Fingertip Detection Using Histogram of Gradients and Support Vector Machine
One important application in computer vision is detection of objects. One important application in computer vision is detection of objects. This paper discusses detection of fingertips by using Histogram of Gradients (HOG) as the feature descriptor and Support Vector Machines (SVM) as the classifier...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | EJournal Article |
| Published: |
Institute of Advanced Engineering and Science,
2017-11-01.
|
| Subjects: | |
| Online Access: | Get fulltext |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| LEADER | 02346 am a22003013u 4500 | ||
|---|---|---|---|
| 001 | ijeecs10018_7727 | ||
| 042 | |a dc | ||
| 100 | 1 | 0 | |a Sophian, Ali |e author |
| 100 | 1 | 0 | |e contributor |
| 700 | 1 | 0 | |a Qurratu'aini, Dayang |e author |
| 245 | 0 | 0 | |a Fingertip Detection Using Histogram of Gradients and Support Vector Machine |
| 260 | |b Institute of Advanced Engineering and Science, |c 2017-11-01. | ||
| 500 | |a https://ijeecs.iaescore.com/index.php/IJEECS/article/view/10018 | ||
| 520 | |a One important application in computer vision is detection of objects. One important application in computer vision is detection of objects. This paper discusses detection of fingertips by using Histogram of Gradients (HOG) as the feature descriptor and Support Vector Machines (SVM) as the classifier. The SVM is trained to produce a classifier that is able to distinguish whether an image contains a fingertip or not. A total of 4200 images were collected by using a commercial-grade webcam, consisting of 2100 fingertip images and 2100 non-fingertip images, were used in the experiment. Our work evaluates the performance of the fingertip detection and the effects of the cell's size of the HOG and the number of the training data have been studied. It has been found that as expected, the performance of the detection is improved as the number of training data is increased. Additionally, it has also been observed that the 10 x 10 size gives the best results in terms of accuracy in the detection. The highest classification accuracy obtained was less than 90%, which is thought mainly due to the changing orientation of the fingertip and quality of the images. | ||
| 540 | |a Copyright (c) 2017 Institute of Advanced Engineering and Science | ||
| 540 | |a http://creativecommons.org/licenses/by-nc-nd/4.0 | ||
| 546 | |a eng | ||
| 690 | |||
| 690 | |||
| 655 | 7 | |a info:eu-repo/semantics/article |2 local | |
| 655 | 7 | |a info:eu-repo/semantics/publishedVersion |2 local | |
| 655 | 7 | |2 local | |
| 786 | 0 | |n Indonesian Journal of Electrical Engineering and Computer Science; Vol 8, No 2: November 2017; 482-486 | |
| 786 | 0 | |n 2502-4760 | |
| 786 | 0 | |n 2502-4752 | |
| 786 | 0 | |n 10.11591/ijeecs.v8.i2 | |
| 787 | 0 | |n https://ijeecs.iaescore.com/index.php/IJEECS/article/view/10018/7727 | |
| 856 | 4 | 1 | |u https://ijeecs.iaescore.com/index.php/IJEECS/article/view/10018/7727 |z Get fulltext |