Biomedical Image Retrieval in a Fuzzy Feature Space with Affine Region Detection and Vector Quantization of a Scale-Invariant Descriptor
نویسندگان
چکیده
This paper presents a biomedical image retrieval approach by detecting affine covariant regions and representing them with an invariant fuzzy feature space. The covariant regions simply refers to a set of pixels or interest points which change covariantly with a class of transformations, such as affinity. A vector descriptor based on Scale-Invariant Feature Transform (SIFT) is then associated with each region, computed from the intensity pattern within the region. The SIFT features are then vector quantized to build a codebbok of keypoints. By mapping the interest points extracted from one image to the keypoints in the codebook, their occurrences are counted and the resulting histogram is called the “bag of keypoints” for that image. Images are finally represented in fuzzy feature space by spreading each region’s membership values through a global fuzzy membership function to all the keypoints in the codebook. The proposed feature extraction and representation scheme is not only invariant to affine transformations but also robust against quantization errors. A systematic evaluation of image retrieval on a biomedical image collection demonstrates the advantages of the proposed image representation approach in terms of precision-recall.
منابع مشابه
DPML-Risk: An Efficient Algorithm for Image Registration
Targets and objects registration and tracking in a sequence of images play an important role in various areas. One of the methods in image registration is feature-based algorithm which is accomplished in two steps. The first step includes finding features of sensed and reference images. In this step, a scale space is used to reduce the sensitivity of detected features to the scale changes. Afterw...
متن کاملLocal Image Descriptor using VQ-SIFT for Image Retrieval
In this paper, we present local image descriptor using VQ-SIFT for more effective and efficient image retrieval. Instead of SIFT's weighted orientation histograms, we apply vector quantization (VQ) histogram as an alternate representation for SIFT features. Experimental results show that SIFT features using VQ-based local descriptors can achieve better image retrieval accuracy than the conventi...
متن کامل"Bag of keypoints"-based biomedical image search with affine covariant region detection and correlation-enhanced similarity matching
This paper presents a “bag of keypoints” based biomedical image retrieval approach by detecting affine covariant regions. The covariant regions simply refers to a set of pixels or interest points which are invariant to affine transformations, as well as occlusion, lighting and intra-class variations. To describe the intensity pattern within the interest points the Scale-Invariant Feature Transf...
متن کاملContent-Based Image Retrieval Based on Affine Noisy Invariant Color Region
The content-based image retrieval methods retrieve images by image features. In this paper, color and gray affine noisy invariant regions are extracted from a query and database images to help accurate retrieval on different attacks. Also a number of color statistical properties of the color region are computed and color feature vectors establishes for this region. Besides, for the gray region,...
متن کاملEfficient Image Recognition Using Local Feature and Fuzzy Triangular Number Based Similarity Measures
Image local scale invariant features are of great importance for object recognition. Among various local scale invariant feature descriptors, Scale Invariant Feature Transform (SIFT) descriptor has been shown to be the most descriptive one and thus widely applied to image retrieval, object recognition and computer vision. By SIFT descriptor, an image may be described by hundreds of key points w...
متن کامل