Dense SIFT Descriptors Research Articles

Recognizing gender from images with facial makeup

<p>Recognizing the sex of an individual is a difficult task due to pose variation, occlusion, illumination effect, facial expression, plastic surgery, and makeup. In this manuscript, a novel approach for gender recognition with facial makeup is proposed. A novel Log-Gabor COSFIRE (LG-COSFIRE) filter is a shape-selective filter that is trained with prototype patterns of interest. The geometrical structure of the faces is acquired using the dual-tree complex wavelet transform (DT-CWT). Dense SIFT descriptor extracts the shape attributes of an image by building local histograms of gradient orientation. Finally, least square support vector machine (LS-SVM) is utilized to recognize the gender of an individual. The experiment was performed on self-built facial makeup for male and female (FMMF) database and achieves 89.7% accuracy.</p>

Improving Gray World Algorithm Guided by Scene Semantics

Gray world algorithm typically shows poor illuminant estimation performance due to scene variations of natural images. To address the above problem, an improved gray world algorithm guided by scene semantics is proposed. Firstly, dense-SIFT descriptors are calculated using grayscale images to avoid the interference of color-biased images, followed by the bag of words (BoW) model to generate unordered visual vocabulary. Secondly, based on the average brightness of these visual words, word frequency histograms are constructed weighted by brightness using the spatial pyramid matching (SPM) algorithm. Thirdly, the scene semantics similarity between images employing the histogram cross kernel function, and retrieve a set of candidate images that similar to the test image is calculated. Finally, after removing the outlier images using the isolated forest algorithm, the pixel statistics distributions of all remaining images are used to adaptively infer and update the fixed assumption of the gray world algorithm. The improved gray world algorithm implements color constancy through illuminant estimation. Experimental results in three publicly available color constancy datasets (ColorChecker, Cube+ and NUS) show that the proposed algorithm outperforms comparable improved gray world algorithms in single camera tests (nearly 20% angular error improvement), at the same time, achieves optimal performance in cross-camera tests.

Ghost-free multi exposure image fusion technique using dense SIFT descriptor and guided filter

A ghost-free multi-exposure image fusion technique using the dense SIFT descriptor and the guided filter is proposed in this paper. The results suggest that the presented scheme produces high-quality images using ordinary cameras and that too without the ghosting artifact. To do so, the dense SIFT descriptor is used to extract the local contrast information from source images. Whereas, for the dynamic scenes, the histogram equalization and median filtering are used to calculate the color dissimilarity feature. Three weighting terms: local contrast, brightness, and color dissimilarity feature are used to estimate the initial weights. The estimated initial weights contain discontinuities. Therefore, the guided filter is used to remove the noise and discontinuity in initial weights. Finally, the fusion is performed using a pyramid decomposition method. Experimental results prove the superiority of the proposed technique over existing state-of-the-art methods in terms of both subjective and objective evaluation.

Dense descriptor for visual tracking and robust update model strategy

Context analysis is a research field that is attracting growing interest in recent years, especially due to the encouraging results carried out by the semantic-based approach. Anyway, semantic strategies entail the use of trackers capable to show robustness to long-term occlusions, viewpoint changes and identity swap that represent the main problem of many tracking-by-detection solutions. This paper proposes a robust tracking-by-detection framework based on dense SIFT descriptors in combination with an ad-hoc target appearance model update able to overtake the discussed issues. The obtained performances show how our tracker competes with state-of-the-art results and manages occlusions, clutter, changes of scale, rotation and appearance, better than competing tracking methods.

Progressive match expansion via coherent subspace constraint

In this paper a quasi-dense matching algorithm called Progressive match Expansion via Coherent Subspace (PECS) is proposed. Our algorithm starts from a set of sparse seeds and iteratively expands potential matches in the region around the seeds until no more matches could be found. The main difference from previous methods is that our method computes a coherent non-rigid transformation to relate the matching pixels instead of using local planar affine model to approximate the real scene surface within the expanding region. The points in the expanding region are treated as a whole and all the matches satisfying the transformation are found at once. First, dense SIFT descriptors are extracted and a subspace encoding the feature similarity between two point sets is computed. This embedding pulls two points closer if they have similar features and makes the non-rigid transformation learning more robust. Second, a coherent non-rigid transformation in the subspace is computed to move one point set towards the other and the spatially aligned two points denote a match. The proposed model is robust to scenes with non-smooth surface and experiment results reveal the good performance in both 2D image matching and 3D reconstruction.

Fast Coding of Feature Vectors Using Neighbor-to-Neighbor Search.

Searching for matches to high-dimensional vectors using hard/soft vector quantization is the most computationally expensive part of various computer vision algorithms including the bag of visual word (BoW). This paper proposes a fast computation method, Neighbor-to-Neighbor (NTN) search [1] , which skips some calculations based on the similarity of input vectors. For example, in image classification using dense SIFT descriptors, the NTN search seeks similar descriptors from a point on a grid to an adjacent point. Applications of the NTN search to vector quantization, a Gaussian mixture model, sparse coding, and a kernel codebook for extracting image or video representation are presented in this paper. We evaluated the proposed method on image and video benchmarks: the PASCAL VOC 2007 Classification Challenge and the TRECVID 2010 Semantic Indexing Task. NTN-VQ reduced the coding cost by 77.4 percent, and NTN-GMM reduced it by 89.3 percent, without any significant degradation in classification performance.

3-D object retrieval using topic model

In the last few years, extensive effort has been spent to develop better performed 3-D object retrieval methods. View-based methods have attracted a significant amount of attention, not only because their state-of-art performance, but also they merely require some of a 3-D object's 2-D view images. However, most recent approaches only deal with the images' primordial-extracted features and ignore their hidden relationships. Considering these latent characters, a visual-topic-model 3-D object retrieval approach is introduced in this paper. In this framework, dense scale invariant feature transform(dense-SIFT) descriptors are extracted from a set of views of each 3-D object, and all the dense-SIFT descriptors are grouped into bag-of-word features using k-means clustering. Then, the topic distribution of a 3-D object is generated via latent dirichlet allocation (LDA) given its bag-of-word features. Gibbs sampling is applied in the learning and inference processing of LDA. We conduct experiments on the Princeton Shape Benchmark (PSB) and National Taiwan University 3D model database (NTU), and the experimental results demonstrate that the proposed method can achieve better retrieval effectiveness than the state-of-the-art methods under several standard evaluation measures.

Partial matching of 3D cultural heritage objects using panoramic views

In this paper, we present a method for partial matching and retrieval of 3D objects based on range image queries. The proposed methodology addresses the retrieval of complete 3D objects using range image queries that represent partial views. The core methodology relies upon Bag-of-Visual-Words modelling and enhanced Dense SIFT descriptor computed on panoramic views and range image queries. Performance evaluation builds upon standard measures and a challenging 3D pottery dataset originating from the Hampson Archaeological Museum collection.

Automated identification of animal species in camera trap images

Abstract Image sensors are increasingly being used in biodiversity monitoring, with each study generating many thousands or millions of pictures. Efficiently identifying the species captured by each image is a critical challenge for the advancement of this field. Here, we present an automated species identification method for wildlife pictures captured by remote camera traps. Our process starts with images that are cropped out of the background. We then use improved sparse coding spatial pyramid matching (ScSPM), which extracts dense SIFT descriptor and cell-structured LBP (cLBP) as the local features, that generates global feature via weighted sparse coding and max pooling using multi-scale pyramid kernel, and classifies the images by a linear support vector machine algorithm. Weighted sparse coding is used to enforce both sparsity and locality of encoding in feature space. We tested the method on a dataset with over 7,000 camera trap images of 18 species from two different field cites, and achieved an average classification accuracy of 82%. Our analysis demonstrates that the combination of SIFT and cLBP can serve as a useful technique for animal species recognition in real, complex scenarios.

Natural Image Classification Based on Improved Support Vector Machine

Local image representation based natural image classification is an important task. SIFT descriptors and bag-of-visterm (BOV)method have achieved very good results. Many studies focused on improving the representation of the image, and then use the support vector machine to classify and identify the image category. However, due to support vector machine its own characteristics, it shows inflexible and slower convergence rate for large samples，with the selection of parameters influencing the results for the algorithm very much. Therefore, this paper will use the improved support vector machine algorithm be based on ant colony algorithm in classification step. The method adopt dense SIFT descriptors to describe image features and then use two levels BOV method to obtain the image representation. In recognition step, we use the support vector machine as a classifier but ant colony optimization method is used to selects kernel function parameter and soft margin constant C penalty parameter. Experiment results show that this solution determined the parameter automatically without trial and error and improved performance on natural image classification tasks.

Integrated image representation based natural scene classification

Natural scene classification (NSC) is a challenging pattern classification problem. As one of state-of-the-art techniques, the bag-of-feature (BOF) model has received extensive considerations in characterizing the image. To boost the flexibility during visterm construction in BOF model, an integrated scheme for image representation is proposed by adaptive analysis on the local visual complexity of image itself. First, the flatness of each scene category is determined by the total flatness of all images belonging to this category. Then the new integrated image representation of the scene category is built by weighting the two representations (based on a pixels gray value descriptor and a dense SIFT descriptor) through the normalized coefficients computed by the flatness of the category. Finally, a hierarchical generative model is exploited to learn natural scene categories. Experimental results demonstrate that the satisfactory classification accuracy achieves about 83.67% on a large set of 15 categories of complex scenes.

How the Number of Interest Points Affect Scene Classification

This paper focuses on the relationship between the number of interest points and the accuracy rate in scene classification. Here, we accept the common belief that more interest points can generate higher accuracy. But, few effort have been done in this field. In order to validate this viewpoint, in our paper, extensive experiments based on bag of words method are implemented. In particular, three different SIFT descriptors and five feature selection methods are adopted to change the number of interest points. As innovation point, we propose a novel dense SIFT descriptor named Octave Dense SIFT, which can generate more interest points and higher accuracy, and a new feature selection method called number mutual information (NMI), which has better robustness than other feature selection methods. Experimental results show that the number of interest points can aggressively affect classification accuracy.

Scene Classification Using a Hybrid Generative/Discriminative Approach

We investigate whether dimensionality reduction using a latent generative model is beneficial for the task of weakly supervised scene classification. In detail we are given a set of labelled images of scenes (e.g. coast, forest, city, river, etc) and our objective is to classify a new image into one of these categories. Our approach consists of first discovering latent "topics" using probabilistic Latent Semantic Analysis (pLSA), a generative model from the statistical text literature here applied to a bag of visual words representation for each image, and subsequently training a multi-way classifier on the topic distribution vector for each image. We compare this approach to that of representing each image by a bag of visual words vector directly, and training a multi-way classifier on these vectors. To this end we introduce a novel vocabulary using dense colour SIFT descriptors, and then investigate the classification performance under changes in the size of the visual vocabulary, the number of latent topics learnt, and the type of discriminative classifier used (k-nearest neighbour or SVM). We achieve superior classification performance to recent publications that have used a bag of visual word representation, in all cases using the authors' own datasets and testing protocols. We also investigate the gain in adding spatial information. We show applications to image retrieval with relevance feedback and to scene classification in videos.