Das, Kaushik
Text detection and object recognition from scene images using CNN and YOLOv3 - Vol.24(5), Sep-Oct - Gurugram IOSR - International Organization of Scientific Research 2022 - 38-47p.
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.
Computer Engineering
Text detection and object recognition from scene images using CNN and YOLOv3 - Vol.24(5), Sep-Oct - Gurugram IOSR - International Organization of Scientific Research 2022 - 38-47p.
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.
Computer Engineering