Publication

Abstract : With the emergence of the Industry 4.0 known as “smart factory”, visual intelligence plays a vital role in various automation-related applications. Entrenched texts in images give plenty of information, which can be utilized in many applications. Various methods and technologies are existing in the realm of text extraction from the images. But due to diversity in arrangement of texts, scene background, shape, size, space, style variations, it is still a challenging task. In the past years, many researchers have been independently analyzing and solving issues related to detection and recognition of texts embedded in natural Images. This paper focuses on an end-to-end deep learning model for text detection and recognition in vehicle number plates. The proposed model’s objective is to read text information in challenging car number plates. The model has been compared across state-of-the-art models to understand its advantages and limitations in cases of horizontal, perspective texts along with Indian/foreign car number plates. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.