A Hybrid Deep Learning Approach for Accurate and Efficient Object Detection
DOI:
https://doi.org/10.63949/Keywords:
- Object detection,
- Deep Learning,
- YOLO,
- CNN
Abstract
Humans can easily identify multiple objects in an image or video but for computers, it is very difficult to identify. The procedure of precisely detecting and promptly recognizing items is quite challenging. However, with the assistance of diverse object detection algorithms, we can now do this work with utmost precision. The proposed method achieved an accuracy of 0.78 to 0.84 on various objects. The advantage of embedding mask RCNN and yolo v7 was achieved with a good precision value. The experimental results were published by masking the specific object and masking the background of the image. The Advantage of using Embedded with Mask R-CNN and YOLO v7 is that it achieves a good precision value. The experimental results were published with masking applied to a specific object and its background. The proposed method concluded that, with YOLO v7, we could reduce the computational effort by 30% and parameter optimization by 40% compared to the existing method.
Downloads
References
[1]. Brownlee, J. (2019). Deep learning for computer vision: Image classification, object detection, and face recognition in Python. Machine Learning Mastery.
[2]. Xiao, Y., Tian, Z., Yu, J., Zhang, Y., Liu, S., Du, S., & Lan, X. (2020). A review of object detection based on deep learning. Multimedia Tools and Applications, 79(33), 23729–23791.
[3]. Bai, Q., Li, S., Yang, J., Song, Q., Li, Z., & Zhang, X. (2020). Object detection recognition and robot grasping based on machine learning: A survey. IEEE Access, 8, 181855–181879.
[4]. Talukdar, J., Gupta, S., Rajpura, P. S., & Hegde, R. S. (2018). Transfer learning for object detection using state-of-the-art deep neural networks. In Proceedings of the 5th International Conference on Signal Processing and Integrated Networks (SPIN) (pp. 78–83). IEEE.
[5]. Vijayakumar, A., & Vairavasundaram, S. (2024). YOLO-based object detection models: A review and its applications. Multimedia Tools and Applications, 83(35), 83535–83574.
[6]. Zhou, Y. (2024). A YOLO-NL object detector for real-time detection. Expert Systems with Applications, 238, 122256.
[7]. Kang, S., Hu, Z., Liu, L., Zhang, K., & Cao, Z. (2025). Object detection YOLO algorithms and their industrial applications: Overview and comparative analysis. Electronics, 14(6), 1104.
[8]. Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2016). Region-based convolutional networks for accurate object detection and segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(1), 142–158.
[9]. Cao, C., Wang, B., Zhang, W., Zeng, X., Yan, X., Feng, Z., Liu, Y., & Wu, Z. (2019). An improved Faster R-CNN for small object detection. IEEE Access, 7, 106838–106846.
[10]. Steno, P., Alsadoon, A., Prasad, P. W. C., Al-Dala’in, T., & Alsadoon, O. H. (2021). A novel enhanced region proposal network and modified loss function: Threat object detection in secure screening using deep learning. The Journal of Supercomputing, 77(4), 3840–3869.
[11]. Zheng, Y., Meng, Y., & Jin, Y. (2011). Object recognition using a bio-inspired neuron model with bottom-up and top-down pathways. Neurocomputing, 74(17), 3158–3169.
[12]. Choi, H. T., Lee, H. J., Kang, H., Yu, S., & Park, H. H. (2021). SSD-EMB: An improved SSD using enhanced feature map block for object detection. Sensors, 21(8), 2842.
[13]. Hou, Y., Wu, Z., Cai, X., & Zhu, T. (2024). The application of improved DenseNet algorithm in accurate image recognition. Scientific Reports, 14(1), 8645.
[14]. Kumar, P., & Alwakid, G. N. (2024). Improved feature extraction and object detection accuracy with the novel DenseNet algorithm compared to the SqueezeNet algorithm in remote sensing images. In Proceedings of the IEEE 9th International Conference on Engineering Technologies and Applied Sciences (ICETAS) (pp. 1–7). IEEE.
[15]. Weng, X., Ma, Q., Li, Q., & Wang, W. (2025). Improved Mask R-CNN algorithm: Multi-ore detection and positioning based multi-sensor fusion in complex field environment. Measurement, 246, 116602.
