The Research on image retrieval based on PCA-SIFT
1
Citation
0
Reference
10
Related Paper
Citation Trend
Abstract:
This study took butterfly images as the research object, collected and sorted out images of 805 different species of butterflies from 12 families in China, and used local features based on points of interest to describe the characteristics of butterfly images. Two local feature methods, SIFT and PCA-SIFT, were applied to the retrieval of butterfly images. PCA-SIFT used 36-dimension descriptors to describe the points of interest based on SIFT 128-dimension descriptors. Experimental results show that the time complexity of PCA-SIFT based butterfly image retrieval is much lower than SIFT, but the retrieval accuracy is also reduced a lot.Keywords:
Scale-invariant feature transform
Scale-invariant feature transform
Image registration
Image Matching
Feature (linguistics)
Feature Matching
Cite
Citations (34)
The Scale Invariant Feature Transform(SIFT) has been widely used in video concept detection.A lot of researches about SIFT have been dones,uch as PCA-SIFT,SURF and MESR.But there are few attentions about the influence of different down-sampling ratios to SIFT extraction.Based on the analysis of the influence of different down-sampling ratios to SIFT extraction,and a Multiple-Level SIFT(ML-SIFT) method for senmantic concept detection is proposed.Experiments on Caltech256 and Scene Class13 show that MAPs of ML-SIFT outperform MAPs of SIFT on Caltech256 and SceneClass13 by 15.7% and 5.1% respectively.In addition,when training the models using different ratios of positive and negative samples,the performances of ML-SIFT are stable.At the same time,the comparison of SIFT,SURF and ML-SIFT is given in the paper.From the experiments,the performances of SIFT and SURF are similar,but when comparing to ML-SIFT,their performances are worse than ML-SIFT.From above analysis,the ML-SIFT algorithm is effective.
Scale-invariant feature transform
Cite
Citations (1)
With the aim to solve the implement problem in scale invariant feature transform (SIFT) algorithm, the theory and the implementation process was analyzed in detail. The characteristics of the SIFT method were analyzed by theory, combined with the explanation of the Rob Hess SIFT source codes. The effect of the SIFT method was validated by matching two different real images. The matching result shows that the features extracted by SIFT method have excellent adaptive and accurate characteristics to image scale, viewpoint change, which are useful for the fields of image recognition, image reconstruction, etc.
Scale-invariant feature transform
Image Matching
Feature Matching
Feature (linguistics)
Cite
Citations (3)
基于局部特征的匹配算法中SIFT(Scale Invariant Feature Transform)算法性能好，应用广泛，但其描述子的维度高、匹配耗时大，对局部相似区域的匹配鲁棒性差。为此，该文提出一种Contourlet-SIFT特征匹配算法。在尺度空间下提取旋转不变特征，对特征及其邻域进行Contourlet变换，由各方向子带分解系数的均值和标准差构建全局纹理描述向量，根据向量间欧氏距离的大小进行特征点排序，选取距离较小的前1%的特征再进行SIFT最近邻比值匹配。实验结果表明该算法对亮度差异大、相似区域多的图像的匹配性能优于SIFT，在保证尺度、旋转、视角等不变性与SIFT相当的同时，匹配速度大为提升。
Scale-invariant feature transform
Contourlet
Feature (linguistics)
Cite
Citations (5)
최근 멀티미디어 정보가 보편화됨에 따라 인터넷에서 이미지를 기반으로 정보를 검색하려는 다양한 시도가 진행되고 있다. 그러나 이미지에는 다양한 패턴이 포함되어 있기 때문에 정확하게 원하는 이미지를 찾는 것은 아직 어려움이 많다. 본 논문에서는 인터넷 쇼핑몰의 상품검색을 효율적으로 할 수 있는 이미지 기반 검색 시스템을 제안한다. 제안된 검색 방법은 SIFT(Scale Invariant Feature Transform) 알고리즘을 이용하여 이미지 검색을 위한 특징을 추출하고, PCA-SIFT를 이용하여 여러 차원에서 키포인트의 매칭을 반복하여 누적 후 사용자가 원하는 상품을 찾아준다. 제안된 방법의 효율성을 검증하기 위해, 다양한 패턴의 상품 이미지를 이용하여 기존 SIFT, PCA-SIFT 방법과 제안된 방법을 비교한 결과, 상표가 포함되지 않은 이미지의 경우 제안방법이 가장 높은 변별력을 보였으며, 효과적인 이미지 검색의 가능성을 보였다. Recently, as multimedia information becomes popular, there are many studies to retrieve images based on images in the web. However, it is hard to find the matching images which users want to find because of various patterns in images. In this paper, we suggest an efficient images retrieval system based on images for finding products in internet shopping malls. We extract features for image retrieval by using SIFT (Scale Invariant Feature Transform) algorithm, repeat keypoint matching in various dimension by using PCA-SIFT, and find the image which users search for by combining them. To verify efficiency of the proposed method, we compare the performance of our approach with that of SIFT and PCA-SIFT by using images with various patterns. We verify that the proposed method shows the best distinction in the case that product labels are not included in images.
Scale-invariant feature transform
Feature (linguistics)
Cite
Citations (1)
Local feature point detection and description are the basis for Computer Vision. SIFT is one of the most efficient local image descriptors and have been well studied in recent years. In this paper, we introduce B-SIFT, a novel binary local image descriptor which is based with SIFT. The method is compared with SIFT, and is shown that B-SIFT is better both in accuracy and efficiency.
Scale-invariant feature transform
Local Binary Patterns
Feature (linguistics)
Cite
Citations (13)
SIFT feature extraction is a computationally intensive problem, for the large scale image, which will take a long time to extract SIFT feature. This paper presents a novel approach, based on MapReduce, to accelerate SIFT feature extraction. A MapReduce based SIFT feature extraction model is established, and the original SIFT feature extraction progress is reformed to fit the model. We have implemented the MapReduce based algorithm and evaluated it on a Hadoop cluster. The experimental results show that this approach can extract SIFT feature simultaneously on Hadoop cluster with a good speed up rate.
Scale-invariant feature transform
Feature (linguistics)
Cite
Citations (4)
This paper summarizes the three robust feature detection and matching methods: Scale Invariant Feature Transform (SIFT), Principal Component Analysis (PCA)–SIFT and Speeded Up Robust Features (SURF). SIFT find its interest points using Difference of Gaussian (DoG). SIFT presents its stability in most situations although it’s slow. PCA-SIFT show its advantages in rotation and illumination change and it is faster than SIFT.SURF is the fastest one with good performance as the same as SIFT. ‘Fast-Hessian’ detector that used in SURF is more than 3 times faster that DOG.
Scale-invariant feature transform
Hessian matrix
Feature (linguistics)
Cite
Citations (10)
Numerous studies have been focusing on the improvement of bag of features (BOF), histogram of oriented gradient (HOG) and scale invariant feature transform (SIFT). However, few works have attempted to learn the connection between them even though the latter two are widely used as local feature descriptor for the former one. Motivated by the resemblance between BOF and HOG/SIFT in the descriptor construction, we improve the performance of HOG/SIFT by a) interpreting HOG/SIFT as a variant of BOF in descriptor construction, and then b) introducing recently proposed approaches of BOF such as locality preservation, data-driven vocabulary, and spatial information preservation into the descriptor construction of HOG/SIFT, which yields the BOF-driven HOG/SIFT. Experimental results show that the BOF-driven HOG/SIFT outperform the original ones in pedestrian detection (for HOG), scene matching and image classification (for SIFT). Our proposed BOF-driven HOG/SIFT can be easily applied as replacements of the original HOG/SIFT in current systems since they are generalized versions of the original ones.
Scale-invariant feature transform
Feature (linguistics)
Cite
Citations (5)
SIFT(scale invariant feature transform)는 크기와 회전에 불변하는 특징을 추출하는 방법으로, 다양한 검출 및 인식 분야에 적용되고 있다. 이러한 특성으로 인하여 SIFT는 복사-이동 조작 검출을 위한 기본 변환으로 널리 사용되고 있다. 그러나 SIFT 기반 복사-이동 조작 검출 방법은 배경 영역이 조작된 경우, 조작 범위가 작은 경우, 영상이 압축된 경우 등에 검출 성능이 떨어지는 단점을 가지고 있다. 본 논문에서는 이러한 단점을 극복하기 위하여 CSLBP(center-symmetric local binary pattern) 지시자를 이용한 SIFT 기반 복사-이동 조작 검출법을 제안한다. CSLBP 지시자는 총 16차원을 가지며, 기존의 128 차원의 SIFT 지시자에 추가하여 사용된다. MICC-F220 및 CMH 데이터에 대한 실험 결과, 제안 방법은 95% 이상의 검출 정확도를 보인다. 특히, 압축된 영상에 대하여 성능의 저하가 없음을 알 수 있다.
Scale-invariant feature transform
Cite
Citations (0)