Towards large-scale geometry indexing by feature selection
نویسندگان
چکیده
We present a new approach to image indexing and retrieval, which integrates appearance with global image geometry in the indexing process, while enjoying robustness against viewpoint change, photometric variations, occlusion, and background clutter. We exploit shape parameters of local features to estimate image alignment via a single correspondence. Then, for each feature, we construct a sparse spatial map of all remaining features, encoding their normalized position and appearance, typically vector quantized to visual word. An image is represented by a collection of such feature maps and RANSAC-like matching is reduced to a number of set intersections. The required index space is still quadratic in the number of features. To make it linear, we propose a novel feature selection model tailored to our feature map representation, replacing our earlier hashing approach. The resulting index space is comparable to baseline bag-of-words, scaling up to one million images while outperforming the state of the art on three publicly available datasets. To our knowledge, this is the first geometry indexing method to dispense with spatial verification at this scale, bringing query times down to milliseconds.
منابع مشابه
Straightforward Feature Selection for Scalable Latent Semantic Indexing
Latent Semantic Indexing (LSI) has been validated to be effective on many small scale text collections. However, little evidence has shown its effectiveness on unsampled large scale text corpus due to its high computational complexity. In this paper, we propose a straightforward feature selection strategy, which is named as Feature Selection for Latent Semantic Indexing (FSLSI), as a preprocess...
متن کاملSemantic Indexing and Multimedia Event Detection: ECNU at TRECVID 2012
1 Abstract This year we participated in two tasks: Semantic Indexing (SIN) and Multimedia Event Detection (MED). In this paper, we present our approaches and discuss the evaluation results. Semantic Indexing (SIN): For video semantic indexing, we focus on the performance improvement by using a Weighted Hamming Embedding kernel compared with traditional BoW approaches. Below are the brief descri...
متن کاملTowards Large-scale and Ultrahigh Dimensional Feature Selection Towards Large-scale and Ultrahigh Dimensional Feature Selection via Feature Generation
In many real-world applications such as text mining, it is desirable to select the most relevant features or variables to improve the generalization ability, or to provide a better interpretation of the prediction models. In this paper, a novel adaptive feature scaling (AFS) scheme is proposed by introducing a feature scaling vector d ∈ [0, 1] to alleviate the bias problem brought by the scalin...
متن کاملDeveloping a New Method in Object Based Classification to Updating Large Scale Maps with Emphasis on Building Feature
According to the cities expansion, updating urban maps for urban planning is important and its effectiveness is depend on the information extraction / change detection accuracy. Information extraction methods are divided into two groups, including Pixel-Based (PB) and Object-Based (OB). OB analysis has overcome the limitations of PB analysis (producing salt-pepper results and features with hole...
متن کاملBiomedical Semantic Indexing using Dense Word Vectors in BioASQ
Background: Biomedical curators are often required to semantically index large numbers of biomedical articles, using hierarchically related labels (e.g., MeSH headings). Large scale hierarchical classification, a branch of machine learning, can facilitate this procedure, but the resulting automatic classifiers are often inefficient because of the very large dimensionality of the dominant bag-of...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Computer Vision and Image Understanding
دوره 120 شماره
صفحات -
تاریخ انتشار 2014