Local Image Regions Research Articles

Color and Local Maximum Edge Patterns Histogram for Content Based Image Retrieval

In this paper, HSV color local maximum edge binary patterns (LMEBP) histogram and LMEBP joint histogram are integrated for content based image retrieval (CBIR). The local HSV region of image is represented by LMEBP, which are evaluated by taking into consideration the magnitude of local difference between the center pixel and its neighbors. This LMEBP differs from the existing LBP in a manner that it extracts the information based on distribution of edges in an image. Further the joint histogram is constructed between uniform two rotational invariant first three LMEBP patterns. The color feature is extracted by calculating the histogram on Hue (H), Saturation (S) and LMEBP histogram on Value (V) spaces. The feature vector of the system is constructed by integrating HSV LMEBP histograms and LMEBP joint histograms. The experimentation has been carried out for proving the worth of our algorithm. It is further mentioned that the databases considered for experiment are Corel-1K and Corel-5K. The results after being investigated show a significant improvement in terms of their evaluation measures as compared to previously available spatial and transform domain methods on their respective databases.

Fusion of multichannel local and global structural cues for photo aesthetics evaluation.

Photo aesthetic quality evaluation is a fundamental yet under addressed task in computer vision and image processing fields. Conventional approaches are frustrated by the following two drawbacks. First, both the local and global spatial arrangements of image regions play an important role in photo aesthetics. However, existing rules, e.g., visual balance, heuristically define which spatial distribution among the salient regions of a photo is aesthetically pleasing. Second, it is difficult to adjust visual cues from multiple channels automatically in photo aesthetics assessment. To solve these problems, we propose a new photo aesthetics evaluation framework, focusing on learning the image descriptors that characterize local and global structural aesthetics from multiple visual channels. In particular, to describe the spatial structure of the image local regions, we construct graphlets small-sized connected graphs by connecting spatially adjacent atomic regions. Since spatially adjacent graphlets distribute closely in their feature space, we project them onto a manifold and subsequently propose an embedding algorithm. The embedding algorithm encodes the photo global spatial layout into graphlets. Simultaneously, the importance of graphlets from multiple visual channels are dynamically adjusted. Finally, these post-embedding graphlets are integrated for photo aesthetics evaluation using a probabilistic model. Experimental results show that: 1) the visualized graphlets explicitly capture the aesthetically arranged atomic regions; 2) the proposed approach generalizes and improves four prominent aesthetic rules; and 3) our approach significantly outperforms state-of-the-art algorithms in photo aesthetics prediction.

Digital Face Recognition Techniques for Matching with Sketches

Face recognition is a well studied problem in many application domains. However, matching sketches with digital face images is a very important law enforcement application that has received relatively less attention. The state-of art face recognition algorithms cannot be used directly and require additional processing to address the non-linear variations present in sketches and digital face images. One of the important clues in solving crimes and apprehending criminals is matching sketches with digital face images. This paper presents an automated algorithm that extracts discriminating information from local regions of both sketches and digital face images. Structural information along with minute details present in local facial regions are encoded using multi scale circular Weber’s local descriptor. Further, an evolutionary Memetic Optimization is proposed to assign optimal weights to every local facial region to boost the identification performance. Since, forensic sketches or digital face images can be of poor quality, a pre-processing technique is used to enhance the quality of images and improve the identification performance. Comprehensive experimental evaluation on different sketch databases show that the proposed algorithm yields better identification performance compared to existing face recognition algorithms and two commercial face recognition systems.

Augmenting multi-instance multilabel learning with sparse bayesian models for skin biopsy image analysis.

Skin biopsy images can reveal causes and severity of many skin diseases, which is a significant complement for skin surface inspection. Automatic annotation of skin biopsy image is an important problem for increasing efficiency and reducing the subjectiveness in diagnosis. However it is challenging particularly when there exists indirect relationship between annotation terms and local regions of a biopsy image, as well as local structures with different textures. In this paper, a novel method based on a recent proposed machine learning model, named multi-instance multilabel (MIML), is proposed to model the potential knowledge and experience of doctors on skin biopsy image annotation. We first show that the problem of skin biopsy image annotation can naturally be expressed as a MIML problem and then propose an image representation method that can capture both region structure and texture features, and a sparse Bayesian MIML algorithm which can produce probabilities indicating the confidence of annotation. The proposed algorithm framework is evaluated on a real clinical dataset containing 12,700 skin biopsy images. The results show that it is effective and prominent.

Mechanisms for similarity matching in disparity measurement

Early neural mechanisms for the measurement of binocular disparity appear to operate in a manner consistent with cross-correlation-like processes. Consequently, cross-correlation, or cross-correlation-like procedures have been used in a range of models of disparity measurement. Using such procedures as the basis for disparity measurement creates a preference for correspondence solutions that maximize the similarity between local left and right eye image regions. Here, we examine how observers’ perception of depth in an ambiguous stereogram is affected by manipulations of luminance and orientation-based image similarity. Results show a strong effect of coarse-scale luminance similarity manipulations, but a relatively weak effect of finer-scale manipulations of orientation similarity. This is in contrast to the measurements of depth obtained from a standard cross-correlation model. This model shows strong effects of orientation similarity manipulations and weaker effects of luminance similarity. In order to account for these discrepancies, the standard cross-correlation approach may be modified to include an initial spatial frequency filtering stage. The performance of this adjusted model most closely matches human psychophysical data when spatial frequency filtering favors coarser scales. This is consistent with the operation of disparity measurement processes where spatial frequency and disparity tuning are correlated, or where disparity measurement operates in a coarse-to-fine manner.

A nonparametric shape prior constrained active contour model for segmentation of coronaries in CTA images.

We present a nonparametric shape constrained algorithm for segmentation of coronary arteries in computed tomography images within the framework of active contours. An adaptive scale selection scheme, based on the global histogram information of the image data, is employed to determine the appropriate window size for each point on the active contour, which improves the performance of the active contour model in the low contrast local image regions. The possible leakage, which cannot be identified by using intensity features alone, is reduced through the application of the proposed shape constraint, where the shape of circular sampled intensity profile is used to evaluate the likelihood of current segmentation being considered vascular structures. Experiments on both synthetic and clinical datasets have demonstrated the efficiency and robustness of the proposed method. The results on clinical datasets have shown that the proposed approach is capable of extracting more detailed coronary vessels with subvoxel accuracy.

Robust and efficient visual tracking under illumination changes based on maximum color difference histogram and min-max-ratio metric

Visual tracking under illumination changes is a challenging task for numerous computer vision applications. We propose a robust and efficient tracking algorithm based on maximum color difference histogram (MCDH) and a well-designed min-max-ratio (MMR) similarity metric. Appearance model is essential to the tracker’s robustness under illumination changes. We propose a new feature descriptor MCDH, calculated by exploiting the maximum color difference information within the eight-neighborhood of each pixel in the object region, to build the object appearance model. Unlike the traditional histogram-based algorithms, the MCDH is efficiently extracted by employing the local integral histogram which is propagated in a specially designed local image region. The similarity metric plays an important role on accurately locating the target. However, the existing metrics are not suitable for comparisons of MCDHs due to many zero-valued bins in MCDH. Therefore, we propose a new MMR metric, defined as the average ratio between the minimum and maximum of a MCDH bin pair. The combination of proposed components enables the tracker to be robust to illumination changes with high computational efficiency. Experiments demonstrate superior performance of the proposed tracking algorithm compared with 10 state-of-art tracking methods when illumination varies.

A general non-local denoising model using multi-kernel-induced measures

Noises are inevitably introduced in digital image acquisition processes, and thus image denoising is still a hot research problem. Different from local methods operating on local regions of images, the non-local methods utilize non-local information (even the whole image) to accomplish image denoising. Due to their superior performance, the non-local methods have recently drawn more and more attention in the image denoising community. However, these methods generally do not work well in handling complicated noises with different levels and types. Inspired by the fact in machine learning field that multi-kernel methods are more robust and effective in tackling complex problems than single-kernel ones, we establish a general non-local denoising model based on multi-kernel-induced measures (GNLMKIM for short), which provides us a platform to analyze some existing and design new filters. With the help of GNLMKIM, we reinterpret two well-known non-local filters in the united view and extend them to their novel multi-kernel counterparts. The comprehensive experiments indicate that these novel filters achieve encouraging denoising results in both visual effect and PSNR index.

Neighborhood-level learning techniques for nonparametric scene models

A new stochastic learning algorithm for use in nonparametric pixel-level background models is presented in this paper. For the first time, we propose the use of kernel density estimation techniques in the model update step to identify outliers within the pixel-level sample collections and replace them with recently observed background pixel values. A neighborhood diffusion process that improves on recently reported scene model learning techniques is presented, wherein information sharing between similarly structured adjacent background models is encouraged to promote spatial consistency within localized image regions. We demonstrate the superiority of the proposed algorithm in comparison with the state-of-the-art visual background extraction system using the well-known percentage correct classification statistic and a new figure of merit, probability correct classification, presented here for the first time.

Automatic local exposure correction using bright channel prior for under-exposed images

We address the problem of exposure correction for under-exposed images in this paper. We propose the bright channel prior based on the statistics of well-exposed images. Using the proposed prior, we are able to estimate the relative exposure in local image regions. A well-exposed noise-free image is then recovered after exposure correction followed by non-uniform denoising and detail enhancement. Our experiments on under-exposed images of various scenes demonstrate the effectiveness of the bright channel prior. Our user study shows that the results generated by our exposure correction method are preferred over existing methods.

로컬 히스토그램 명세화에 기반한 화질 개선

In this paper we propose an image enhancement technique based on histogram specification method over local overlapping regions referred as Local Histogram Specification. First, both reference and original images are splitted into local regions that each overlaps half of its adjacent regions and general histogram specification method is used between corresponding local regions of reference and original image. However it produces noticeable boundary effects. Linear weighted image blending method is used to reduce this effect in order to make seamless image and we also proposed new technique dealing with over-enhanced contrast areas. We satisfied with our experimental results that showed better enhancement accuracy and less noise amplifications compared to other well-known image enhancement methods. We conclude that the proposed method is well suited for motion detection systems as a responsible part to overcome sudden illumination changes.

Bayesian Segmentation Based Local Geometrically Invariant Image Watermarking

Robust digital watermarking has been an active research topic in the last decade. As one of the promising approaches, feature point based image watermarking has attracted many researchers. However, the related work usually suffers from the following limitations: 1 The feature point detector is sensitive to texture region, and some noise feature points are always detected in the texture region. 2 The feature points focus too much on high contrast region, and the feature points are distributed unevenly. Based on Bayesian image segmentation, we propose a local geometrically invariant image watermarking scheme with good visual quality in this paper. Firstly, the Bayesian image segmentation is used to segment the host image into several homogeneous regions. Secondly, for each homogeneous region, image feature points are extracted using the multiscale Harris-Laplace detector, and the corresponding invariant local image regions are constructed adaptively. Finally, by taking the human visual system HVS into account, digital watermark is repeatedly embedded into local image regions by modulating the magnitudes of DFT coefficients. By binding the digital watermark with the invariant local image regions, the watermark detection can be done without synchronization error. Experimental results show that the proposed image watermarking is not only invisible and robust against common image processing operations such as sharpening, noise adding, and JPEG compression etc, but also robust against the geometric distortions.

Low-Rank Affinity Based Local-Driven Multilabel Propagation

This paper presents a novel low-rank affinity based local-driven algorithm to robustly propagate the multilabels from training images to test images. A graph is constructed over the segmented local image regions. The labels for vertices from the training data are derived based on the context among different training images, and the derived vertex labels are propagated to the unlabeled vertices via the graph. The multitask low-rank affinity, which jointly seeks the sparsity-consistent low-rank affinities from multiple feature matrices, is applied to compute the edge weights between graph vertices. The inference process of multitask low-rank affinity is formulated as a constrained nuclear norm andℓ2,1-norm minimization problem. The optimization is conducted efficiently with the augmented Lagrange multiplier method. Based on the learned local patch labels we can predict the multilabels for the test images. Experiments on multilabel image annotation demonstrate the encouraging results from the proposed framework.

Zernike moment and local distribution fitting fuzzy energy-based active contours for image segmentation

This paper presents a new region-based active contour model for extracting the object boundaries in an image, based on techniques of curve evolution. The proposed model introduces an energy functional that involves intensity distributions in local image regions and fuzzy membership functions. The local image intensity distribution information used to guide the motion of the contour, in the paper, is derived by Hueckel operator in the neighborhood of each image point. The parameters of Hueckel operator are estimated by a set of orthogonal Zernike moments before curve evolution. Meanwhile, the fuzzy membership functions are used to measure the association degree of each image pixel to the region outside and inside the contour. To minimize the energy functional, instead of solving the Euler–Lagrange equation of the underlying problem, the paper employs a direct method to compute the energy alterations. As a result, the model can deal with images with intensity inhomogeneity. In addition, the model effectively alleviates the sensitivity to contour initialization. Moreover, the model reduces computational cost, avoids problems associated with choosing time steps as well as allows fast convergence to the segmentation solutions. Experimental results on synthetic, real images and comparisons with other models show the desired performances of the proposed model.

Memetically Optimized MCWLD for Matching Sketches With Digital Face Images

One of the important cues in solving crimes and apprehending criminals is matching sketches with digital face images. This paper presents an automated algorithm to extract discriminating information from local regions of both sketches and digital face images. Structural information along with minute details present in local facial regions are encoded using multiscale circular Weber's local descriptor. Further, an evolutionary memetic optimization algorithm is proposed to assign optimal weight to every local facial region to boost the identification performance. Since forensic sketches or digital face images can be of poor quality, a preprocessing technique is used to enhance the quality of images and improve the identification performance. Comprehensive experimental evaluation on different sketch databases show that the proposed algorithm yields better identification performance compared to existing face recognition algorithms and two commercial face recognition systems.

Protein subcellular location pattern classification in cellular images using latent discriminative models

Motivation: Knowledge of the subcellular location of a protein is crucial for understanding its functions. The subcellular pattern of a protein is typically represented as the set of cellular components in which it is located, and an important task is to determine this set from microscope images. In this article, we address this classification problem using confocal immunofluorescence images from the Human Protein Atlas (HPA) project. The HPA contains images of cells stained for many proteins; each is also stained for three reference components, but there are many other components that are invisible. Given one such cell, the task is to classify the pattern type of the stained protein. We first randomly select local image regions within the cells, and then extract various carefully designed features from these regions. This region-based approach enables us to explicitly study the relationship between proteins and different cell components, as well as the interactions between these components. To achieve these two goals, we propose two discriminative models that extend logistic regression with structured latent variables. The first model allows the same protein pattern class to be expressed differently according to the underlying components in different regions. The second model further captures the spatial dependencies between the components within the same cell so that we can better infer these components. To learn these models, we propose a fast approximate algorithm for inference, and then use gradient-based methods to maximize the data likelihood.Results: In the experiments, we show that the proposed models help improve the classification accuracies on synthetic data and real cellular images. The best overall accuracy we report in this article for classifying 942 proteins into 13 classes of patterns is about 84.6%, which to our knowledge is the best so far. In addition, the dependencies learned are consistent with prior knowledge of cell organization.Availability: http://murphylab.web.cmu.edu/software/.Contact: Jeff.Schneider@cs.cmu.edu, murphy@cmu.edu

Super-resolution reconstruction of faces by enhanced global models of shape and texture

We present a computationally efficient method for the super-resolution reconstruction of face images from their low-resolution versions. It is based on generative models and utilizes both the shape and texture components together. The main idea is that the image details can be synthesized by global modeling of accurately aligned local image regions. In order to achieve sufficient accuracy in alignment, shape reconstruction is considered as a separate problem and solved together with texture reconstruction in a coordinated manner. Meanwhile, the statistical dependency between the shape and texture components is also considered. Moreover, different from traditional model-based super-resolution methods, we use a corrected form of the degradation operator with the aligned images. We show that when the degradation is used with the aligned texture components as is, it causes bias in the reconstructions. To overcome this problem, we reflect the same processing performed in alignment onto the degradation operator and use this corrected version in texture reconstruction. Experimental results show that the proposed solution provides superior image reconstructions (both qualitatively and quantitatively) in a faster way.

Improving Image Classification Using Semantic Attributes

The Bag-of-Words (BoW) model--commonly used for image classification--has two strong limitations: on one hand, visual words are lacking of explicit meanings, on the other hand, they are usually polysemous. This paper proposes to address these two limitations by introducing an intermediate representation based on the use of semantic attributes. Specifically, two different approaches are proposed. Both approaches consist in predicting a set of semantic attributes for the entire images as well as for local image regions, and in using these predictions to build the intermediate level features. Experiments on four challenging image databases (PASCAL VOC 2007, Scene-15, MSRCv2 and SUN-397) show that both approaches improve performance of the BoW model significantly. Moreover, their combination achieves the state-of-the-art results on several of these image databases.

An Image Region Description Method Based on Step Sector Statistics and its Application in Image Copy-Rotate/Flip-Move Forgery Detection

A robust method for local image region feature description based on step sector statistics is proposed in this paper. The means and the standard deviations along the radial direction of the circle image region are extracted through the sector masks, and the rearrangement of these statistics makes this image region description method rotation-robust. The proposed description method is applied in the detection of copy-rotate-move forgery, and it can detect the exact rotation angle between the duplicate regions. With minor extension, the proposed description method can also be applied in the detection of copy-flip-move forgery. The experimental results show that the proposed description method can work well for the detection of copy-rotate/flip-move forgery.

Local maximum edge binary patterns: A new descriptor for image retrieval and object tracking

A new algorithm meant for content based image retrieval (CBIR) and object tracking applications is presented in this paper. The local region of image is represented by local maximum edge binary patterns (LMEBP), which are evaluated by taking into consideration the magnitude of local difference between the center pixel and its neighbors. This LMEBP differs from the existing LBP in a manner that it extracts the information based on distribution of edges in an image. Further, the effectiveness of our algorithm is confirmed by combining it with Gabor transform. Four experiments have been carried out for proving the worth of our algorithm. Out of which three are meant for CBIR and one for object tracking. It is further mentioned that the database considered for first three experiments are Brodatz texture database (DB1), MIT VisTex database (DB2), rotated Brodatz database (DB3) and the fourth contains three observations. The results after being investigated show a significant improvement in terms of their evaluation measures as compared to LBP and other existing transform domain techniques.