Transmission and storage of local feature descriptors are of critical importance for mobile visual search applications. We perform a comprehensive survey of Scale Invariant Feature Transform (SIFT) compression schemes proposed in the literature and evaluate them in a common framework. Further, we compare the different schemes to the recently proposed low bit-rate Compressed Histogram of Gradien...

We investigate transform coding to efficiently store and transmit SIFT and SURF image descriptors. We show that image and feature matching algorithms are robust to significantly compressed features. We achieve nearperfect image matching and retrieval for both SIFT and SURF using ∼2 bits/dimension. When applied to SIFT and SURF, this provides a 16× compression relative to conventional floating p...

Dermatologists consider color as one of the major discriminative aspects of melanoma. In this paper we evaluate the importance of color in the keypoint detection and description steps of the Bag-of-Features model. We compare the performance of gray scale against that of color sampling methods using Harris Laplace detector and its color extensions. Moreover, we compare the performance of SIFT an...

For many years, various local descriptors that are insensitive to geometric changes such as viewpoint, rotation, and scale changes, have been attracting attention due to their promising performance. However, most existing local descriptors including the SIFT (Scale Invariant Feature Transform) are based on luminance information rather than color information thereby resulting in instability to p...

Convolutional Neural Network (NN) has gained a lot of attention of the researchers due to its high accuracy in classification and feature learning. In this paper, we evaluated the performance of CNN used as feature for image retrieval with the gold standard feature, aka SIFT. Experiments are conducted on famous Oxford 5k data-set. The mAP of SIFT and CNN is 0.6279 and 0.5284, respectively. The ...

Latest results indicate that features learned via convolutional neural networks outperform previous descriptors on classification tasks by a large margin. It has been shown that these networks still work well when they are applied to datasets or recognition tasks different from those they were trained on. However, descriptors like SIFT are not only used in recognition but also for many correspo...

car license plate recognition is addressed in this paper. given the development of intelligent transportation systems, it is absolutely essential to implement a strong license plate recognition system. efforts were made to put forward a novel reliable method for car license plate recognition in iran. each license plate recognition system comprises three main parts. the first part is the license...

Zhai and Shah (2006) proposed a model of spatiotemporal saliency using a combination of temporal and spatial attention models. The temporal model utilized Lowe’s SIFT (2004) to compute feature points and the correspondences between them in successive frames. Bay, Tuytelaars, & Van Gool introduced SURF (2006) as an alternative feature detector and descriptor. The authors of SURF show that it is ...

Abstract. While image registration has been studied in different areas of computer vision, aligning images depicting different scenes remains a challenging problem, closer to recognition than to image matching. Analogous to optical flow, where an image is aligned to its temporally adjacent frame, we propose SIFT flow, a method to align an image to its neighbors in a large image collection consi...