Xunfei Li
ABSTRACT
This paper proposes a method for segmenting examination paper questions from the perspective of intelligent image processing. In terms of image preprocessing, firstly, the black area in the examination paper is extracted using the OTSU and adaptive threshold segmentation methods, followed by the extraction of edge contours using the sobel operator. To obtain the text and illustrations in the paper more accurately and completely, the contours are further enhanced using morphological operation to determine the areas containing the question items. Regarding the segmentation of the examination paper questions, the question areas are selected based on their aspect ratios, thus excluding the parts of option or illustration. Finally, a complete examination paper questions is determined by analyzing the top, bottom, left and right edge of the two adjacent questions areas, each complete question is segmented and displayed using rectangular bounding boxes.
- Hu Xiang, 2019, “Design and Implementation of Examination Paper Intelligent Assistant Marking System”, Huazhong University of Science and Technology, DOI:10.27157/d.cnki.ghzku.2019.003863.Google Scholar
Cross Ref
- Guo Leibin, 2020, “A Research and Implementation of Mathematical Papers’ Layout Segmentation Algorithm”, University of Electronic Science and Technology, DOI:10.27005/d.cnki.gdzku.2020.003195.Google ScholarCross Ref
- Ji He, Chen Yajun, Liu Xue, Ma Deng, 2022, “Design of drug box detection system based on machine vision”, Wireless Internet Technology,19(06):76-77.Google Scholar
- ZHONG Qiao, 2017, “Text Line Segmentation and Correction on Scanned Image based on Graph Theory”, Hunan University.Google Scholar
- Zhang Jiaying, 2019. “Design of an intelligent recognition system for test papers based on machine vision” [J]. electronic production,2019(14):22-24.DOI:10.16589/j.cnki.cn11-3571/tn.2019.14.008.Google ScholarCross Ref
- ZHANG Yi, KUANG Yi, WANG Mei, HUANG Zhi−yuan, HU Song, 2020, “Human Contour Detection Algorithm Based on OpenCV”, Computer technology and development, 2020, 30(08).Google Scholar
- Muthukrishnan.R, M.Radha, 2011, “Edge Detection Techniques For Image Segmentation”, International Journal of Computer Science and Information Technology 3(6):259-267, DOI:10.5121/ijcsitGoogle ScholarCross Ref
- LEI De-chao, REN Shou-hua, 2022 “Analysis and Research of License Plate Recognition System Based on OpenCV Image Processing”, College of information and electrical engineering, Heilongjiang Bayi Agricultural University,30(04), DOI:10.19414/j.cnki.1005-1228.2022.04.010.Google ScholarCross Ref
- Mohammad Hosein Jafari, Shadrokh Samavi, 2015, “Iterative Semi-Supervised Learning Approach for Color Image Segmentation”, 9th Iranian Conference on Machine Vision and Image Processing, DOI:10.1109/IranianMVIP.2015.7397508.Google ScholarCross Ref
- GONG Jiamin, ZHAO Mengkai, SUN Yibin, JIANG Jiewei, 2022, “ZHANG Kaize Test question automatic segmentation method based on named entity recognition”, Transducer and Microsystem Technologies, 2022, DOI:10.13873/J.1000-9787(2022)05-0135-05Google ScholarCross Ref
Index Terms
- A segmentation method for examination paper questions
Recommendations
IFCM Based Segmentation Method for Liver Ultrasound Images
In this paper we have proposed an iterative Fuzzy C-Mean (IFCM) method which divides the pixels present in the image into a set of clusters. This set of clusters is then used to segment a focal liver lesion from a liver ultrasound image. Advantage of ...
A marker-based watershed method for X-ray image segmentation
Digital X-ray images are the most frequent modality for both screening and diagnosis in hospitals. To facilitate subsequent analysis such as quantification and computer aided diagnosis (CAD), it is desirable to exclude image background. A marker-based ...
Image Segmentation Method with Positron Emission Tomography Time Sequence Images
IBICA '11: Proceedings of the 2011 Second International Conference on Innovations in Bio-inspired Computing and ApplicationsPositron emission tomography(PET)images are often used to detect physiology function.However,PET images have more blurs than anatomic images,such as magnetic resonance imaging(MRI)and computed tomography(CT).With the graylevel of PET images,Doctors need ...
Comments