Indoor/Outdoor Deep Learning Based Image Classification for Object Recognition Applications
Main Article Content
Abstract
With the rapid development of smart devices, people's lives have become easier, especially for visually disabled or special-needs people. The new achievements in the fields of machine learning and deep learning let people identify and recognise the surrounding environment. In this study, the efficiency and high performance of deep learning architecture are used to build an image classification system in both indoor and outdoor environments. The proposed methodology starts with collecting two datasets (indoor and outdoor) from different separate datasets. In the second step, the collected dataset is split into training, validation, and test sets. The pre-trained GoogleNet and MobileNet-V2 models are trained using the indoor and outdoor sets, resulting in four trained models. The test sets are used to evaluate the trained models using many evaluation metrics (accuracy, TPR, FNR, PPR, FDR). Results of Google Net model indicate the high performance of the designed models with 99.34% and 99.76% accuracies for indoor and outdoor datasets, respectively. For Mobile Net models, the result accuracies are 99.27% and 99.68% for indoor and outdoor sets, respectively. The proposed methodology is compared with similar ones in the field of object recognition and image classification, and the comparative study proves the transcendence of the propsed system.
Received 29/11/2023
Revised 02/04/2023
Accepted 04/04/2023
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
References
Lv H, Shi S, Gursoy D. A look back and a leap forward: a review and synthesis of big data and artificial intelligence literature in hospitality and tourism. J Hosp Mark Manag. 2022; 31(2): 145-75. https://doi.org/10.1080/19368623.2021.1937434
Rozenwald MB, Galitsyna AA, Sapunov GV, Khrameeva EE, Gelfand MS. A machine learning framework for the prediction of chromatin folding in Drosophila using epigenetic features. Peer J Comput Sci. 2020; 6(30). https://doi.org/10.7717/peerj-cs.307
Sharma N, Sharma R, Jindal N. Machine learning and deep learning applications-a vision. Glob Trans Proc. 2021; 2(1): 24-8. https://doi.org/10.1016/j.gltp.2021.01.004
Alzubaidi L, Zhang J, Humaidi AJ, Al-Dujaili A, Duan Y, Al-Shamma O, et al. Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. J Big Data. 2021; 8(1): 1-74. DOI:10.1186/s40537-021-00444-8
Adeel A, Gogate M, Hussain A. Contextual deep learning-based audio-visual switching for speech enhancement in real-world environments. Inf Fusion. 2020; 1(59): 163-70. https://doi.org/10.1016/j.inffus.2019.08.008
Tian H, Chen SC, Shyu ML. Evolutionary programming based deep learning feature selection and network construction for visual data classification. Inf Syst Front. 2020 Oct; 22(5): 1053-66. https://doi.org/10.1007/s10796-020-10023-6
Lee SB, Gui X, Manquen M, Hamilton ER. Use of training, validation, and test sets for developing automated classifiers in quantitative ethnography. Int Conf Quant Ethn. 2019; 117-127. https://doi.org/10.1007/978-3-030-33232-7_10
Vishwakarma M, Singh HP, Kumar N, Arora M. The Need of Smart Guidance Systems for Blind People in the World. Proc Int Conf Big Data Mach Learn App. 2021; 191-195. https://doi.org/10.1007/978-981-15-8377-3_17
Durgadevi S, Thirupurasundari K, Komathi C, Balaji SM. Smart machine learning system for blind assistance. Int Conf Power Energy Control Trans Syst. IEEE. 2020; 1-4. https://doi.org/10.1109/ICPECTS49113.2020.9337031
Tapu R, Mocanu B, Zaharia T. DEEP-SEE: Joint object detection, tracking and recognition with application to visually impaired navigational assistance. Sensors. 2017; 17(11): 2473. https://doi.org/10.3390/s17112473
Yadav AV, Verma SS, Singh DD. Virtual Assistant for blind people. Int J Adv Sci Res Eng Trends. 2021; 6(5):156-159. http://ijasret.com/VolumeArticles/FullTextPDF/831_36.VIRTUAL_ASSISTANT_FOR_BLIND_PEOPLE.pdf
Ephzibah EP. Assisting Blind People Using Machine Learning Algorithms. Tur. Co. Mat. 2021; 12(8): 3162-70. https://doi.org/10.17762/turcomat.v12i8.4161
Qureshi TA, Rajbhar M, Pisat Y, Bhosale V. AI Based App for Blind People. Int Res J Eng Technol. 2021; 8(03): 2883-7. https://doi.org/10.1177/02646196221131746
Mamun SA, Daud ME, Mahmud M, Kaiser MS, Rossi AL. ALO: AI for least observed people. Int Conf Appl Intell Inform. Springer. 2021; 306-317. https://www.springerprofessional.de/en/alo-ai-for-least-observed-people/19396306
Chaurasia MA, Rasool S, Afroze M, Jalal SA, Zareen R, Fatima U, et al. Automated Navigation System with Indoor Assistance for Blind. In Contactless Healthcare Facilitation and Commodity Delivery Management During COVID 19 Pandemic. Springer, Singapore. 2022; 119-128. https://doi.org/10.1007/978-981-16-5411-4_10
Mone S, Salunke N, Jadhav O, Barge A, Magar N. Machine Learning Based Computer Vision Application for Visually Disabled People. Int J Sci Res Comput Sci Eng Inf Technol. 2021; 7(3): 488-494. https://doi.org/10.32628/CSEIT2173130
Wang K, Chen CM, Hossain MS, Muhammad G, Kumar S, Kumari S. Transfer reinforcement learning-based road object detection in next generation IoT domain. Comput Netw. 2021; 193:1-12. https://doi.org/10.1016/j.comnet.2021.108078
Bouteraa Y. Design and Development of a Wearable Assistive Device Integrating a Fuzzy Decision Support System for Blind and Visually Impaired People. Micromachines. 2021; 12(9): 1082. https://doi.org/10.3390/mi12091082
Periša M, Peraković D, Cvitić I, Krstić M. Innovative ecosystem for informing visual impaired person in smart shopping environment: IoT Shop. Wirel Netw. 2022; 28(1): 469-79. https://doi.org/10.1007/s11276-021-02591-5
Dhou S, Alnabulsi A, Al-Ali AR, Arshi M, Darwish F, Almaazmi S, et al. An IoT machine learning-based mobile sensors unit for visually impaired people. Sensors. 2022; 22(14): 5202. https://doi.org/10.3390/s22145202
Zhang E, fruit recognition dataset. Kaggle. 2022. [Online]. https://www.kaggle.com/datasets/sshikamaru/fruit-recognition .
Buyukkinaci M., fruit images for object detection dataset. Kaggle. 2018. https://www.kaggle.com/datasets/mbkinaci/fruit-images-for-object-detection .
Roy P, Ghosh S, Bhattacharya S, Pal U. Natural images dataset. Kaggle, 2018. https://www.kaggle.com/datasets/prasunroy/natural-images .
Annamraju. Weapon detection dataset. Kaggle. 2019. https://www.kaggle.com/datasets/abhishek4273/gun-detection-dataset .
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, et al. Going deeper with convolutions. Proc. IEEE conf Comput Vis Pattern Recognit. 2015: 1-9. https://doi.org/10.48550/arXiv.1409.4842
Hub T. Convolutional neural network architectures. Principles and Labs for Deep Learning. 2021: 6: 201. https://doi.org/10.1016/C2020-0-03408-0
AL-Huseiny MS, Sajit AS. Transfer learning with GoogLeNet for detection of lung cancer. Indones J Electr Eng. 2021; 22(2): 1078-86. http://doi.org/10.11591/ijeecs.v22.i2.pp1078-1086
Sharma S, Kumar H. Detection and classification of plant diseases by Alexnet and GoogleNet deep learning architecture. Int J Sci Res Eng Trends. 2022; 8(1): 218-23. https://ijsret.com/wp-content/uploads/2022/01/IJSRET_V8_issue1_120.pdf
Zakaria N, Mohamed F, Abdelghani R, Sundaraj K. VGG16, ResNet-50, and GoogLeNet Deep Learning Architecture for Breathing Sound Classification: A Comparative Study. Int Conf Artif Intell Cyber Secur Syst. IEEE. 2021:1-6. https://doi.org/10.1109/AI-CSP52968.2021.9671124
Mayya A, Khozama S. A. Novel Medical Support Deep Learning Fusion Model for the Diagnosis of COVID-19. Int Conf Adv Trends Multidiscip Res Innov. IEEE. 2020: 1-6. https://doi.org/10.1109/ICATMRI51801.2020.9398317
Abdullah TH, Alizadeh F, Abdullah BH. COVID-19 Diagnosis System using SimpNet Deep Model. Baghdad Sci J. 2022; 19(5): 1078-1089. DOI: http://dx.doi.org/10.21123/bsj.2022.19.4.ID0000.
Zaki SM, Jaber MM, Kashmoola MA. Diagnosing COVID-19 Infection in Chest X-Ray Images Using Neural Network. Baghdad Sci J. 2022; 19(6): 1356-1361. DOI: https://dx.doi.org/10.21123/bsj.2022.5965.
Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC. Mobilenetv2: Inverted residuals and linear bottlenecks. Proc IEEE conf Comput Vis Pattern Recognit. 2018: 4510-4520. https://doi.org/10.48550/arXiv.1801.04381
Feigenbaum J J. A machine learning approach to census record linking. Harvard University. 2016. https://ranabr.people.stanford.edu/sites/g/files/sbiybj26066/files/media/file/machine_learning_approach.pdf