Automatic Plant Organ Detection from Images using Convolutional Neural Networks

Nguyễn Thị Thanh Nhàn, Lê Thị Lan, Vũ Hải, Hoàng Văn Sâm

Abstract


Detecting plant organs from multiple organ images is the first step in a plant identification system. The current researches mainly rely on the assumption that the type of an organ is manually predetermined. Few works have been done on automatic plant organ detection but they are mainly based on hand-designed features. In this paper, we propose a method for automatic plant organ detection using the convolutional neural network. Different experiments on a subset of the PlantClef 2015 have been conducted to evaluate the robustness of the proposed method. The proposed method obtains 27:44% (for seven-organ cases) and 27:69% (for five-organ cases) of improvement in rank-1 over the state-of-the-art work.

DOI: 10.32913/rd-ict.vol1.no39.634


Keywords


Phát hiện bộ phận cây, nhận dạng cây, học sâu, mạng nơ-ron tích chập.

References


James S. Cope, David Corney, Jonathan Y. Clark, Paolo Remagnino, and Paul Wilkin, “Plant species identification using digital morphometrics: A review”, Expert Systems with Applications 39, no. 8, pp 7562-7573, 2012.

Pierre Bonnet et al. “Plant identification: man vs. machine”. Multimedia Tools and Applications, 75(3):1647–1665, jun 2015

Maria-Elena Nilsback and Andrew Zisserman, “Automated flower classification over a large number of classes”, Computer Vision, Graphics & Image Processing. ICVGIP'08. Sixth Indian Conference on, IEEE, 2008, pp. 722-729, 2008.

Yudong Zhang and Lenan Wu, “Classification of fruits using computer vision and a multiclass support vector machine”, Sensors 12, no. 9, pp 12489-12505, 2012.

Zhi-Kai Huang, “Bark classification using rbpnn based on both color and texture feature”, International Journal of Computer Science and Network Security 6, no. 10, pp 100-103, 2006.

Hervé Goeau, Pierre Bonnet, and Alexis Joly, “LifeCLEF Plant Identification Task 2015”, CLEF: Conference and Labs of the Evaluation forum, CLEF2015 Working notes, vol. 1391, 2015.

Thi Thanh-Nhan Nguyen, Thi-Lan Le, Hai Vu, Huy-Hoang Nguyen, and Van-Sam Hoang, “A combination of deep learning and hand-designed feature for plant identification based on leaf and flower images”, Advanced Topics in Intelligent Information and Database Systems, Springer, pp 223-233, 2017.

Alexis Joly, Hervé Goeau, Pierre Bonnet, Vera Bakíc, Julien Barbe, Souheil Selmi, Itheri Yahiaoui, Jennifer Carré, Elise Mouysset, Jean-François Molino, Nozha Boujemaa, Daniel Barthélémy“Interactive plant identification based on social image data”, Ecological Informatics 23, pp 22-34, 2014.

Quang-Khue Nguyen, Thi-Lan Le, and Ngoc-Hai Pham, “Leaf based plant identification system for android using surf features in combination with bag of words model and supervised learning”, International Conference on Advanced Technologies for Communications (ATC 2013), pp 404-407, 2013.

Neeraj Kumar, Peter N. Belhumeur, Arijit Biswas, DavidW. Jacobs,W. John Kress, Ida Lopez, and João V. B. Soares, “Leafsnap: A computer vision system for automatic plant species identification”, Computer Vision_ECCV 2012, Springer, pp 502-516, 2012.

Phan Thị Thu Hồng, Đoàn Thị Thu Hà, Nguyễn Thị Thủy, “Ứng dụng phân lớp ảnh chụp lá cây bằng phương pháp máy vecto hỗ trợ”, Tạp chí khoa học và phát triển, tập 11, số 7, pp 1045-1052, 2013.

Hyeon-Joong Yoo, “Deep convolution neural networks in computer vision”, IEIE Transactions on Smart Processing & Computing 4, pp 35-43, 2015.

Sue Han Lee, Chee Seng Chan, Paul Wilkin, and Paolo Remagnino, “Deep-plant: Plant identification with convolutional neural networks”, Image Processing (ICIP), IEEE International Conference on, IEEE, pp 452-456, 2015.

Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich, “Going deeper with convolutions”, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1-9, 2015.

Goëau, Hervé, et al. "Lifeclef plant identification task 2014." CLEF2014 Working Notes. Working Notes for CLEF 2014 Conference, Sheffield, UK, September, pp 15-18, 2014.

Goëau, Hervé, Pierre Bonnet, and Alexis Joly. "Plant identification in an open-world (lifeclef 2016)." CLEF working notes 2016.

Goëau, Hervé, Pierre Bonnet, and Alexis Joly. "Plant identification based on noisy web data: the amazing performance of deep learning (lifeclef 2017)." CEUR Workshop Proceedings, 2017.

Phyu KH, Kutics A, Nakagawa A.“Self-adaptive feature extraction scheme for mobile image retrieval of flowers”Eighth international conference on signal image technology and internet based systems (SITIS), pp 366–373, 2012.

A. Oliva and A. Torralba. “Modeling the shape of the scene : A holistic repre sentation of the spatial envelope”. International Journal of Computer Vision 42, 145–175, 2001.


Full Text: PDF

CƠ QUAN CHỦ QUẢN: BỘ THÔNG TIN VÀ TRUYỀN THÔNG (MIC)
Giấp phép số 69/GP-TTĐT cấp ngày 26/12/2014.
Tổng biên tập: Vũ Chí Kiên
Tòa soạn: 110-112, Bà Triệu, Hà Nội; Điện thoại: 04. 37737136; Fax: 04. 37737130; Email: chuyensanbcvt@mic.gov.vn
Ghi rõ nguồn “Tạp chí Công nghệ thông tin và truyền thông” khi phát hành lại thông tin từ website này