BoVW Model Research Articles

Integrated SURF and Spatial Augmented Color Feature Based Bovw Model with Svm for Image Classification

In this paper, Bag-of-visual-words (BoVW) model with Speed up robust features (SURF) and spatial augmented color features for image classification is proposed. In BOVW model image is designated as vector of features occurrence count. This model ignores spatial information amongst patches, and SURF Feature descriptor is relevant to gray images only. As spatial layout of the extracted feature is important and color is a vital feature for image recognition, in this paper local color layout feature is augmented with SURF feature. Feature space is quantized using K-means clustering for feature reduction in constructing visual vocabulary. Histogram of visual word occurrence is then obtained which is applied to multiclass SVM classifier. Experimental results show that accuracy is improved with the proposed method.

Improved Hieroglyph Representation for Image Retrieval

In recent years, an interdisciplinary effort between archaeologists and computer vision experts has emerged to provide image retrieval tools that facilitate and support cultural heritage preservation. The performance of these tools largely depends on the hieroglyph representation quality. In the literature, the most successful hieroglyph representation for retrieval following the BoVW model includes a thinning hieroglyph process and selects interest points through uniform random sampling. However, thinned hieroglyphs could have noise or redundant information, and a random set of interest points could include non-useful interest points that are different in each iteration. In this article, we propose improving this hieroglyph representation by pruning thinned hieroglyphs and introducing an improved interest-point selection. Our experiments show that our proposal significantly improves the hieroglyph retrieval results of state-of-the-art methods.

A Privacy-preserving Image Retrieval Method Based on Improved BoVW Model in Cloud Environment

ABSTRACTWith the rapid development of cloud computing technology, more and more users choose to outsource image data to clouds. To protect users’ privacy and guarantee data’s confidentiality, images need to be encrypted before being outsourced to CSP, but this brings new difficulties to some basic yet important data services, such as content-based image retrieval (CBIR). In this paper, a privacy-preserving image retrieval method based on an improved BoVW model is proposed. An improved BoVW method based on Hamming embedding can provide binary signatures that refine the matching based on visual words; therefore, retrieval precision is improved significantly; orthogonal transformation is utilized to implement privacy-preserving image retrieval, where image features are divided into two different fields with orthogonal decomposition, for which encryption and distance comparison are executed separately, and two kinds of operation results are fused in the final vector with orthogonal composition. As a result, cloud server can extract components from encrypted features directly and compare distance with those of query image, without violating the privacy of images and features. Any algorithm can be used to encrypt features, which enhance the practicability of the proposed method. The security analysis and experimental results prove its security and retrieval performance.

Image compression based on SVD for BoVW model in fingerprint classification

Image compression based on SVD for BoVW model in fingerprint classification

A robust CBIR framework in between bags of visual words and phrases models for specific image datasets

One objective of the Content Based Image Retrieval research field is to propose new methodologies and tools to manage the increasing number of images available. Linked to a specific context of small expert datasets without prior knowledge, our research work focuses on improving the discriminative power of the image representation while keeping the same efficiency for retrieval. Based on the well-known bag of visual words model, we propose three different methodologies inspired by the visual phrase model effectiveness and a compression technique which ensures the same effectiveness for retrieval than the BoVW model. Our experimental results study the performance of our proposals on different well known benchmark datasets and show its good performance compared to other recent approaches.

Research on the BOVW Model of Infrared Video Based on the Motion History

Aiming at the feature representation problem of infrared video, this paper presents an approach for bag of visual words model by considering the spatial and the temporal relations among the visual features. In this approach, motion mask image was generated based on motion history image, optical flow vector is mapping to visual code book. By using motion history value and motion energy value calculating the weighting coefficient, the BOVW was constructed based on angle voting. Experiments have demonstrated improved performances on motion feature representation in the infrared video.