Abstract: Object detection and text recognition, which is otherwise called Optical Character Recognition (OCR), is an emerges as an active area of research because of the quick development with many existing applications. With the fast improvement in the Deep Learning (DL),various powerful tools which can able to learn semantic, high-level, deeper features to tackle the problems in the traditional methods. However, these methods are generally deterministic and gives deterministic output. In this paper, a new DL based object detection and text detection methods was introduced with a novel hybrid activation function. The proposed detection model detects the text and object with high precision rate..
Keywords: Object detection, text detection, real-time images, Deep Learning (DL), hybrid activation function
[1]. Abas, S. M., & Abdulazeez, A. M. (2021). Detection and Classification of Leukocytes in Leukemia using YOLOv2 with CNN. Asian Journal of Research in Computer Science, 64-75.
[2]. Baimukashev, D., Zhilisbayev, A., Kuzdeuov, A., Oleinikov, A., Fadeyev, D., Makhataeva, Z., & Varol, H. A. (2019). Deep learning based object recognition using physically-realistic synthetic depth scenes. Machine Learning and Knowledge Extraction, 1(3), 883-903.
[3]. Belongie, S., Malik, J., &Puzicha, J. (2002). Shape matching and object recognition using shape contexts. IEEE transactions on pattern analysis and machine intelligence, 24(4), 509-522.
[4]. Busta, M., Neumann, L., & Matas, J. (2015). Fastext: Efficient unconstrained scene text detector. In Proceedings of the IEEE international conference on computer vision (pp. 1206-1214).
[5]. Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., &Zagoruyko, S. (2020, August). End-to-end object detection with transformers. In European conference on computer vision (pp. 213-229). Springer, Cham.
