Sparse Based Automatic Plant Identification System

Parida, Padmini (2017) Sparse Based Automatic Plant Identification System. MTech thesis.

[img]PDF (Fulltext is restricted upto 22.01.2020)
Restricted to Repository staff only



Plant knowledge is crucial for protecting biodiversity. Medicinal plants have been used throughout the human history. Ayurveda is one of the oldest medicine system, which is even recognized in the modern medical society, uses plants for the preparation of medicines. An individual with deep knowledge of plants can only differentiate between these species. This makes leaf identification very difficult. Nowadays, with the rich development in image processing, pattern recognition, and availability of digital cameras, cell phones and the remote access to databases, gives an idea for automatic plant identification using digital image processing.For plant identification shape of a leaf is used because shape and size of the leaf can be easily observed, captured, described and are less affected by seasonal changes. For automatic plant identification, the first step is to extract features from leaf images to be recognized.A leaf image can be described by its, shape texture and color. The color of a leaf may differ with the seasons and climatic conditions, while most plants of leaves have comparable color. In this work, a system is being developed which utilized shape of a leaf for automatic plant identification because leaf shape is universal and can be easily extracted. This system takes input as a leaf image and outputs the name of the species and other relevant details which are stored in the database.The system is designed using the technique of image identification using shape feature sparse representation based classifier. The descriptor used for shape identification described using SIFT. The classification was done using a sparse representation based classifier with the LC-KSVD algorithm. The system was tested for a certain class of leaves and the performance of the system is compared with an existing system.

Item Type:Thesis (MTech)
Uncontrolled Keywords:SIFT(Scale Invariant Feature Transform); sparse based classifier; Shape feature ; LC-KSVD; Leaf
Subjects:Engineering and Technology > Electronics and Communication Engineering > Image Processing
Engineering and Technology > Electronics and Communication Engineering > Signal Processing
Divisions: Engineering and Technology > Department of Electronics and Communication Engineering
ID Code:8871
Deposited By:Mr. Kshirod Das
Deposited On:28 Mar 2018 15:16
Last Modified:28 Mar 2018 15:16
Supervisor(s):Sahoo, Ajit Kumar

Repository Staff Only: item control page