Image-based processing for ripeness classification of oil palm fruit

Septiarini, Anindita; Hamdani, Hamdani; Hatta, Heliza Rahmania; Kasim, Anita Ahmad

doi:10.1109/icsitech46713.2019.8987575

Cited by 37 publications

(21 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dates are sorted into four grades in Southern California and Arizona, USA according to the criteria shown in Table 1 [7]. With proper calibration and segmentation, the size measurement in terms of the length of the date can be measured with high accuracy since the contrast between the background and fruit is fairly high.…”

Section: Date Skin Qualitymentioning

confidence: 99%

“…Guava fruits were classified into four maturity levels using the K-nearest neighbor (KNN) algorithm to analyze color distribution in HSI (Hue, Saturation, and Intensity) color space [3]. Image processing techniques were used for corn seed grading [4], plum fruit maturity evaluation [5], quality assessment of pomegranate fruits [6], and the ripeness of palm fruit [7]. Two grading systems for date maturity [8] and skin quality [9] evaluation were designed specifically for Medjool dates.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Smart Camera for Quality Inspection and Grading of Food Products

et al. 2020

View full text Add to dashboard Cite

Due to the increasing consumption of food products and demand for food quality and safety, most food processing facilities in the United States utilize machines to automate their processes, such as cleaning, inspection and grading, packing, storing, and shipping. Machine vision technology has been a proven solution for inspection and grading of food products since the late 1980s. The remaining challenges, especially for small to midsize facilities, include the system and operating costs, demand for high-skilled workers for complicated configuration and operation and, in some cases, unsatisfactory results. This paper focuses on the development of an embedded solution with learning capability to alleviate these challenges. Three simple application cases are included to demonstrate the operation of this unique solution. Two datasets of more challenging cases were created to analyze and demonstrate the performance of our visual inspection algorithm. One dataset includes infrared images of Medjool dates of four levels of skin delamination for surface quality grading. The other one consists of grayscale images of oysters with varying shape for shape quality evaluation. Our algorithm achieved a grading accuracy of 95.0% on the date dataset and 98.6% on the oyster dataset, both easily surpassed manual grading, which constantly faces the challenges of human fatigue or other distractions. Details of the design and functions of our smart camera and our simple visual inspection algorithm are discussed in this paper.Electronics 2020, 9, 505 2 of 18 or sorting machines for food products on the market have been designed to automate these tasks and have proven to be very successful.Many recent developments were aimed at broad grading applications. For example, a machine learning-based system was built to use color and texture features for tomato grading and surface defect detection [1]. Color and texture features were collected for maturity evaluation, defect detection, size and shape analysis for mangoes [2]. Guava fruits were classified into four maturity levels using the K-nearest neighbor (KNN) algorithm to analyze color distribution in HSI (Hue, Saturation, and Intensity) color space [3]. Image processing techniques were used for corn seed grading [4], plum fruit maturity evaluation [5], quality assessment of pomegranate fruits [6], and the ripeness of palm fruit [7]. Two grading systems for date maturity [8] and skin quality [9] evaluation were designed specifically for Medjool dates. All these recent developments were designed for their unique grading applications. Although some may be easier than others to adapt for similar applications, minor adjustments are needed even for a simple generic solution such as color grading or shape analysis.A comprehensive review of fruit and vegetable quality evaluation systems revealed that many systems use slightly different handcrafted features for even the same applications [10]. For example, twenty-six different color features in four different color spaces and twenty-two texture fe...

show abstract

Section: Date Skin Qualitymentioning

confidence: 99%

mentioning

confidence: 99%

Smart Camera for Quality Inspection and Grading of Food Products

et al. 2020

View full text Add to dashboard Cite

show abstract

“…e data obtained as a result of the segmentation of the images obtained for the determination of the date fruits' ripening stages with the Otsu method was classified with the support vector machines (SVM) method, and an accuracy of 92.5% was achieved on 160 images [15]. In another study, in which 6 features extracted from date fruit images are used, it is stated that the SVM classifier, ANN, random forest (RF), and decision trees (DT) give better results than the classification approaches.…”

Section: Introductionmentioning

confidence: 99%

Classification of Date Fruits into Genetic Varieties Using Image Analysis

Köklü

Kursun

Taşpınar

et al. 2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

A great number of fruits are grown around the world, each of which has various types. The factors that determine the type of fruit are the external appearance features such as color, length, diameter, and shape. The external appearance of the fruits is a major determinant of the fruit type. Determining the variety of fruits by looking at their external appearance may necessitate expertise, which is time-consuming and requires great effort. The aim of this study is to classify the types of date fruit, that are, Barhee, Deglet Nour, Sukkary, Rotab Mozafati, Ruthana, Safawi, and Sagai by using three different machine learning methods. In accordance with this purpose, 898 images of seven different date fruit types were obtained via the computer vision system (CVS). Through image processing techniques, a total of 34 features, including morphological features, shape, and color, were extracted from these images. First, models were developed by using the logistic regression (LR) and artificial neural network (ANN) methods, which are among the machine learning methods. Performance results achieved with these methods are 91.0% and 92.2%, respectively. Then, with the stacking model created by combining these models, the performance result was increased to 92.8%. It has been concluded that machine learning methods can be applied successfully for the classification of date fruit types.

show abstract

“…Iqbal [1] et al proposed to achieve the classification of fruits based on color features of fruits combined with probability distribution functions; Siswantoro [2], Rajasekar [3], et al proposed to classify fruits with the help of KNN(K-Nearest Neighbors) and color and texture features; Yang [4], Ben [5], et al proposed to use logistic regression and inconsistent spectral wavelengths of fruits of the same species before and after ripening features to classify fruits; some other scholars use support vector machines with various features of fruits such as shape, texture, and color to classify and identify fruits, such as Septiarini [6], zhang [7], Liu [8], Lin [9], Castro [10], Qureshi [11], etc. ; Hasan [12], Javel [ 13], Khan [14] and others proposed fruit classification based on fuzzy logic combined with shape and color features.In addition to this, Bani [15] proposed to retrieve images of fruits and vegetables using color, texture features combined with spatial and frequency domains.…”

Section: Introductionmentioning

confidence: 99%

Circular Fruit and Vegetable Classification Based on Optimized GoogLeNet

Song

Fuxiang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

The fruit and vegetable classification problem is an inseparable branch in the field of image recognition. GoogLeNet provides a more ideal solution for the fruit and vegetable classification problem. We use the GoogLeNet network to classify apples, lemons, oranges, pomegranates, tomatoes, and colored peppers. Through experiments, we obtained the training accuracy of GoogLeNet as 96.88%, the testing accuracy as 96%, and the training speed as 11.38 sheets/second. The recognition accuracy of this model can meet the basic recognition requirements, but the training speed is low. Therefore, we decided to optimize GoogLeNet to significantly improve the training speed and further enhance the recognition accuracy of GoogLeNet. We reduced the number of convolutional kernels of GoogLeNet and adjusted the structure of Inception, which reduced the number of parameters of GoogLeNet by nearly 48% and increased the training speed of GoogLeNet from 11.38 to 33.68 sheets/second. To further improve its recognition accuracy, we tried two methods: 1) introducing a new activation function Swish; 2) between convolutional layers, we introduced DropBlock layer; these two methods improved the testing accuracy of GoogLeNet by 2%. Finally, we introduce AlexNet, VGGNet, ResNet18, DenseNet121, and Inception-ResNet to compare with our optimized GoogLeNet. By comparison, we found that our model has incredible performance in ACC, AUC, FPS, Recall, etc.

show abstract

Image-based processing for ripeness classification of oil palm fruit

Cited by 37 publications

References 26 publications

Smart Camera for Quality Inspection and Grading of Food Products

Smart Camera for Quality Inspection and Grading of Food Products

Classification of Date Fruits into Genetic Varieties Using Image Analysis

Circular Fruit and Vegetable Classification Based on Optimized GoogLeNet

Contact Info

Product

Resources

About