan 2013
Monika Sharma, Vibhuti P N Jaiswal, Amit Goyal
A Plant Recognition Approach Using Shape and Color Features in Leaf Images

[...]

09 Sep 2013
Ali Caglayan, Oguzhan Guclu, Ahmet Burak Can
Automatic Detection and Grading of Multiple Fruits by Machine Learning

[...]

01 Mar 2020-Food Analytical Methods
Anuja Bhargava, Atul Bansal
Frequently Asked Questions (1)
Q1. What are the contributions in this paper?

This work aims to contribute to an automatic content-based durian species recognition that will be able to assist users in differentiating various species of durian. 

Trending Questions (1)
How can image processing and artificial neural network be used to classify durian species?

The paper proposes a durian species recognition system using global shape representations and the K-Nearest Neighbors algorithm.

See answers from 3 other papers