PLANT IDENTIFICATION AND RETRIEVAL

Vietnamese medicinal plant retrieval:

Interface of our Vietnamese medicinal plant retrieval
Based on the current methods on plant identification, we have developed a new application for Vietnam: Vietnamese medicinal plant retrieval. Our system provides three main possibilities for searching a given plant: a conventional keyword based search engine, a fully automatic leaf images based plant identification and interactive plant identification with aids of the graphical tool. These search modesare integrated inside a generic framework with interactive user interface that facilitates the use of the system ona very common Android platform. More information can be found at VnMed
This application gots the second prize of Viettel contest for mobile application for heath-care and has been chosen in the finalist of Nhan tai dat viet, 2014 for mobile application.

Publications:
Thi-Lan Le, Duc-Tuan Tran, Van-Nam HoangFully automatic leaf-based plant identification, application for Vietnamese medicinal plant search, [pdf] SoICT, 2014

Multi-organ plant identification:

Fusion of leaf and flower for plant identification.

We investigate different fusion scheme in order to obtain a robust plant identification based on images of multiple organs.

Publications:
DO Thanh Binh, NGUYEN Huy Hoang, NGUYEN Thi Thanh Nhan, VU Hai, TRAN Thi Thanh Hai, LE Thi Lan, Plant identification using late fusion of multi-organ images, The 9th International Conference on Knowledge and Systems Engineering (KSE 2017), IEEE - October 2017.
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, 9th Asian Conference on Intelligent Information and Database Systems, 3-5 April 2017, Kanazawa, Japan.
Thi Thanh Nhan Nguyen, Van Tuan Le, Thi Lan Le, Hai Vu, Natapon Pantuwong, Yasushi Yagi, Flower species identification Using Deep Convolutional Neural Networks, Regional Conference on Computer and Information Engineering (RCCIE), Myamar, Oct 2016.

Kernel and modified kernel descriptor for simple leaf on complex background:

Leaf identification based on Modified Kernel Descriptor and Interactive Segmentation.

Obtained results on ImageClef 2014 dataset (80 classes of single leaf on complex background).
In this work, we combine interactive segmentation with kernel descriptor. In order to extract leaf from the image, we firstly develop an interactive image segmentation for mobile device with tactile screen. This allows to separate the leaf region from the complex background image in few manipulations. Then, we extract the kernel descriptor from the leaf region to build leaf representation. Since the leaf images may be taken at different scale and rotation levels, we propose two improvements in kernel descriptor extraction that makes the kernel descriptor to be robust to scale and rotation

Publications:
Thi-Lan Le, Nam-Duong Duong, Hai Vu, Van-Toi Nguyen, Van-Nam Hoang, Thi Thanh Nhan Nguyen, Complex Background Leaf-based Plant Identification Method Based on Interactive Segmentation and Kernel Descriptor, The 2nd International Workshop on Environmental Multimedia Retrieval (EMR 2015) - in conjunction with ICMR 2015, Shanghai, China; 06/2015.

Leaf identification based on SURF descriptor and BOW:

Leaf identification based on SURF descriptor and BOW

Publications:
Quang-Khue Nguyen, Thi-Lan Le, 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) - October 2013, Ho Chi Minh city, VietNam..

Vietnamese medicinal plant retrieval: Interface of our Vietnamese medicinal plant retrieval	Based on the current methods on plant identification, we have developed a new application for Vietnam: Vietnamese medicinal plant retrieval. Our system provides three main possibilities for searching a given plant: a conventional keyword based search engine, a fully automatic leaf images based plant identification and interactive plant identification with aids of the graphical tool. These search modesare integrated inside a generic framework with interactive user interface that facilitates the use of the system ona very common Android platform. More information can be found at VnMed This application gots the second prize of Viettel contest for mobile application for heath-care and has been chosen in the finalist of Nhan tai dat viet, 2014 for mobile application.
Publications: Thi-Lan Le, Duc-Tuan Tran, Van-Nam HoangFully automatic leaf-based plant identification, application for Vietnamese medicinal plant search, [pdf] SoICT, 2014
Multi-organ plant identification: Fusion of leaf and flower for plant identification.	We investigate different fusion scheme in order to obtain a robust plant identification based on images of multiple organs.
Publications: DO Thanh Binh, NGUYEN Huy Hoang, NGUYEN Thi Thanh Nhan, VU Hai, TRAN Thi Thanh Hai, LE Thi Lan, Plant identification using late fusion of multi-organ images, The 9th International Conference on Knowledge and Systems Engineering (KSE 2017), IEEE - October 2017. 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, 9th Asian Conference on Intelligent Information and Database Systems, 3-5 April 2017, Kanazawa, Japan. Thi Thanh Nhan Nguyen, Van Tuan Le, Thi Lan Le, Hai Vu, Natapon Pantuwong, Yasushi Yagi, Flower species identification Using Deep Convolutional Neural Networks, Regional Conference on Computer and Information Engineering (RCCIE), Myamar, Oct 2016.
Kernel and modified kernel descriptor for simple leaf on complex background: Leaf identification based on Modified Kernel Descriptor and Interactive Segmentation. Obtained results on ImageClef 2014 dataset (80 classes of single leaf on complex background).	In this work, we combine interactive segmentation with kernel descriptor. In order to extract leaf from the image, we firstly develop an interactive image segmentation for mobile device with tactile screen. This allows to separate the leaf region from the complex background image in few manipulations. Then, we extract the kernel descriptor from the leaf region to build leaf representation. Since the leaf images may be taken at different scale and rotation levels, we propose two improvements in kernel descriptor extraction that makes the kernel descriptor to be robust to scale and rotation
Publications: Thi-Lan Le, Nam-Duong Duong, Hai Vu, Van-Toi Nguyen, Van-Nam Hoang, Thi Thanh Nhan Nguyen, Complex Background Leaf-based Plant Identification Method Based on Interactive Segmentation and Kernel Descriptor, The 2nd International Workshop on Environmental Multimedia Retrieval (EMR 2015) - in conjunction with ICMR 2015, Shanghai, China; 06/2015.
Leaf identification based on SURF descriptor and BOW: Leaf identification based on SURF descriptor and BOW
Publications: Quang-Khue Nguyen, Thi-Lan Le, 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) - October 2013, Ho Chi Minh city, VietNam..