Welcome to Francis Academic Press

Academic Journal of Computing & Information Science, 2019, 2(3); doi: 10.25236/AJCIS.020308.

Leaf Contour Recognition Using Hash Learning

Author(s)

Shuman Pan, Tao Li, Yichen Yin

Corresponding Author:
Shuman Pan
Affiliation(s)

College of Science, Beijing Forestry University, Beijing 100083, China

Abstract

In the era of big data, hash learning has gained wide attention in large-scale images classification and recognition. In this paper, we identify the type of leaves by hash learning. Firstly, we process original leaf images into contour images and calculate the values of eight geometric feature for each image. Then, we set optimal thresholds for each feature and perform hash mapping. Finally, the type of leaves is determined by calculating the similarity of their hash codes. We conduct an experiment on 14 types of leaves and use one deep learning model as a comparative experiment. The results show that our method has higher recognition accuracy and recognition efficiency as well as reduces the overhead of data storage and transmission.

Keywords

Leaf recognition, image processing, shape features, hash learning

Cite This Paper

Shuman Pan, Tao Li, Yichen Yin. Leaf Contour Recognition Using Hash Learning. Academic Journal of Computing & Information Science (2019), Vol. 2, Issue 3: 68-74. https://doi.org/10.25236/AJCIS.020308.

References

[1] CHEN Liangxi, WANG Bin. Comparative study of leaf image recognition algorithms based on shape features[J]. Computer Engineering and Applications, 2017, 53(9):17-25.
[2] Hua Qiang, Guo Xinxin, Zhang Feng, et al. Hash retrieval algorithm based on random forest[J]. Computer Science and Exploration, 2019(7):1174-1183.
[3] Li Wujun, Zhou Zhihua. Big Data Hash Learning: Current Situation and Trends [J]. Science Bulletin, 2015, 60(Z1): 485-490.
[4] SG Wu, FS Bao, EY Xu, Y. Wang, Y. Chang and Q. Xiang. A Leaf Recognition Algorithm for Plant Classification Using Probabilistic Neural Network [M]. 2007 IEEE International Symposium on Signal Processing and Information Technology, Giza, 2007, pp. 11-16.
[5] Moghaddam, Reza Farrahi, and M. Cheriet. AdOtsu: An adaptive and parameterless generalization of Otsu's method for document image binarization[J]. Pattern Recognition, 2012, 45(6):2419-2431.
[6] ZHU Ji-chao, LU Peng. A large-scale image retrieval method based on shape features[J]. Software, 2012, 33(12): 299-304.
[7] WANG Xiaofeng, HUANG Deshuang, DU Jixiang, ZHANG Guojun.Study on feature extraction and recognition of leaf image[J].Computer Engineering and Applications, 2006(03):190-193.
[8] Yuan Peisen, Zhang Yong, Li Meiling, et al. Research on trademark image retrieval based on deep hash learning[J]. Journal of East China Normal University(Natural Science), 2018, 201(05): 180-190.
[9] Zuo Xin, Shen Jifeng, Yu Hualong, Gao Shang, Xu Dan, Hu Chunlong.Image retrieval method based on hash coding learning[J]. Journal of Jiangsu University of Science and Technology (Natural Science Edition), 2015, 29(6): 567 -573.