Highly Efficient Machine Learning Approach for Automatic Disease and Color Classification of Olive Fruits
The following ends have been established via an in-depth examination and assessment of numerous prior studies on olive fruit classifications: First, several of these researches rely on the use of an unrelated image library. Since every image features a single fruit with a background that contrasts s...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10419345/ |
| _version_ | 1797243360390414336 |
|---|---|
| author | Nashaat M. Hussain Hassan A. A. Donkol M. Mourad Mabrook A. M. Mabrouk |
| author_facet | Nashaat M. Hussain Hassan A. A. Donkol M. Mourad Mabrook A. M. Mabrouk |
| author_sort | Nashaat M. Hussain Hassan |
| collection | DOAJ |
| description | The following ends have been established via an in-depth examination and assessment of numerous prior studies on olive fruit classifications: First, several of these researches rely on the use of an unrelated image library. Since every image features a single fruit with a background that contrasts sharply with the fruit’s hue, they are all ready for testing. As was previously stated, this issue is unrelated to reality. In practical application, one must deal with a frame that holds hundreds of fruits. To keep the fruits steady, they are put on a conveyor with multiple channels. It’s also notable that the majority of this study offered suggestions for useful technology that could yet be developed. Finally, it is important to emphasize that processing speed data is essential in this type of application and has not been collected in many of these experiments. The presented work deals with a new strategy based on two principles: first, a successful extraction of the fruits from the background; and second, the classification of olive fruits into eight categories based on colors and defects. The fruits were extracted from the backdrop using a modified version of the K-Means technique. The outcomes of the suggested fruit extraction were examined utilizing several assessment techniques. By contrasting the outcomes of pertinent procedures with the suggested proposal for fruit extraction, the efficacy and precision of the proposed method were verified. Depending on why the fruit needed to be separated, there were two stages to the process. Three colors were separated using the SVM algorithm, and five distinct defects were separated using the ANN algorithm Approximately 15,000 photos of olive fruits that were shot straight from the fruit conveyor were included in a robust database that was used in the proposed study to validate the effectiveness of the suggested technology. Efficiency was further validated by contrasting our outcomes with those of related technology. When the fruits were set on a white backdrop, the test accuracy results of the suggested approach showed that it was highly efficient in classifying the fruits in the shortest period; the suggested method had an effectiveness of 99.26% for fruit classification. The most important discovery was that it could classify fruits with an efficiency of 97.25% while they were being put on a fruit conveyor, which was in contrast to other approaches. The unique findings of the study that was presented hold promise for practical implementation. |
| first_indexed | 2024-04-24T18:53:53Z |
| format | Article |
| id | doaj.art-49b4783df63947af90ad10e53be82fb1 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-24T18:53:53Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-49b4783df63947af90ad10e53be82fb12024-03-26T17:46:11ZengIEEEIEEE Access2169-35362024-01-0112356833569910.1109/ACCESS.2024.336229410419345Highly Efficient Machine Learning Approach for Automatic Disease and Color Classification of Olive FruitsNashaat M. Hussain Hassan0https://orcid.org/0000-0002-7556-5466A. A. Donkol1https://orcid.org/0000-0002-2007-8214M. Mourad Mabrook2https://orcid.org/0000-0003-3268-8084A. M. Mabrouk3Faculty of Engineering and Technology, Badr University in Cairo (BUC), Badr City, EgyptCommunication and Electronics Department, Faculty of Engineering, Electrical Engineering, South Valley University, Qena, EgyptSpace Communication Department, Faculty of Navigation Science and Space Technology, Beni-Suef University, Beni Suef, EgyptFaculty of Engineering, King Salman International University (KSIU), South Sinai, El Tor, EgyptThe following ends have been established via an in-depth examination and assessment of numerous prior studies on olive fruit classifications: First, several of these researches rely on the use of an unrelated image library. Since every image features a single fruit with a background that contrasts sharply with the fruit’s hue, they are all ready for testing. As was previously stated, this issue is unrelated to reality. In practical application, one must deal with a frame that holds hundreds of fruits. To keep the fruits steady, they are put on a conveyor with multiple channels. It’s also notable that the majority of this study offered suggestions for useful technology that could yet be developed. Finally, it is important to emphasize that processing speed data is essential in this type of application and has not been collected in many of these experiments. The presented work deals with a new strategy based on two principles: first, a successful extraction of the fruits from the background; and second, the classification of olive fruits into eight categories based on colors and defects. The fruits were extracted from the backdrop using a modified version of the K-Means technique. The outcomes of the suggested fruit extraction were examined utilizing several assessment techniques. By contrasting the outcomes of pertinent procedures with the suggested proposal for fruit extraction, the efficacy and precision of the proposed method were verified. Depending on why the fruit needed to be separated, there were two stages to the process. Three colors were separated using the SVM algorithm, and five distinct defects were separated using the ANN algorithm Approximately 15,000 photos of olive fruits that were shot straight from the fruit conveyor were included in a robust database that was used in the proposed study to validate the effectiveness of the suggested technology. Efficiency was further validated by contrasting our outcomes with those of related technology. When the fruits were set on a white backdrop, the test accuracy results of the suggested approach showed that it was highly efficient in classifying the fruits in the shortest period; the suggested method had an effectiveness of 99.26% for fruit classification. The most important discovery was that it could classify fruits with an efficiency of 97.25% while they were being put on a fruit conveyor, which was in contrast to other approaches. The unique findings of the study that was presented hold promise for practical implementation.https://ieeexplore.ieee.org/document/10419345/Olive fruit pre-processingolives detecting and extractingfeatures extractionsSVM classifierANN classifierhyper parameters tuning |
| spellingShingle | Nashaat M. Hussain Hassan A. A. Donkol M. Mourad Mabrook A. M. Mabrouk Highly Efficient Machine Learning Approach for Automatic Disease and Color Classification of Olive Fruits IEEE Access Olive fruit pre-processing olives detecting and extracting features extractions SVM classifier ANN classifier hyper parameters tuning |
| title | Highly Efficient Machine Learning Approach for Automatic Disease and Color Classification of Olive Fruits |
| title_full | Highly Efficient Machine Learning Approach for Automatic Disease and Color Classification of Olive Fruits |
| title_fullStr | Highly Efficient Machine Learning Approach for Automatic Disease and Color Classification of Olive Fruits |
| title_full_unstemmed | Highly Efficient Machine Learning Approach for Automatic Disease and Color Classification of Olive Fruits |
| title_short | Highly Efficient Machine Learning Approach for Automatic Disease and Color Classification of Olive Fruits |
| title_sort | highly efficient machine learning approach for automatic disease and color classification of olive fruits |
| topic | Olive fruit pre-processing olives detecting and extracting features extractions SVM classifier ANN classifier hyper parameters tuning |
| url | https://ieeexplore.ieee.org/document/10419345/ |
| work_keys_str_mv | AT nashaatmhussainhassan highlyefficientmachinelearningapproachforautomaticdiseaseandcolorclassificationofolivefruits AT aadonkol highlyefficientmachinelearningapproachforautomaticdiseaseandcolorclassificationofolivefruits AT mmouradmabrook highlyefficientmachinelearningapproachforautomaticdiseaseandcolorclassificationofolivefruits AT ammabrouk highlyefficientmachinelearningapproachforautomaticdiseaseandcolorclassificationofolivefruits |