Removal of Noise Using Filters for Efficient Leaf Identification
Plant species identification and classification based on leaf shape is becoming a popular trend, since each leaf carries substantial information that can be used to identify and classify the type of a plant. This is difficult because the features of a leaf shape can be influenced by other leaves t...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2015
|
| Subjects: | |
| Online Access: | http://eprints.unisza.edu.my/716/1/FH03-FIK-15-03310.pdf http://eprints.unisza.edu.my/716/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Plant species identification and classification based on leaf shape is becoming a popular trend, since each leaf carries substantial
information that can be used to identify and classify the type of a plant. This is difficult because the features of a leaf shape can
be influenced by other leaves that have similar features but different categories or classes. To overcome this problem, an efficient
preprocessing stage needs to be considered. This paper presents the most popular statistical operators such as mean, median and
adaptive (wiener) filters techniques for noise removal in preprocessing stage. Three different filter techniques were applied to
various categories or classes of plant leaf and evaluated using mean square error (MSE) and peak signal to noise ratio (PSNR).
The leaf images acquired from UCI database were used for the study. The results showed that Wiener filter presents the best
performance in terms of noise removal. But in terms of processing time Mean filter is the best. These results can be applicable to
plant identification and classification in the preprocessing stage. |
|---|