Skip to main content

Research Repository

Advanced Search

A deep action-oriented video image classification system for text detection and recognition

Chaudhuri, Abhra; Shivakumara, Palaiahnakote; Nath Chowdhury, Pinaki; Pal, Umapada; Lu, Tong; Lopresti, Daniel; Hemantha Kumar, G.

A deep action-oriented video image classification system for text detection and recognition Thumbnail


Authors

Abhra Chaudhuri

Pinaki Nath Chowdhury

Umapada Pal

Tong Lu

Daniel Lopresti

G. Hemantha Kumar



Abstract

For the video images with complex actions, achieving accurate text detection and recognition results is very challenging. This paper presents a hybrid model for classification of action-oriented video images which reduces the complexity of the problem to improve text detection and recognition performance. Here, we consider the following five categories of genres, namely concert, cooking, craft, teleshopping and yoga. For classifying action-oriented video images, we explore ResNet50 for learning the general pixel-distribution level information and the VGG16 network is implemented for learning the features of Maximally Stable Extremal Regions and again another VGG16 is used for learning facial components obtained by a multitask cascaded convolutional network. The approach integrates the outputs of the three above-mentioned models using a fully connected neural network for classification of five action-oriented image classes. We demonstrated the efficacy of the proposed method by testing on our dataset and two other standard datasets, namely, Scene Text Dataset dataset which contains 10 classes of scene images with text information, and the Stanford 40 Actions dataset which contains 40 action classes without text information. Our method outperforms the related existing work and enhances the class-specific performance of text detection and recognition, significantly.

Citation

Chaudhuri, A., Shivakumara, P., Nath Chowdhury, P., Pal, U., Lu, T., Lopresti, D., & Hemantha Kumar, G. (2021). A deep action-oriented video image classification system for text detection and recognition. SN Applied Sciences, 3, Article 838. https://doi.org/10.1007/s42452-021-04821-z

Journal Article Type Article
Acceptance Date Sep 22, 2021
Publication Date 2021-11
Deposit Date Feb 2, 2024
Publicly Available Date Feb 5, 2024
Journal SN Applied Sciences
Print ISSN 2523-3971
Publisher Springer
Peer Reviewed Peer Reviewed
Volume 3
Article Number 838
DOI https://doi.org/10.1007/s42452-021-04821-z

Files





You might also like



Downloadable Citations