An Algorithm for Pre-processing of Areca Nut for Quality Classification

Patil, Sameer; Naik, Aparajita; Sequeira, Marlon; Naik, Gourish M.; Parab, Jivan S.

doi:10.1007/978-3-030-84760-9_8

Cited by 8 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To classify the quality of Areca nut, Patil et al [ 73 ] propose a method where the nut boundary is detected using K-Means segmentation, followed by Canny edge detection. When compared with eight different techniques of image preprocessing, the authors conclude that K-Means segmentation achieves one of the three best results for applications involving Areca nut segregation.…”

Section: Related Workmentioning

confidence: 99%

Graphical Image Region Extraction with K-Means Clustering and Watershed

Jardim

António²,

Mora

2022

J. Imaging

View full text Add to dashboard Cite

With a wide range of applications, image segmentation is a complex and difficult preprocessing step that plays an important role in automatic visual systems, which accuracy impacts, not only on segmentation results, but directly affects the effectiveness of the follow-up tasks. Despite the many advances achieved in the last decades, image segmentation remains a challenging problem, particularly, the segmenting of color images due to the diverse inhomogeneities of color, textures and shapes present in the descriptive features of the images. In trademark graphic images segmentation, beyond these difficulties, we must also take into account the high noise and low resolution, which are often present. Trademark graphic images can also be very heterogeneous with regard to the elements that make them up, which can be overlapping and with varying lighting conditions. Due to the immense variation encountered in corporate logos and trademark graphic images, it is often difficult to select a single method for extracting relevant image regions in a way that produces satisfactory results. Many of the hybrid approaches that integrate the Watershed and K-Means algorithms involve processing very high quality and visually similar images, such as medical images, meaning that either approach can be tweaked to work on images that follow a certain pattern. Trademark images are totally different from each other and are usually fully colored. Our system solves this difficulty given it is a generalized implementation designed to work in most scenarios, through the use of customizable parameters and completely unbiased for an image type. In this paper, we propose a hybrid approach to Image Region Extraction that focuses on automated region proposal and segmentation techniques. In particular, we analyze popular techniques such as K-Means Clustering and Watershedding and their effectiveness when deployed in a hybrid environment to be applied to a highly variable dataset. The proposed system consists of a multi-stage algorithm that takes as input an RGB image and produces multiple outputs, corresponding to the extracted regions. After preprocessing steps, a K-Means function with random initial centroids and a user-defined value for k is executed over the RGB image, generating a gray-scale segmented image, to which a threshold method is applied to generate a binary mask, containing the necessary information to generate a distance map. Then, the Watershed function is performed over the distance map, using the markers defined by the Connected Component Analysis function that labels regions on 8-way pixel connectivity, ensuring that all regions are correctly found. Finally, individual objects are labelled for extraction through a contour method, based on border following. The achieved results show adequate region extraction capabilities when processing graphical images from different datasets, where the system correctly distinguishes the most relevant visual elements of images with minimal tweaking.

show abstract

Section: Related Workmentioning

confidence: 99%

Graphical Image Region Extraction with K-Means Clustering and Watershed

Jardim

António²,

Mora

2022

J. Imaging

View full text Add to dashboard Cite

show abstract

“…A disease detection and classification system based on Android was proposed by Tlhobogang and Wannous [11]. The arecanut diseases can be prevented by using machine learning models, various techniques have been employed such as deep learning [12], convolutional neural network (CNN) [13], [14], image processing [15], [16], K-means [17], [18], support vector machine (SVM) [19], learning and machine perception (LAMP) [20] and real time identification of diseases [21]. Also, a simple practical architecture with three stages illumination normalization, feces detection and trait identification for CNN classification is proposed [22].…”

Section: Introductionmentioning

confidence: 99%

Identification and categorization of diseases in arecanut: a machine learning approach

Hegde

Sadanand

Hegde

et al. 2023

IJEECS

View full text Add to dashboard Cite

Arecanut is one of the prominent commercial crops that are grown worldwide for traditional medicines, furniture, cosmetics, food, veterinary preparations, and textile industries. It experiences a variety of diseases during its existence, from the bottom to the tip. The conventional method for detection of diseases is through visual inspection and it is also necessary to have properly designed laboratories to check these harvests. It is a time consuming and tedious task to inspect these crops across wide acres of plantations. The proposed system has been developed that uses convolutional neural network (CNN) to identify and categorize diseases in arecanuts, trunks and leaves also suggesting effective preventative measures. Proprietary dataset consists of 1,100 photos of healthy and diseased arecas. The ratio between the train and test data is 80:20. Binary cross entropy is employed as the loss function for model construction, with accuracy serving as the metrics and Adam serving as the optimizing function. In identification and categorization of arecanut diseases, the suggested approach was shown to be efficient with 93.05% accuracy.

show abstract

“…The experimental outcome is a 97.65% success rate in GLCM features, a 98.28 percent success rate in Mean Around features, and a 99.05 percent success rate in Mean Around-GLCM features. Sameer Patil et al, [26] proposed a technique for quality classification of arecanut using preprocessing techniques. A Raspberry-Pi board and a 5 Megapixel camera module are used to capture the images.…”

Section: Introductionmentioning

confidence: 99%

A Literature Review of the Detection and Categorization of various Arecanut Diseases using Image Processing and Machine Learning Approaches

Puneeth¹,

Nethravathi

2021

IJAEML

View full text Add to dashboard Cite

Background/Purpose: Every scholarly research project starts with a survey of the literature, which acts as a springboard for new ideas. The purpose of this literature review is to become familiar with the study domain and to assess the work's credibility. It also improves with the subject's integration and summary. This article briefly discusses the detection of disease and classification to achieve the objectives of the study. Objective: The main objective of this literature survey is to explore the different techniques applied to identify and classify the various diseases on arecanut. This paper also recommends the methodology and techniques that can be used to achieve the objectives of the study. Design/Methodology/Approach: Multiple data sources, such as journals, conference proceedings, books, and research papers published in reputable journals, were used to compile the essential literature on the chosen topic and collect information from the arecanuts research centre and many farmers in the south Canara and Udupi districts, before narrowing down the literature that is relevant to the research work. The shortlisted literature was carefully assessed by reading each paper and taking notes as appropriate. The information gathered is then examined to identify the potential gap in the study. Findings/Result: Based on the analysis of the papers reviewed, discussion with farmers and research center officers, it is observed that, not much work is carried out in the field of disease identification and classification on arecanut using machine learning techniques. This survey paper recommends techniques and the methodology that can be applied to identify and classify the diseases in arecanut and to classify them in to healthy and unhealthy. Research limitations/implications: The literature review mentioned in this paper are detection and classification of different diseases in arecanut. Originality/Value: This paper focuses on various online research journals, conference papers, technical books, and web articles. Paper Type: Literature review paper on techniques and methods used to achieve the objectives.

show abstract

An Algorithm for Pre-processing of Areca Nut for Quality Classification

Cited by 8 publications

References 17 publications

Graphical Image Region Extraction with K-Means Clustering and Watershed

Graphical Image Region Extraction with K-Means Clustering and Watershed

Identification and categorization of diseases in arecanut: a machine learning approach

A Literature Review of the Detection and Categorization of various Arecanut Diseases using Image Processing and Machine Learning Approaches

Contact Info

Product

Resources

About