Abstract
Design of the intelligent making system (iMAS) poses a big technical challenge to recognize both printed and handwriting characters from the scanned images. In this paper, we propose an iMAS method based on the attention generative adversarial network (GAN), which innovatively applies the idea of removing raindrops through attention GAN to remove the printed text first, and then generates the image of handwriting text. The proposed method introduces a classical attention model in the visual field and generates the attention maps which focus only on the important areas through recurrent neural network (RNN), and adopts you only look once at object detection (YOLOv3) method to recognize the characters. Experimental results show that the structural similarity (SSIM) of the image generated by attention GAN is 0.89 and the accuracy of recognition is 91.34%.
Highlights
With the increasing applications of artificial intelligence (AI) in various fields, intelligent making system is considered one of effective tools to reduce the workload of teachers and it can ensure the accuracy of scoring of students’ test papers
When measuring the similarity between the generated picture and the real picture, we refer to the idea of [18] to introduce the Structural Similarity (SSIM) of the two images as part of the loss function
In this paper, we have proposed an intelligent making system (iMAS) based on attention generative adversarial network (GAN) to score papers
Summary
With the increasing applications of artificial intelligence (AI) in various fields, intelligent making system (iMAS) is considered one of effective tools to reduce the workload of teachers and it can ensure the accuracy of scoring of students’ test papers. Before applying on you only look once (YOLO), in order to reduce the difficulty of character recognition, we need to remove the printed text from the images of students’ papers, leaving only the handwriting text. Qian et al [15] proposed the method of GAN which is combined with attention model to remove a large number of raindrops in the images. Attention GAN is applied to remove the printed text in the image, which do not need to focus on the paper in the intelligent scoring system, and to leave only the handwritten answers. Attention GAN is trained to generate images of the leaving handwritten answers. These images are used to make the dataset for character recognition.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
