Claim Missing Document
Check
Articles

Found 9 Documents
Search
Journal : Indonesian Journal of Electrical Engineering and Computer Science

Comparing bags of features, conventional convolutional neural network and AlexNet for fruit recognition Nik Noor Akmal Abdul Hamid; Rabiatul Adawiya Razali; Zaidah Ibrahim
Indonesian Journal of Electrical Engineering and Computer Science Vol 14, No 1: April 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v14.i1.pp333-339

Abstract

This paper presents a comparative study between Bag of Features (BoF), Conventional Convolutional Neural Network (CNN) and Alexnet for fruit recognition.  Automatic fruit recognition can minimize human intervention in their fruit harvesting operations, operation time and harvesting cost.  On the other hand, this task is very challenging because of the similarities in shapes, colours and textures among various types of fruits. Thus, a robust technique that can produce good result is necessary. Due to the outstanding performance of deep learning like CNN and its pre-trained models like AlexNet in image recognition, this paper investigates the accuracy of conventional CNN, and Alexnet in recognizing thirty different types of fruits from a publicly available dataset.  Besides that, the recognition performance of BoF is also examined since it is one of the machine learning techniques that achieves good result in object recognition.   The experimental results indicate that all of these three techniques produce excellent recognition accuracy. Furthermore, conventional CNN achieves the fastest recognition result compared to BoF, and Alexnet.
Evaluation of Color Models for Palm Oil Fresh Fruit Bunch Ripeness Classification Nurbaity Sabri; Zaidah Ibrahim; Dino Isa
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 2: August 2018
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v11.i2.pp549-557

Abstract

This paper investigates the application of eight color models for automatic palm oil Fresh Fruit Bunch (FFB) ripeness classification with multi-class Support Vector Machine (SVM).  Ripeness classification is important during harvesting to ensure that they are harvested during the correct ripe stage for optimum oil production.  Since color is a significant indicator for agriculturists to determine the ripeness of FFB, it is critical to determine the right color model. Eight color models have been investigated namely, HSV, I1I2I3, LAB, XYZ, YCbCr, YIQ, YUV and RGB. Color moments were extracted from each of these color models for the classification of four stages of FFB ripeness that are unripe, under-ripe, ripe and over-ripe.  A database of five hundred images of palm oil FFB has been constructed and experiments showed that YCbCr and YUV outperform the other color models.
Evaluation of CNN, Alexnet and GoogleNet for Fruit Recognition Nur Azida Muhammad; Amelina Ab Nasir; Zaidah Ibrahim; Nurbaity Sabri
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 2: November 2018
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v12.i2.pp468-475

Abstract

Fruit recognition is useful for automatic fruit harvesting. Fruit recognition application can reduce or minimize human intervention during fruit harvesting operation. However, in computer vision, fruit recognition is very challenging because of similar shapes, colors and textures among various fruits. Illuminations changes due to weather condition also leads to a challenging task for fruit recognition. Thus, this paper tends to investigate the performance of basic Convolutional Neural Network (CNN), Alexnet and Googlenet in recognizing nine different types of fruits from a publicly available dataset.  The experimental results indicate that all these techniques produce excellent recognition accuracy, but basic CNN achieves the fastest recognition result compared with Alexnet and Googlenet.
Deep Learning for Roman Handwritten Character Recognition Muhaafidz Md Saufi; Mohd Afiq Zamanhuri; Norasiah Mohammad; Zaidah Ibrahim
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 2: November 2018
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v12.i2.pp455-460

Abstract

The advantage of deep learning is that the analysis and learning of massive amounts of unsupervised data make it a beneficial tool for Big Data analysis. Convolution Neural Network (CNN) is a deep learning method that can be used to classify image, cluster them by similarity, and perform image recognition in the scene. This paper conducts a comparative study between three deep learning models, which are simple-CNN, AlexNet and GoogLeNet for Roman handwritten character recognition using Chars74K dataset. The produced results indicate that GooleNet achieves the best accuracy but it requires a longer time to achieve such result while AlexNet produces less accurate result but at a faster rate.
Flower and leaf recognition for plant identification using convolutional neural network Nurul FatihahSahidan; Ahmad Khairi Juha; Norasiah Mohammad; Zaidah Ibrahim
Indonesian Journal of Electrical Engineering and Computer Science Vol 16, No 2: November 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v16.i2.pp737-743

Abstract

This paper presents flower and leaf recognition for plant identification using Convolutional Neural Network (CNN). In this study, the performance of CNN for plant identification using images of the leaves, flowers and a combination of both are investigated.  Two publicly available datasets, namely Folio leaf dataset and Flower Recognition dataset, have been used for the training and testing purposes.  CNN has been proven to produce excellent results for object recognition but its performance can still be influenced by the type of images and the number of layers of the CNN architecture.   Experimental results indicate that the utilization of leaf images only arrive to the highest accuracy for plant identification compared to the images of flowers only or the combination of both, that are 98%, 85% and 74%, respectively.
Leaf Recognition using Texture Features for Herbal Plant Identification Zaidah Ibrahim; Nurbaity Sabri; Nur Nabilah Abu Mangshor
Indonesian Journal of Electrical Engineering and Computer Science Vol 9, No 1: January 2018
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v9.i1.pp152-156

Abstract

This research investigates the application of texture features for leaf recognition for herbal plant identification.  Malaysia is rich with herbal plants but not many people can identify them and know about their uses.   Preservation of the knowledge of these herb plants is important since it enables the general public to gain useful knowledge which they can apply whenever necessary.  Leaf image is chosen for plant recognition since it is available and visible all the time.   Unlike flowers that are not always available or roots that are not visible and not easy to obtain, leaf is the most abundant type of data available in botanical reference collections.  A comparative study has been conducted among three popular texture features that are Histogram of Oriented Gradients (HOG), Local Binary Pattern (LBP) and Speeded-Up Robust Features (SURF) with multiclass Support Vector Machine (SVM) classifier.  A new leaf dataset has been constructed from ten different herb plants.  Experimental results using the new constructed dataset and Flavia, an existing dataset, indicate that HOG and LBP produce similar leaf recognition performance and they are better than SURF.
Evaluation of basic convolutional neural network and bag of features for leaf recognition Nurul Fatihah Sahidan; Ahmad Khairi Juha; Zaidah Ibrahim
Indonesian Journal of Electrical Engineering and Computer Science Vol 14, No 1: April 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v14.i1.pp327-332

Abstract

This paper presents the evaluation of basic Convolutional Neural Network (CNN) and Bag of Features (BoF) for Leaf Recognition. In this study, the performance of basic CNN and BoF for leaf recognition using a publicly available dataset called Folio dataset has been investigated. CNN has proven its powerful feature representation power in computer vision. The same goes with BoF where it has set new performance standards on popular image classification benchmarks and has achieved scalability breakthrough in image retrieval. The feature that is being utilized in the BoF is Speeded-Up Robust Feature (SURF) texture feature. The experimental results indicate that BoF achieves better accuracy compared to basic CNN.
Convolutional neural network vs bag of features for bambara groundnut leaf disease recognition Hafizatul Hanin Hamzah; Nurbaity Sabri; Zaidah Ibrahim; Dino Isa
Indonesian Journal of Electrical Engineering and Computer Science Vol 14, No 1: April 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v14.i1.pp368-374

Abstract

This paper investigates bambara groundnut leaf disease recognition using two popular techniques known as Convolutional Neural Network (CNN) and Bag of Features (BOF) with Speeded-up Robust Feature (SURF) and Support Vector Machine (SVM) classifier.  Leaf disease recognition has attracted many researchers because the outcome is useful for farmers. One of the crops that provide high income for farmers is bambara groundnut but the leaves are easily infected with diseases especially after the rain.  This could affect the crop productivity.  Thus, automatic disease recognition is crucial.  A new dataset that consists of 400 images of the infected and non-infected leaves of bambara groundnut has been constructed. The experimental results indicate that both of these techniques produce excellent leaf disease recognition accuracy.
Comparison of convolutional neural network and bag of features for multi-font digit recognition Nasibah Husna Mohd Kadir; Sharifah Nur Syafiqah Mohd Nur Hidayah; Norasiah Mohammad; Zaidah Ibrahim
Indonesian Journal of Electrical Engineering and Computer Science Vol 15, No 3: September 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v15.i3.pp1322-1328

Abstract

This paper evaluates the recognition performance of Convolutional Neural Network (CNN) and Bag of Features (BoF) for multiple font digit recognition. Font digit recognition is part of character recognition that is used to translate images from many document-input tasks such as handwritten, typewritten and printed text.  BoF is a popular machine learning method while CNN is a popular deep learning method.  Experiments were performed by applying BoF with Speeded-up Robust Feature (SURF) and Support Vector Machine (SVM) classifier and compared with CNN on Chars74K dataset. The recognition accuracy produced by BoF is just slightly lower than CNN where the accuracy of CNN is 0.96 while the accuracy of BoF is 0.94.