Laplacian Sift in Visual Search

نویسندگان

  • Xin Xin
  • Zhu Li
  • Aggelos K. Katsaggelos
چکیده

With the explosive growth of video capture capable mobile handsets and online visual data repositories, the popular query-by-capture applications call for a compact visual descriptor with minimum descriptor length. How to preserve the visual descriptor information while minimizing the bit rate for representing the descriptors, is a focus of the ongoing MPEG7 CDVS (Compact Descriptor for Visual Search) standardization effort. In this work, we present a SIFT descriptor dimension reduction scheme based on Laplacian Graph Embedding, which computes a linear embedding that preserves the topological relationship among visual descriptors. Simulation results demonstrate the effectiveness of the proposed solution at low bit rates.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Laplacian embedding and key points topology verification for large scale mobile visual identification

Visual query-by-capture applications call for a compact visual descriptor with minimum descriptor length. Preserving the visual identification performance while minimising the bit rate is a focus of the on-going MPEG7 CDVS (Compact Descriptors for Visual Search) standardisation effort. In this paper we tackle this problem by adopting Laplacian embedding for SIFT feature compression and employin...

متن کامل

Weakly supervised learning from SIFT keypoints: An approach combining fast eigendecompostion, regularization and diffusion on graphs

In this paper we propose a unified approach to propagate knowledge into a high-dimensional space from a small informative set, in this case SIFT features. Our contribution lies in three aspects. First, we propose a spectral graph embedding of the SIFT points for dimensionality reduction, which provides efficient keypoints transcription into an euclidean manifold. We use iterative deflation to s...

متن کامل

Multi-Focus Image Fusion in DCT Domain using Variance and Energy of Laplacian and Correlation Coefficient for Visual Sensor Networks

The purpose of multi-focus image fusion is gathering the essential information and the focused parts from the input multi-focus images into a single image. These multi-focus images are captured with different depths of focus of cameras. A lot of multi-focus image fusion techniques have been introduced using considering the focus measurement in the spatial domain. However, the multi-focus image ...

متن کامل

Survey of SIFT Compression Schemes

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...

متن کامل

Weakly supervised learning from scale invariant feature transform keypoints: an approach combining fast eigendecompostion, regularization, and diffusion on graphs

We propose a unified approach to propagate knowledge into a high-dimensional space from a small informative set, in this case, scale invariant feature transform (SIFT) features. Our contribution lies in three aspects. First, we propose a spectral graph embedding of the SIFT points for dimensionality reduction, which provides efficient keypoints transcription into a Euclidean manifold. We use it...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2012