A digital image recommendation system using Semantic Segmentation
DOI:
https://doi.org/10.33387/ijeeic.v3i2.11397Keywords:
Semantic segmentation, Pearson Correlation Coefficient, recommendation system, Global average poolingAbstract
The research aims to determine the nature and features of a digital image in order to suggest or recommend relative images (candidate) to the image (query) that is determined by the user which may contain high scientific or valuable contents. The proposed method processes the semantic segmentation firstly, then computing the feature similarity, by segmenting the image into meaningful object regions then extracting isolating features for the determined objects, then the system will enhance the matching range between the recommendation query and the output of the semantic level. The sample was consisting of 1380 images based on 70/30 split with selected 3 labels (cars, persons and trees). The preprocessing step has been applied where the features were extracted from the determined image in order to determine its contents then we can recommend (candidate) the images with the relative features, this process is applied using the concept of semantic segmentation, where the procedure is partitioned into several steps: The first step includes grouping (cars, persons and trees) images from multiple online and real-world datasets, the grouped raw data that can be processed by the system normalization have been processed using Min-Max normalization that is used for standardizing the input data. The second step is the feature extraction process which is achieved using a modified VGG-16 net and the fully connected layers have been removed and the output will be a 2-D features map, then we convert this map to a 1-D vector called feature vector using a Global Average Pooling. The next step is obtaining feature labels by applying a Support Vector Machine SVM classifier, then we recommended the images with relative features to the determined (query) image, this step is achieved using a Pearson correlation coefficient. The final step is constructing a Confusion Matrix and applying the (F1-score, Recall, Precision and Accuracy) metrices in order to estimate the performance.
Downloads
References
[1] Shefali Gupta, Meenu Dave, A recommendation system: Trends and Future, International journal of Engineering and Advanced Technology, (IJEAT), Blue Eyes Intelligence Engineering & Sciences Publication, Vol. 8, Issue 6S3, pp. 1361-1364, 2019, ISSN: 2249-8958.
[2] He, X.; Liu, Q.; Jung, S. The Impact of Recommendation System on User Satisfaction: A Moderated Mediation Approach. J. Theor. Appl. Electron. Commer. Res. 2024, Vol.19, pp.448–466, DOI: 10.3390/ jtaer19010024.
[3] Vicky Rolanda, Teddy Surya Gunawan and Wanayumini, Content-Based Filtering Recommendation System using Categories Search Engine, IJRVOCAS, 2023, Vol. 2, No. 4, Special issue- INCOSTIG, pp. 120-125, DOI: 10.53893.
[4] Krzysztof Wolk, Marek S. Tatara, A Review of Semantic Segmentation and Instance Segmentation Techniques in Forestry using LiDAR and Imagery Data, MDPI Electronics, 2024, Vol. 13, No. 20, 4139, DOI: 10.3390/electronics13204139.
[5] Aakanksha, Shanu Sharma, Semantic segmentation: Systematic Analysis from state-of-the-Art Techniques to Advance Deep Networks, Journal of Information Technology Research, 2022, Vol. 15, Issue 1, pp.1-28, DOI: 10.4018/JITR.299388.
[6] Venkata S., Bonthu K, Lingamallu R., Bisht D, Chhabra S, " Content Based Image Retrieval using Deep Learning", AIP Conference proc., 2025, 3157, 030003, DOI: 10.1063/5.0261658.
[7] M.K. Kar, M.K. Nath, and D.R.Neog, A Review on Progress in Semantic Image Segmentation and Its Application to Medical Images, SN Computer Science, 2021, Vol.2, No.5, DOI: 10.1007/s42979-021-00784-5.
[8] Yutong Li, The Application of Semantic Segmentation on 2D images, Highlights in Science, Engineering and Technology, IFMPT, 2023, Vol.31, pp.88-96.
[9] Abhishek Thakur, Shamneeh Sharma and Tushar Sharma, "Design of Semantic Segmentation Algorithm to classify Forged Pixels", 12th IEEE International Conference on Communication System and Networks Technologies, 2023, pp.409-413, DOI: 10.1109/csnt.2023.73.
[10] Muqing Li, Ziyi Zhu, and others, "Research on Image Classification and Semantic Segmentation Model based on Convolutional Neural Network", Journal of Computing and Electronic Information Management, 2024, Vol. 12, No. 3, pp. 95-100, DOI: 10.54097/qg7hakzu.
[11] Khaleghian S, Ullah H, and others, "Sea Ice Classification of SAR Imagery based on Convolution Neural Network", Remote Sens., 2021, Vol. 13, 1734, pp.1-20, DOI: 10.3390/rs13091734.
[12] Mogan J N, Lee C P, and others, "VGG16-MLP:Gait Recognition with Fine-Tuned VGG-16 and Multilayer Perception", Appl. Sci., 2022, Vol. 12, 7639, pp.1-12, DOI: 10.3390/app12157639.
[13] Pavel L., Nataliya S, Nikolay N, Maxim B, "High-Speed Wavelet Image Processing using Winograd method with Downsampling", MDPI Mathematics, 2023, Vol. 11, No. 22, 4644, DOI: 10.3390/math11224644.
[14] Tae-Wan Kim, Keun-Chang Kwak, "Pixel-Level Fuzzy Rule Attention Maps for Interpretable MRI Classification", 2025, Vol. 17, 2187, DOI: 10.3390/sym17122187.
[15] Pandey S., Mishra P., " An efficient image classification using SVM, CNN", International journal of Computer Applications ICAIDSC, 2025, Vol.1, pp. 5-10, DOI: 10.5120/icaidsc202403.
[16] Jonatha Sousa Pimentel, Raydonal Ospina, Anderson Ara, "A Novel Fusion Support Vctor Machine integrating weak and sphere models for classification challenges with massive data", Decision Analytics Journal, 2024, Vol.11, DOI: 10.1016/j.dajour.2024.100457.
[17] Guido R, Ferrisi S, Lofaro D and Conforte D, "An Overview on the advancement of Support Vector Machine in Healthcare Applications: A Review", Information, 2024, Vol. 15, No. 4, 235, DOI: 10.3390/info15040235.
[18] James G, Umoren I., Ekong A., "Analysis of Support Vector Machine and Random Forest models for classification of the impact of technodtress in covid and post-covid era", Journal of the Nigerian Society of Physical Sciences, 2024, Vol. 6, No. 3, DOI: 10.46481`/jnsps.2024.2102.
[19] Fahmy Amin, Moahmoud, "Confusion Matrix in Binary Classification Problems: A Step-by-Step Tutorial", Journal of Engineering Research, 2022, Vol. 6, No. 5, Article1, pp.1-12.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal Of Electrical Engineering and Inteligent Computing

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Privacy Statement
How the International Journal of Electrical Engineering and Intelligent Computing (IJEEIC) collects, uses, and protects personal data
1. Our Commitment
The names and email addresses entered on this journal site are used exclusively for the stated purposes of this journal and are not made available for any other purpose or to any other party.
This statement explains what personal data IJEEIC collects through its website, why it is collected, and how it is protected. IJEEIC handles personal data in line with Indonesian Law No. 27 of 2022 on Personal Data Protection.
2. Data We Collect
3. How We Use Your Data
- To manage submissions, peer review, editing, and publication of articles.
- To communicate with authors, reviewers, and editors about manuscripts.
- To send journal notifications and announcements that users have subscribed to.
- To publish author names and affiliations with accepted articles.
- To compile anonymous statistics on journal use and readership.
6. Data Retention and Security
- Account data is kept for as long as the account is active, or until the user asks for it to be removed.
- Data related to published articles is kept permanently as part of the scholarly record.
- Access to the editorial system is restricted to authorized editorial staff, and the website is protected with secure connections (HTTPS).
7. Your Rights
- Access and correction: you can view and update your personal details at any time by logging in and editing your profile.
- Deletion: you can ask the editorial office to delete your account and personal data. Data linked to published articles cannot be removed from the scholarly record.
- Unsubscribe: you can stop receiving journal notifications from your profile settings.
8. Contact
Questions or requests about personal data can be sent to:
Editorial Office of IJEEIC
Department of Electrical Engineering, Faculty of Engineering, Universitas Khairun
Jl. Yusuf Abdulrahman No. 53, Gambesi, Ternate, North Maluku, Indonesia
Email: ijeeic.unkhair@gmail.com · Contact page

