scholarly journals DETECTING FEATURES VIA MODIFIED HARRIS CORNERS AND MATCHING THEM THROUGH SIFT

2020 ◽  
Author(s):  
Jimut Bahan Pal
Keyword(s):  
Noise Intensity ◽  
Scale Invariant ◽  
Sift Algorithm ◽  
Invariant Feature ◽  
Harris Corner ◽  
Key Points ◽  
Daunting Task ◽  
Feature Transform ◽  
Scale Invariant Feature ◽  
Robust To Noise

Interpreting images spatially is a daunting task which is achieved by detecting corners and features.The most important task of detecting features is achieved by Harris Corner Algorithm. The algorithmis not robust to different scale of the same image. The algorithm may detect corner but when theimage is zoomed in, the corner may appear as ridges. We use the corners detected from HarrisCorner algorithm and treat these as key points to pass into Scale Invariant Feature Transform (SIFT)algorithm. The SIFT algorithm extracts descriptor vector of dimension 128 X 1 from these cornersand can be used to find similarity between different images. This process is quite robust to noise,intensity, scale and occlusion and is used for matching images from a database of descriptors. Wehave investigated both the algorithms in this paper and made a modified version of Harris Corneralgorithm by performing different kind of thresholding, both of them gave a little different result.

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.

Logo Matching and Recognition Based on Context

2018 ◽  
pp. 164-176
Author(s):  
Tapan Kumar Das
Keyword(s):  
Real World ◽  
Scale Invariant Feature Transform ◽  
Gray Scale ◽  
Scale Invariant ◽  
Invariant Feature ◽  
Key Points ◽  
Gray Scale Image ◽  
Feature Transform ◽  
Graphic Elements ◽  
Scale Invariant Feature

Logos are graphic productions that recall some real-world objects or emphasize a name, simply display some abstract signs that have strong perceptual appeal. Color may have some relevance to assess the logo identity. Different logos may have a similar layout with slightly different spatial disposition of the graphic elements, localized differences in the orientation, size and shape, or differ by the presence/absence of one or few traits. In this chapter, the author uses ensemble-based framework to choose the best combination of preprocessing methods and candidate extractors. The proposed system has reference logos and test logos which are verified depending on some features like regions, pre-processing, key points. These features are extracted by using gray scale image by scale-invariant feature transform (SIFT) and Affine-SIFT (ASIFT) descriptor method. Pre-processing phase employs four different filters. Key points extraction is carried by SIFT and ASIFT algorithm. Key points are matched to recognize fake logo.

scholarly journals MRI Images under the Optimized Registration Algorithm for Primary Open Angle Glaucoma Visual Path Damage

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Bin Zhou ◽  
Min Chen
Keyword(s):  
Primary Open Angle Glaucoma ◽  
Open Angle Glaucoma ◽  
Scale Invariant Feature Transform ◽  
Open Angle ◽  
Scale Invariant ◽  
Sift Algorithm ◽  
Invariant Feature ◽  
Feature Transform ◽  
Scale Invariant Feature ◽  
The Impact

To explore the impact of different image registration algorithms on the diagnosis of visual path damage in patients with primary open angle glaucoma (POAG), 60 cases of suspected POAG patients were selected as the research objects. Shape-preserving scale invariant feature transform (SP-SIFT) algorithm, scale invariant feature transform (SIFT) algorithm, and Kanade-Lucas-Tomasi (KLT) algorithm were compared and applied to MRI images of 60 POAG patients. It was found that the SP-SIFT algorithm converged after 33 iterations, which had a higher registration speed than the SIFT algorithm and the KLT algorithm. The mean errors of the SP-SIFT algorithm in the rotation angle, X-direction translation, and Y-direction translation were 2.11%, 4.56%, and 4.31%, respectively. Those of the SIFT algorithm were 5.55%, 9.98%, and 7.01%, respectively. Those of the KLT algorithm were 7.45%, 11.31%, and 8.56%, respectively, and the difference among algorithms was significant ( P < 0.05 ). The diagnostic sensitivity and accuracy of the SP-SIFT algorithm for POAG were 96.15% and 94.34%, respectively. Those of the SIFT algorithm were 94.68% and 90.74%, respectively. Those of the KLT algorithm were 94.21% and 90.57%, respectively, and the three algorithms had significant differences ( P < 0.05 ). The results of MRI images based on the SP-SIFT algorithm showed that the average thickness of the cortex of the patient’s left talar sulcus, right talar sulcus, left middle temporal gyrus, and left fusiform gyrus were 2.49 ± 0.15 mm, 2.62 ± 0.13 mm, 3.00 ± 0.10 mm, and 2.99 ± 0.17 mm, respectively. Those of the SIFT algorithm were 2.51 ± 0.17 mm, 2.69 ± 0.12 mm, 3.11 ± 0.13 mm, and 3.09 ± 0.14 mm, respectively. Those of the KLT algorithm were 2.35 ± 0.12 mm, 2.52 ± 0.16 mm, 2.77 ± 0.11 mm, and 2.87 ± 0.17 mm, respectively, and the three algorithms had significant differences ( P < 0.05 ). In summary, the SP-SIFT algorithm was ideal for POAG visual pathway diagnosis and was of great adoption potential in clinical diagnosis.

scholarly journals Analisis Komparasi Pencocokan Pola Citra Jenis Ikan Mujair (Oreochromis Mossambicus) Menggunakan Algortima Scale Invariant Feature Transform Dengan Algoritma k-Nearest Neighbor

2021 ◽  
Vol 20 (1) ◽  
pp. 16-21
Author(s):  
Suhadi . ◽  
Rudi Budi Agung ◽  
Syamsul Bahri
Keyword(s):  
Fish Species ◽  
Nearest Neighbor ◽  
Sampling Error ◽  
Oreochromis Mossambicus ◽  
K Nearest Neighbor ◽  
Scale Invariant ◽  
Sift Algorithm ◽  
Invariant Feature ◽  
Feature Transform ◽  
Scale Invariant Feature

Fish is a very large source of protein, by eating fish it can be healthier and participate in educating the nation's future generations, so it must be preserved. Fish is a food commodity that is easily available in Indonesia, and the price is also affordable. Tilapia fish (Oreochromis Mossambicus) is a popular consumption fish in Indonesia found in rivers, lakes, and lakes with a salt content of less than 0.05% for breeding. Tilapia fish is widely consumed by the public as a cheap and delicious fish that is often found in traditional and modern markets. This fish is often sold fresh or through the process of freezing (frozen). Previous research used the K-Nearest Neighbor (K-NN) algorithm and Image Processing to detect fish species using a smartphone. The purpose of this study was to analyze the comparison between the Scale Invariant Feature Transform (SIFT) Algorithm and the K-Nearest Neighbor (K-NN) Algorithm to determine the matching image patterns of Mujair fish species. The conclusion of this study is that the SIFT algorithm is the most accurate with a sampling error of 0.31% and the k-NN algorithm with a sampling error of 69.89%.

The Study of Reduce the Mismatch Based on the SIFT Feature Matching

2012 ◽  
Vol 580 ◽  
pp. 378-382
Author(s):  
Xiao Yu Liu ◽  
Yan Piao ◽  
Lei Liu
Keyword(s):  
Image Matching ◽  
Feature Matching ◽  
Scale Invariant ◽  
Sift Algorithm ◽  
Invariant Feature ◽  
Space Rotation ◽  
Feature Transform ◽  
The Difference ◽  
Scale Invariant Feature ◽  
Keypoints Matching

The algorithm of SIFT (scale-invariant feature transform) feature matching is an international hotspot in the areas of the keypoints matching and target recognition at the present time. The algorithm is used in the image matching widely because of the good invariance of scale, illumination and space rotation .This paper proposes a new theory to reduce the mismatch—the theory to reduce the mismatch based on the main orientation of keypoints. This theory should firstly compute the grads of the main orientation of a couple of matched keypoints in the two images and the difference between them. Because the difference of the main orientation of matched keypoints should be much larger than the couples which are matched correctly, we can distinguish and reduce the mismatch through setting the proper threshold, and it can improve the accuracy of the SIFT algorithm greatly.

scholarly journals ANALISIS PENDETEKSI KECOCOKAN OBJEK PADA CITRA DIGITAL DENGAN METODE ALGORITMA SIFT DAN HISTOGRAM COLOR RGB

2018 ◽  
Vol 1 (1) ◽  
pp. 20-27
Author(s):  
Rosidin Al Caruban ◽  
Bambang Sugiantoro ◽  
Yudi Prayudi
Keyword(s):  
Digital Image ◽  
Digital Images ◽  
Scale Invariant Feature Transform ◽  
Digital Image Forensics ◽  
Scale Invariant ◽  
Sift Algorithm ◽  
Scientific Methods ◽  
Invariant Feature ◽  
Feature Transform ◽  
Scale Invariant Feature

Through using tools of image processing on digital images just like gimp and adobe photoshop applications, an image on digital images can be a source of information for anyone who observes it. On one hand, those applications can easily change or manipulate the authenticity of the image. On the other hand, they can be misused to undermine the credibility of the authenticity of the image in various aspects. Thus, they can be considered as a crime. The implementation of the SIFT Algorithm (Scale Invariant feature transform) and RGB color histogram in Matlab can detect object fitness in digital images and perform accurate test. This study discusses the implementation of getting object fitness on digital image that has been manipulated by SIFT Algorithm method on the Matlab source. It is done by comparing the original image with the manipulated one. The object fitness in digital images can be obtained from a number of key points and other additional parameters through comparing number of pixels on the analyzed image and on the changed histogram in RGB color on each analyzed image. The digital image forensics which is known as one of the scientific methods commonly used in researches is aimed to obtain evidences or facts in determining the authenticity of the image on digital images. The use of the SIFT algorithm is chosen as an extraction method because it is invariant to scale, rotation, translation, and illumination changes. SIFT is used to obtain characteristics of the pattern of the gained key point. The tested result of the SIFT Algorithm method (Scale Invariant feature transform) is expected to produce a better image analysis.

Research and Improvement of Content-Based Image Retrieval Framework

2018 ◽  
Vol 32 (12) ◽  
pp. 1850043 ◽  
Author(s):  
Yong Hou ◽  
Qingjun Wang
Keyword(s):  
Image Retrieval ◽  
High Performance ◽  
Gaussian Mixture ◽  
Scale Invariant Feature Transform ◽  
Scale Invariant ◽  
Sift Algorithm ◽  
Invariant Feature ◽  
Match Rate ◽  
Feature Transform ◽  
Scale Invariant Feature

This paper proposed a high-performance image retrieval framework, which combines the improved feature extraction algorithm SIFT (Scale Invariant Feature Transform), improved feature matching, improved feature coding Fisher and improved Gaussian Mixture Model (GMM) for image retrieval. Aiming at the problem of slow convergence of traditional GMM algorithm, an improved GMM is proposed. This algorithm initializes the GMM by using on-line [Formula: see text]-means clustering method, which improves the convergence speed of the algorithm. At the same time, when the model is updated, the storage space is saved through the improvement of the criteria for matching rules and generating new Gaussian distributions. Aiming at the problem that the dimension of SIFT (Scale Invariant Feature Transform) algorithm is too high, the matching speed is too slow and the matching rate is low, an improved SIFT algorithm is proposed, which preserves the advantages of SIFT algorithm in fuzzy, compression, rotation and scaling invariance advantages, and improves the matching speed, the correct match rate is increased by an average of 40% to 55%. Experiments on a recently released VOC 2012 database and a database of 20 category objects containing 230,800 images showed that the framework had high precision and recall rates and less query time. Compared with the standard image retrieval framework, the improved image retrieval framework can detect the moving target quickly and effectively and has better robustness.

The Improved Algorithm of Scale Invariant Feature Transform on Palmprint Recognition

2011 ◽  
Vol 186 ◽  
pp. 565-569
Author(s):  
Zhong Qu ◽  
Zheng Yong Wang
Keyword(s):  
Euclidean Distance ◽  
Recognition Rate ◽  
Scale Invariant Feature Transform ◽  
Palmprint Recognition ◽  
Scale Invariant ◽  
Sift Algorithm ◽  
Invariant Feature ◽  
Feature Transform ◽  
Simulation Results ◽  
Scale Invariant Feature

This paper presents a new method of palmprint recognition based on improved scale invariant feature transform (SIFT) algorithm which combines the Euclidean distance and weighted sub-region. It has the scale, rotation, affine, perspective, illumination invariance, and also has good robustness to the target's motion, occlusion, noise and other factors. Simulation results show that the recognition rate of the improved SIFT algorithm is higher than the recognition rate of SIFT algorithm.

Sign in / Sign up

Export Citation Format

Share Document