scholarly journals SCALE INVARIANT FEATURE TRANSFORM PLUS HUE FEATURE

2017 ◽  
Vol XLII-2/W6 ◽  
pp. 27-32
Author(s):  
M. B.Daneshvar
Keyword(s):  
Scale Invariant Feature Transform ◽  
Scale Invariant ◽  
Keypoint Matching ◽  
Matching Process ◽  
Invariant Feature ◽  
Speed Up ◽  
Euclidean Distances ◽  
Feature Transform ◽  
The Difference ◽  
Scale Invariant Feature

This paper presents an enhanced method for extracting invariant features from images based on Scale Invariant Feature Transform (SIFT). Although SIFT features are invariant to image scale and rotation, additive noise, and changes in illumination but we think this algorithm suffers from excess keypoints. Besides, by adding the hue feature, which is extracted from combination of hue and illumination values in HSI colour space version of the target image, the proposed algorithm can speed up the matching phase. Therefore, we proposed the Scale Invariant Feature Transform plus Hue (SIFTH) that can remove the excess keypoints based on their Euclidean distances and adding hue to feature vector to speed up the matching process which is the aim of feature extraction. In this paper we use the difference of hue features and the Mean Square Error (MSE) of orientation histograms to find the most similar keypoint to the under processing keypoint. The keypoint matching method can identify correct keypoint among clutter and occlusion robustly while achieving real-time performance and it will result a similarity factor of two keypoints. Moreover removing excess keypoint by SIFTH algorithm helps the matching algorithm to achieve this goal.

scholarly journals Implementasi Metode Speed Up Robust Feature dan Scale Invariant Feature Transform untuk Identifikasi Telapak Kaki Individu

2017 ◽  
Vol 3 (4) ◽  
pp. 178
Author(s):  
Muhammad Baresi Ariel ◽  
Ratri Dwi Atmaja ◽  
Azizah Azizah
Keyword(s):  
Feature Extraction ◽  
Nearest Neighbor ◽  
Scale Invariant Feature Transform ◽  
K Nearest Neighbor ◽  
Scale Invariant ◽  
Invariant Feature ◽  
Speed Up ◽  
Feature Transform ◽  
Speed Up Robust Feature ◽  
Scale Invariant Feature

<p><em>Abstrak</em><strong> - Biometrik merupakan metode pengidentifikasian individu berdasarkan ciri fisiknya. Salah satu ciri fisik yang dapat digunakan untuk biometrik adalah telapak kaki. Ciri fisik ini dipilih karena memiliki tingkat keunikan yang tinggi, sehingga hampir tidak terdapat individu yang memiliki ciri yang sama. Metode-metode ekstraksi ciri seperti Scale Invariant Feature Transform (SIFT) dan Speed Up Robust Feature (SURF) akan sesuai jika digunakan untuk mendukung sistem identifikasi telapak kaki. Tahapan yang dilakukan untuk mendapatkan deskriptor dimulai dari scanning telapak kaki, pre-processing, ekstraksi ciri dengan menggunakan SURF dan SIFT sampai pada proses matching pada saat pengujian. Perbandingan keduanya dilihat dari aspek akurasi. Proses penentuan klasifikasi dan kelas menggunakan algoritma K-Nearest Neighbor (K- NN). Hasilnya akan menjadi data-data penelitian dalam paper ini. Diharapkan menggunakan metode SIFT dan SURF akan memberikan hasil dengan tingkat keakurasian yang tinggi.</strong></p><p><em><strong>Kata Kunci</strong> – Biometric, Footprint, SURF, SIFT, K- NN</em></p><p><em>Abstract</em><strong> - Biometric is a method used to identify indivduals using their physical features. One of the physical features that can be used for biometric is the footprint. The footprint was chosen because of having a high level of uniqueness where it is almost impossible to find two individuals that have the same footprint. Feature extraction methods such as Scale Invariant Feature Transform (SIFT) and Speed Up Robust Feature (SURF) are appropriate if used for footprint identification system. The steps used in obtaining descriptor start from scanning the footprint, pre-processing, feature extraction using SURF and SIFT and last the matching process. The comparison between the two methods will be observed by their accuracy. The K-Nearest Neighbor (K-NN) algorithm will be used for the classification process. The outputs will be used for research data in this research proposal. It will be expected that using SIFT and SURF for the feature extraction will result in high accuracy.</strong></p><p><em><strong>Keywords</strong> – Biometric, Footprint, SURF, SIFT, K- NN</em></p>

Implementation of SIFT for detection of electronic waste

2018 ◽  
Vol 7 (2.8) ◽  
pp. 353
Author(s):  
A Roshna Meeran ◽  
V Nithya
Keyword(s):  
Image Processing ◽  
Electronic Waste ◽  
Scale Invariant Feature Transform ◽  
Recycling Process ◽  
Scale Invariant ◽  
Object Matching ◽  
Invariant Feature ◽  
Detection And Identification ◽  
Feature Transform ◽  
Scale Invariant Feature

The paper focuses on the investigation of image processing of Electronic waste detection and identification in recycling process of all Electronic items. Some of actually collected images of E-wastes would be combined with other wastes. For object matching with scale in-variance the SIFT (Scale -Invariant- Feature Transform) is applied. This method detects the electronic waste found among other wastes and also estimates the amount of electronic waste detected the give set of wastes. The detection of electronics waste by this method is most efficient ways to detect automatically without any manual means.

scholarly journals Scale-Invariant Feature Transform Algorithm with Fast Approximate Nearest Neighbor

2017 ◽  
Vol 14 (3) ◽  
pp. 651-661 ◽  
Author(s):  
Baghdad Science Journal
Keyword(s):  
Nearest Neighbor ◽  
Daily Basis ◽  
Scale Invariant Feature Transform ◽  
Scale Invariant ◽  
Suggested Approach ◽  
Approximate Nearest Neighbor ◽  
Invariant Feature ◽  
Key Points ◽  
Feature Transform ◽  
Scale Invariant Feature

There is a great deal of systems dealing with image processing that are being used and developed on a daily basis. Those systems need the deployment of some basic operations such as detecting the Regions of Interest and matching those regions, in addition to the description of their properties. Those operations play a significant role in decision making which is necessary for the next operations depending on the assigned task. In order to accomplish those tasks, various algorithms have been introduced throughout years. One of the most popular algorithms is the Scale Invariant Feature Transform (SIFT). The efficiency of this algorithm is its performance in the process of detection and property description, and that is due to the fact that it operates on a big number of key-points, the only drawback it has is that it is rather time consuming. In the suggested approach, the system deploys SIFT to perform its basic tasks of matching and description is focused on minimizing the number of key-points which is performed via applying Fast Approximate Nearest Neighbor algorithm, which will reduce the redundancy of matching leading to speeding up the process. The proposed application has been evaluated in terms of two criteria which are time and accuracy, and has accomplished a percentage of accuracy of up to 100%, in addition to speeding up the processes of matching and description.

Sign in / Sign up

Export Citation Format

Share Document