Authors : Pradeep Rao K. B.; G. Lakshmi Prasad; Siddappa P. Harijan; Vishnu D. M.; Shashank B.

Volume/Issue : Volume 10 - 2025, Issue 11 - November

Google Scholar : https://tinyurl.com/434btuzv

Scribd : https://tinyurl.com/yc8hycbf

DOI : https://doi.org/10.38124/ijisrt/25nov1127

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 30 to 40 days to display the article.

Abstract : Scene recognition is a fundamental problem in computer vision that aims to identify and classify the type of environment represented in an image or video frame. The ability to distinguish between indoor and outdoor scenes plays a crucial role in a variety of applications, including autonomous navigation, surveillance systems, robotics, and context-aware computing. This research presents a web-based indoor and outdoor scene recognition system built using a deep learning framework integrated with a Flask front-end interface. The system employs a pre-trained Convolutional Neural Network (CNN) with a ResNet backbone for robust feature extraction and a Softmax classifier for probabilistic scene categorization. Three modes of input (image upload, video upload, and live camera feed) are supported, allowing for real-time and batch inference. The preprocessing pipeline ensures consistent input normalization, while temporal smoothing techniques reduce label flickering in dynamic video streams. Experimental results demonstrate that the proposed system achieves high classification accuracy and stability across multiple scene categories, effectively distinguishing indoor and outdoor environments. The developed framework provides a reliable and extensible foundation for real-world scene understanding applications requiring high accuracy and computational efficiency.

Keywords : Scene Recognition, Indoor–Outdoor Classification, Convolutional Neural Networks (CNN), ResNet, Deep Learning, Computer Vision.

References :

1. Sharma, V., Nagpal, N., Shandilya, A., Dureja, A., & Dureja, A. (2022, December). A practical approach to detect indoor and outdoor scene recognition. In Proceedings of the 4th International Conference on Information Management & Machine Intelligence (pp. 1-10).
2. Surendran, R., Chihi, I., Anitha, J., & Hemanth, D. J. (2023). Indoor scene recognition: an attention-based approach using feature selection-based transfer learning and deep liquid state machine. Algorithms, 16(9), 430.
3. Kumar, B., Gupta, H., Ingale, S. P., & Vyas, O. P. (2023, January). Classification of indoor–outdoor scene using deep learning techniques. In Machine Learning, Image Processing, Network Security and Data Sciences: Select Proceedings of 3rd International Conference on MIND 2021 (pp. 517-535). Singapore: Springer Nature Singapore.   
4. Uckan, T., Aslan, C., & Hark, C. (2025). A Comprehensive Hybrid Approach for Indoor Scene Recognition Combining CNNs and Text-Based Features. Sensors, 25(17), 5350. 
5. Kumari, S., Jha, R. R., Bhavsar, A., & Nigam, A. (2019, September). Indoor–outdoor scene classification with residual convolutional neural network. In Proceedings of 3rd International Conference on Computer Vision and Image Processing: CVIP 2018, Volume 2 (pp. 325-337). Singapore: Springer Singapore. 
6. Bao, Y., & Li, Y. (2022). PNN for indoor and outdoor scene recognition. 2022 14th International Conference on Measuring Technology and Mechatronics Automation (ICMTMA), 392–396.
7. Mao, Y., & Tian, C. (2023). Indoor-Outdoor Scene Recognition Method based on Adaboost-PNN. 1–6.
8. Jassim, O. A., Abed, M. J., & Saied Saied, Z. H. (2023). Indoor/Outdoor Deep Learning Based Image Classification for Object Recognition Applications. Baghdad Science Journal.
9. Nagrale, P. T. (2024). Advanced Deep Learning Techniques for Indoor-Outdoor Scene Recognition Integrating CNN and Edge Detection for Enhanced Classification Accuracy in Dynamic Environments. Deleted Journal, 27(2), 612–631.
10. Jamali, M., Davidsson, P., Khoshkangini, R., Ljungqvist, M. G., & Mihailescu, R.-C. (2024). Specialized indoor and outdoor scene-specific object detection models.
11. Horn, C. (2022). Hybrid Mayfly Lévy Flight Distribution Optimization Algorithm-Tuned Deep Convolutional Neural Network for Indoor–Outdoor Image Classification. International Journal of Image and Graphics.
12. Goel, A., & Singhal, N. (2020). The indoor-outdoor image classification and comparison of machine learning methods using the mpeg-7 descriptors. 9(6), 3797–3802.
13. Zhang, Y., Zhao, F., Shao, W., & Luo, H. (2016). A pervasive indoor and outdoor scenario identification algorithm based on the sensing data and human activity. 240–247.
14. Alameer, A., Degenaar, P., & Nazarpour, K. (2019). Context-Based Object Recognition: Indoor Versus Outdoor Environments (pp. 473–490). Newcastle University.
15. Pakhare, J. D., Uplane, M. D. (2022). Scene Categorization From Indoor-Outdoor Images Using Hybrid MAMF-Based Deep Convolutional Neural Networks. International Journal of Software Innovation10(1), 1–21.