ABSTRACT Fine‐grained image classification (FGIC) aims to distinguish visually similar categories by capturing subtle differences, yet the coexistence of large intra‐class variation and small inter‐class differences makes this task highly challenging. This paper provides a systematic review of recent deep learning‐based FGIC methods. According to the type of training data, existing approaches are categorized into four groups: (1) conventional models with large‐scale samples (strongly supervised, weakly supervised, semi‐supervised, and unsupervised); (2) few‐shot learning models for limited‐sample scenarios (e.g. meta‐learning and metric learning); (3) models leveraging external information, including multi‐modal and web‐sourced data; and (4) emerging diffusion‐based models. Representative algorithms in each category are summarized and analysed in terms of their advantages and limitations. The paper also reviews mainstream benchmark datasets and introduces a newly proposed application‐oriented dataset, CIIP‐TPID, to support real‐world tasks. Additionally, practical applications of FGIC in public security, medicine, and commerce are discussed. Finally, future research directions are outlined, including diffusion‐based data augmentation, advanced multi‐modal fusion, transformer architecture optimization, lightweight models for edge deployment, and robustness against noisy labels. This review provides a structured and up‐to‐date reference for researchers and practitioners in the field.

Bidirectional mapping-based generalized zero-shot learning (GZSL) methods rely on the quality of synthesized features to recognize seen and unseen data. Therefore, learning a joint distribution of seen-unseen classes and preserving the distinction between seen-unseen classes is crucial for GZSL methods. However, existing methods only learn the underlying distribution of seen data, although unseen class semantics are available in the GZSL problem setting. Most methods neglect retaining seen-unseen classes distinction and use the learned distribution to recognize seen and unseen data. Consequently, they do not perform well. In this work, we utilize the available unseen class semantics alongside seen class semantics and learn joint distribution through a strong visual-semantic coupling. We propose a bidirectional mapping coupled generative adversarial network (BMCoGAN) by extending the concept of the coupled generative adversarial network into a bidirectional mapping model. We further integrate a Wasserstein generative adversarial optimization to supervise the joint distribution learning. We design a loss optimization for retaining distinctive information of seen-unseen classes in the synthesized features and reducing bias towards seen classes, which pushes synthesized seen features towards real seen features and pulls synthesized unseen features away from real seen features. We evaluate BMCoGAN on benchmark datasets and demonstrate its superior performance against contemporary methods.

Aspect-level sentiment classification is a fine-grained task in sentiment analysis whose main purpose is to identify the sentiment polarity of a specific aspect. Current Graph Convolutional Network (GCN) has its distinctive superiority in tackling sentiment classification both semantically and syntactically. However, GCN still has deficiencies in introducing the noise during processing and dealing with sentences of complex structure. To address these issues, we propose a novel Bi-branch GCN (Bi-B GCN). In our model, an attention weight graph, by employing the attention mechanism, is constructed to substitute the basic syntax dependency tree and thus to remove the irrelevant information. Furthermore, a semantic dependency graph is devised to supplement the semantic information to the syntax dependency tree, based on which the connection between different words can be captured. In addition, on the task of sentiment classification, the integration of semantic information and the syntactic information is conducted by using a combinational gated mechanism. Substantial experiments to validate the working performance of Bi-B GCN are performed on a variety of datasets. The encouraging results establish a strong evidence of the high accuracy of the proposed model.

Domain adaptation aims to transfer knowledge from a domain with adequate labeled samples to a domain with scarce labeled samples. Prior research has introduced various open set domain adaptation settings in the literature to extend the applications of domain adaptation methods in real-world scenarios. This paper focuses on the type of open set domain adaptation setting where the target domain has both private (‘unknown classes’) label space and the shared (‘known classes’) label space. However, the source domain only has the ‘known classes’ label space. Prevalent distribution-matching domain adaptation methods are inadequate in such a setting that demands adaptation from a smaller source domain to a larger and diverse target domain with more classes. For addressing this specific open set domain adaptation setting, prior research introduces a domain adversarial model that uses a fixed threshold for distinguishing known from unknown target samples and lacks at handling negative transfers. We extend their adversarial model and propose a novel adversarial domain adaptation model with multiple auxiliary classifiers. The proposed multi-classifier structure introduces a weighting module that evaluates distinctive domain characteristics for assigning the target samples with weights which are more representative to whether they are likely to belong to the known and unknown classes to encourage positive transfers during adversarial training and simultaneously reduces the domain gap between the shared classes of the source and target domains. A thorough experimental investigation shows that our proposed method outperforms existing domain adaptation methods on a number of domain adaptation datasets.

Texture feature is important in describing tire pattern image which provides useful clue in solving crime cases and traffic accidents. In this paper, we propose a novel texture feature extraction method based on HOG (Histogram of Oriented Gradient) and dominant gradient (DG) in tire pattern images, named HOG-DG. The proposed HOG-DG is not only robust to illumination and scale changes but also is rotation-invariant. In the proposed HOG-DG, HOG features are first computed from circular local cells, and HOG features from an image are concatenated and normalized using the DG to construct the HOG-DG feature. HOG-DG is used to train a support-vector-machine (SVM) classifier for tire pattern classification. Experimental results demonstrate its outstanding performance for tire pattern description.

Convolutional Neural Networks are highly effective for image classification. However, it is still vulnerable to image distortion. Even a small amount of noise or blur can severely hamper the performance of these CNNs. Most work in the literature strives to mitigate this problem simply by fine-tuning a pre-trained CNN on mutually exclusive or a union set of distorted training data. This iterative fine-tuning process with all known types of distortion is exhaustive and the network struggles to handle unseen distortions. In this work, we propose distortion robust DCT-Net, a Discrete Cosine Transform based module integrated into a deep network which is built on top of VGG16 [1]. Unlike other works in the literature, DCT-Net is "blind" to the distortion type and level in an image both during training and testing. The DCT-Net is trained only once and applied in a more generic situation without further retraining. We also extend the idea of dropout and present a training adaptive version of the same. We evaluate our proposed DCT-Net on a number of benchmark datasets. Our experimental results show that once trained, DCT-Net not only generalizes well to a variety of unseen distortions but also outperforms other comparable networks in the literature.

The main challenge of single image super resolution (SISR) is the recovery of high frequency details such as tiny textures. However, most of the state-of-the-art methods lack specific modules to identify high frequency areas, causing the output image to be blurred. We propose an attention-based approach to give a discrimination between texture areas and smooth areas. After the positions of high frequency details are located, high frequency compensation is carried out. This approach can incorporate with previously proposed SISR networks. By providing high frequency enhancement, better performance and visual effect are achieved. We also propose our own SISR network composed of DenseRes blocks. The block provides an effective way to combine the low level features and high level features. Extensive benchmark evaluation shows that our proposed method achieves significant improvement over the state-of-the-art works in SISR.

Approximation of the geometric features is an essential step in point cloud segmentation and surface reconstruction. Often, the planar surfaces are estimated using principal component analysis (PCA), which is sensitive to noise and smooths the sharp features. Hence, the segmentation results into unreliable reconstructed surfaces. This article presents a point cloud segmentation method for building detection and roof plane extraction. It uses PCA for saliency feature estimation including surface curvature and point normal. However, the point normals around the anisotropic surfaces are approximated using a consistent isotropic sub-neighbourhood by Low-Rank Subspace with prior Knowledge (LRSCPK). The developed segmentation technique is tested using two real-world samples and two benchmark datasets. Per-object and per-area completeness and correctness results indicate the robustness of the approach and the quality of the reconstructed surfaces and extracted buildings.

Automatic 3D extraction of building roofs from remotely sensed data is important for many applications including city modeling. This paper proposes a new method for automatic 3D roof extraction through an effective integration of LIDAR (Light Detection And Ranging) data and multispectral orthoimagery. Using the ground height from a DEM (Digital Elevation Model), the raw LIDAR points are separated into two groups. The first group contains the ground points that are exploited to constitute a ‘ground mask’. The second group contains the non-ground points which are segmented using an innovative image line guided segmentation technique to extract the roof planes. The image lines extracted from the grey-scale version of the orthoimage are classified into several classes such as ‘ground’, ‘tree’, ‘roof edge’ and ‘roof ridge’ using the ground mask and colour and texture information from the orthoimagery. During roof plane extraction the lines from the later two classes are used to fit roof planes to the neighbouring non-ground LIDAR points. Finally, a new rule-based procedure is applied to remove planes constructed on trees. Experimental results show that the proposed method successfully removes vegetation and offers high extraction rates.

Multimodal image registration (MMIR) is the alignment of contents in images captured from different sensors or instruments. MMIR is important in medical applications as it enables the visualization of the complementary contents in biomedical microscopic images. The registration for such images can be challenging as the structures of their contents are usually only partially similar. Thus in this paper, we propose a new method to maximize the structural similarity of the contents in such images by utilizing intensity relationships among Red-Green-Blue color channels. Our experimental results will demonstrate that our proposed method substantially improves the accuracy of registering such images as compared to the state-of-the-art methods.

We propose a direct approach to learning sparse kernel classifiers for multi-instance (MI) classification to improve efficiency while maintaining predictive accuracy. The proposed method builds on a convex formulation for MI classification by considering the average score of individual instances for bag-level prediction. In contrast, existing formulations used the maximum score of individual instances in each bag, which leads to nonconvex optimization problems. Based on the convex MI framework, we formulate a sparse kernel learning algorithm by imposing additional constraints on the objective function to enforce the maximum number of expansions allowed in the prediction function. The formulated sparse learning problem for the MI classification is convex with respect to the classifier weights. Therefore, we can employ an effective optimization strategy to solve the optimization problem that involves the joint learning of both the classifier and the expansion vectors. In addition, the proposed formulation can explicitly control the complexity of the prediction model while still maintaining competitive predictive performance. Experimental results on benchmark data sets demonstrate that our proposed approach is effective in building very sparse kernel classifiers while achieving comparable performance to the state-of-the-art MI classifiers.

Texture feature plays a vital role in content based Image retrieval (CBIR). Wavelet texture feature modeled by generalized Gaussian density (GGD) [1] performs better than discrete wavelet texture feature. Curve let texture feature was proposed in [2]. In this paper, we compute a new texture feature by applying the generalized Gaussian density to the distribution of curve let coefficients which we call curve let GGD texture feature. The purpose of this paper is to investigate curve let GGD texture feature and compare its retrieval performance with that of curve let, wavelet and wavelet GGD texture features. Experimental results show that both curve let and curve let GGD features perform significantly better than wavelet and wavelet GGD texture features. Among the two types of curve let based features, curve let feature shows better performance in CBIR than curve let GGD texture feature. The findings are discussed in the paper.

Corner detectors have many applications in computer vision and image identification and retrieval. Contour-based corner detectors directly or indirectly estimate a significance measure (e.g., curvature) on the points of a planar curve, and select the curvature extrema points as corners. While an extensive number of contour-based corner detectors have been proposed over the last four decades, there is no comparative study of recently proposed detectors. This paper is an attempt to fill this gap. The general framework of contour-based corner detection is presented, and two major issues-curve smoothing and curvature estimation, which have major impacts on the corner detection performance, are discussed. A number of promising detectors are compared using both automatic and manual evaluation systems on two large datasets. It is observed that while the detectors using indirect curvature estimation techniques are more robust, the detectors using direct curvature estimation techniques are faster.

As texture information among pixels can be effectively represented using Local binary patterns (LBPs), image descriptors built using LBPs or its variants have been frequently used for various image analysis applications, e.g. medical image and texture image classification and retrieval. However, neither LBP nor any of its existing variants can be used to build descriptors for classifying multimodal images effectively. This is because the same object when captured in different modalities may result in opposite pixel intensity in some corresponding parts of the images, which in turn will cause their descriptors to be very different. To solve this problem, we propose a novel modality invariant texture descriptor which is built by modifying the standard procedure for building LBP. In this paper, we explain how the proposed descriptor can be built efficiently. We also demonstrate empirically that compared to all the state of the art LBP-based descriptors, the proposed descriptor achieves better accuracy for classifying multimodal images.

Music information retrieval (MIR) is an emerging research area that receives growing attention from both the research community and music industry. It addresses the problem of querying and retrieving certain types of music from large music data set. Classification is a fundamental problem in MIR. Many tasks in MIR can be naturally cast in a classification setting, such as genre classification, mood classification, artist recognition, instrument recognition, etc. Music annotation, a new research area in MIR that has attracted much attention in recent years, is also a classification problem in the general sense. Due to the importance of music classification in MIR research, rapid development of new methods, and lack of review papers on recent progress of the field, we provide a comprehensive review on audio-based classification in this paper and systematically summarize the state-of-the-art techniques for music classification. Specifically, we have stressed the difference in the features and the types of classifiers used for different classification tasks. This survey emphasizes on recent development of the techniques and discusses several open issues for future research.

In this paper, we explore the use of naive Bayes classifiers for music classification and retrieval. The motivation is to employ all audio features extracted from local windows for classification instead of just using a single song-level feature vector produced by compressing the local features. Two variants of naive Bayes classifiers are studied based on the extensions of standard nearest neighbor and support vector machine classifiers. Experimental results have demonstrated superior performance achieved by the proposed naive Bayes classifiers for both music classification and retrieval as compared to the alternative methods.

Effective texture feature is an essential component in any content based image retrieval system. In the past, spectral features, like Gabor and wavelet, have shown superior retrieval performance than many other statistical and structural based features. Recent researches on multi-resolution analysis have found that curvelet captures texture properties, like curves, lines, and edges, more accurately than Gabor filters. However, the texture feature extracted using curvelet transform is not rotation invariant. This can degrade its retrieval performance significantly, especially in cases where there are many similar images with different orientations. This paper analyses the curvelet transform and derives a useful approach to extract rotation invariant curvelet features. Experimental results show that the new rotation invariant curvelet feature outperforms the curvelet feature without rotation invariance.

In content based image analysis and retrieval, texture feature is an essential component due to its strong discriminative power. Directionality is one of the most significant texture features which are well perceived by the human visual system. A new method to calculate the directionality of image is proposed in this paper. In contrast to Tamura method which uses the statistical property of the directional histogram of an image to calculate its directionality, the proposed method makes use of the geometric property of the directional histogram. Both subjective and objective analyses prove that the proposed method outperforms the conventional Tamura method. It has also been shown that the proposed directionality has better retrieval performance than the conventional Tamura directionality.

The SIFT (scale invariant feature transform) has demonstrated its superior performance in identifying transformed images over many other approaches. However, both of its detection and matching stages are expensive, because a large number of keypoints are detected in the scale-space and each keypoint is described using a 128-dimensional vector. We present two possible solutions for feature-point reduction. First is to down scale the image before the SIFT keypoint detection and second is to use corners (instead of SIFT keypoints) which are visually significant, more robust, and much smaller in number than the SIFT keypoints. Either the curvature descriptor or the highly distinctive SIFT descriptors at corner locations can be used to represent corners.We then describe a new feature-point matching technique, which can be used for matching both the down-scaled SIFT keypoints and corners. Experimental results show that two feature-point reduction solutions combined with the SIFT descriptors and the proposed feature-point matching technique not only improve the computational efficiency and decrease the storage requirement, but also improve the transformed image identification accuracy (robustness).

Geometric transformations change the image pixel positions where the watermark is embedded. As a result, a copyright verifier fails to detect the watermark even though the watermark is present in the transformed image. The content-based watermarking schemes try to solve this problem by first dividing the image into many disjoint patches and then locating those patches with respect to the salient points of the image. Most of the existing content-based schemes are vulnerable to scaling and general affine transformations. They do not work well against high JPEG compression either. This paper presents a content-based blind watermarking scheme using corners. The proposed scheme achieves robustness against affine transformations and signal processing attacks by using triangular patch normalization and spread spectrum watermarking technique respectively.

Music emotion annotation is a task of attaching emotional terms to musical works. As volume of online musical contents expands rapidly in recent years, demands for retrieval by emotion are emerging. Currently, literature on music retrieval using emotional terms is rare. Emotion annotated data are scarce in existing music databases because annotation is still a manual task. Automating music emotion annotation is an essential prerequisite to research in music retrieval by emotion, for without which even sophisticated retrieval methods may not be very useful in a data deficient environment. This paper describes a machine learning approach to annotate music using a large number of emotional terms. We also estimate the training data size requirements for a workable annotation system. Our empirical result shows that 1) the task of music emotion annotation could be modelled using machine learning techniques to support a large number of emotional terms, 2) the combination of sampling method and data-driven detection threshold is highly effective in optimizing the use of existing annotated data in training machine learning models, 3) synonymous relationships enhance the annotation performance and 4) the training data size requirement is within reach for a workable annotation system. Essentially, automatic music emotion annotation enables music retrieval by emotion to be performed as a text retrieval task.

Feature extraction is a key issue in content-based image retrieval (CBIR). In the past, a number of texture features have been proposed in literature, including statistic methods and spectral methods. However, most of them are not able to accurately capture the edge information which is the most important texture feature in an image. Recent researches on multi-scale analysis, especially the curvelet research, provide good opportunity to extract more accurate texture feature for image retrieval. Curvelet was originally proposed for image denoising and has shown promising performance. In this paper, a new image feature based on curvelet transform has been proposed. We apply discrete curvelet transform on texture images and compute the low order statistics from the transformed images. Images are then represented using the extracted texture features. Retrieval results show, it significantly outperforms the widely used Gabor texture feature.

There are many applications, such as image copyright protection, where transformed images of a given test image need to be identified. The solution to this identification problem consists of two main stages. In stage one, certain representative features, such as corners, are detected in all images. In stage two, the representative features of the test image and the stored images are compared to identify the transformed images for the test image.Curvaturescale-space(CSS) corner detectors look for curvature maxima or inflection points on planar curves. However, the arc-length used to parameterize the planar curves by the existing CSS detectors is not invariant to geometric transformations such as scaling. As a solution to stage one, this paper presents an improved CSS corner detector using the affine-length parameterization which is relatively invariant to affine transformations. We then present an improved corner matching technique as a solution to the stage two. Finally, we apply the proposed corner detection and matching techniques to identify the transformed images for a given image and report the promising results.

Many contour-based image corner detectors are based on the curvature scale-space (CSS). We identify the weaknesses of the CSS-based detectors. First, the ldquocurvaturerdquo itself by its ldquodefinitionrdquo is very much sensitive to the local variation and noise on the curve, unless an appropriate smoothing is carried out beforehand. In addition, the calculation of curvature involves derivatives of up to second order, which may cause instability and errors in the result. Second, the Gaussian smoothing causes changes to the curve and it is difficult to select an appropriate smoothing-scale, resulting in poor performance of the CSS corner detection technique. We propose a complete corner detection technique based on the chord-to-point distance accumulation (CPDA) for the discrete curvature estimation. The CPDA discrete curvature estimation technique is less sensitive to the local variation and noise on the curve. Moreover, it does not have the undesirable effect of the Gaussian smoothing. We provide a comprehensive performance study. Our experiments showed that the proposed technique performs better than the existing CSS-based and other related methods in terms of both average repeatability and localization error.

Curvature scale-space (CSS) corner detectors look for curvature maxima or inflection points on planar curves. They use arc-length parameterized curvature. Therefore, they are not robust to affine transformations since the arc-length of a curve is not preserved under affine transformations. However, the affine-length of a curve is relatively invariant to affine transformations. This paper presents an improved CSS corner detector by applying the affine-length parameterized curvature to the CSS corner detection technique. A thorough robustness study has been carried out on a large database considering a wide range of affine transformations.

In contour-based comer detectors, absolute curvature values of many corners either remain unaltered or change slightly under affine transformations. Moreover, affine-length of a curve is relatively invariant to affine transformations. This paper presents a novel corner matching technique using corners detected by contour-based detectors. For each corner we use its position, absolute curvature value, and affine-lengths between this corner and other corners on the same curve. The iterative matching procedure tries to find three corner matches with minimum absolute curvature difference to calculate affine transformation parameters. Original corners are transformed with the estimated parameters prior to matching with the test corner set.

Music information retrieval (MIR) systems able to classify and retrieve different emotional expression in music pieces are still in its infancy. The challenge is on automatically extracting the perceptual features from music signal. Three rhythmic features that have influence on perceived emotional expression in music are: the tempo (fast/slow), the articulation (staccato/legato) and the motion (firm/flowing, where firm event is mainly evoked by the variation of loudness among events or by the durational variation between events). So far, only parts of the rhythmic features were extracted and used for emotion classification. As a result, either the classification result was not satisfactory or only broad classification of emotion was achieved. In this paper, we propose efficient and effective algorithms to determine these three rhythmic features based on both the findings from music psychology and psycho acoustics researches. Experimental results, with polyphonic music extracts mainly from CD recordings, have shown that our proposed algorithms are effective in determining these three rhythmic features.

Texture is an important feature to describe images. Though lots of work has been done for efficient texture feature extraction from rectangular images, no much effort has been made in texture feature extraction from arbitrary-shaped regions in region-based image retrieval (RBIR) system. In this paper, we present an efficient texture feature extraction algorithm for arbitrary-shaped regions. This algorithm first extends an arbitrary-shaped region into a rectangular area onto which block transformation can be applied. Based on the projection-onto-convex-sets (POCS) theory, a set of coefficients best describing the original region are finally obtained, from which texture feature of the region can be extracted. Via intensive experiments, we select a set of parameters proper for image retrieval purpose. Experimental results on real-world image database demonstrate the effectiveness of the proposed algorithm for image retrieval purpose

Vector quantization histogram (VQH) is a content-based image retrieval technique that has high retrieval effectiveness. However, as VQH's image indexing process is highly computationally intensive, it is not ideal as an online system. We propose an efficient image encoding technique to address this issue. Our experimental results show the proposed technique greatly improves the retrieval efficiency of VQH and it also has little adverse effects on VQH's retrieval effectiveness.

The performance of existing copyright protection schemes is questionable due to their vulnerability to geometric transformations. Though a few of them can resist global geometric transformations like rotation and scaling attacks, most of them are vulnerable to rotation-scale and cropping attacks. This paper presents a novel geometric distortion correction scheme robust to global geometric transformations. It restores an attacked image to its approximate original by reversing the attack using the invariant centroid and geometric moments of the image. Experimental results show the effectiveness of the proposed scheme

To improve the retrieval accuracy of content-based image retrieval, an important task is to reduce the 'semantic gap' between low-level image features and the richness of human semantics. We present a region-based image retrieval system using high-level semantic concepts. The contribution of the paper is two-fold. First, salient low-level features are extracted from arbitrarily-shaped regions. Second, a fuzzy-ID3 decision tree learning method is proposed to derive association rules which map low-level image features to high-level concepts. Experimental results prove that, by reducing the 'semantic gap', the proposed system not only improves the retrieval accuracy, but also supports users in query-by-keyword.

In this paper, spherical harmonics are proposed as shape descriptors for 2d images. We introduce the concept of connectivity; 2d images are decomposed using connectivity which is followed by 3d model construction. Spherical harmonics are obtained for 3d models and used as descriptors for the underlying 2d shapes. Difference between two images is computed as the Euclidean distance between their spherical harmonics descriptors. Experiments are performed to test the effectiveness of spherical harmonics for retrieval of 2d images. Item S8 within the MPEG-7 Still Images Content Set is used for performing experiments; this dataset consists of 3621 still images. Experimental results show that the proposed descriptors for 2d images are effective.

Perceptual tempo refers to listener's tempo perception how fast the music goes, when he listens to a piece of music with fairly constant overall tempo. Existing work on automatically determining the tempo of a piece of music is usually not able to determine the Perceptual tempo. Therefore, our previous work on the Perceptual Tempo Estimator (PTE) improved on existing work and experimental results had shown its effectiveness in determining the perceptual tempo than the existing work. However there are music pieces that have overall uniform perceived tempo, but have some small parts (segments) with quite different tempo from other parts. The PTE may not work well for this type of music pieces if the energy level in these small segments is significantly high. In this paper, we propose an improved PTE (IPTE) to provide better tempo determination. Experimental results show that IPTE is more effective in determining the Perceptual tempo of the music signal with constant perceived tempo.

The MPEG-7 standard defines two types of texture features: texture retrieval descriptor (TRD) for retrieval and texture browsing descriptor (TBD)for browsing. The retrieval process is straightforward but it is unclear how one could use TBD for browsing. This paper describes two methods of generating layouts for browsing a texture image database. The layouts are then subject to quantitative and qualitative evaluations. The experiments showed that: (1) only some features of TBD are appropriate for browsing, (2) once the inappropriate features are removed TBD is good for browsing only if the textures are structured, (3) the layouts generated usingTRDare more suitable for browsing.

Performance of traditional content-based image retrieval systems is far from user’s expectation due to the ‘semantic gap’ between low-level visual features and the richness of human semantics. In attempt to reduce the ‘semantic gap’, this paper introduces a region-based image retrieval system with high-level semantic color names. In this system, database images are segmented into color-texture homogeneous regions. For each region, we define a color name as that used in our daily life. In the retrieval process, images containing regions of same color name as that of the query are selected as candidates. These candidate images are further ranked based on their color and texture features. In this way, the system reduces the ‘semantic gap’ between numerical image features and the rich semantics in the user’s mind. Experimental results show that the proposed system provides promising retrieval results with few features used.

Gabor filters have been proven to be very useful for texture retrieval and are widely adopted (1, 2, 3, 4, 5, 6). However, the original Gabor texture features are rotation variant. Recently, Zhang et al proposed rotation normalization using circular shift. They have shown the proposed rotation normalization is effective through some examples, but did not comprehensively study its performance. The purpose of this paper is to study the performance of the rotation normalization on a good size texture database. Our experimental results show that the proposed rotation normalization is effective in retrieving rotated textures and has some adverse effect on retrieving non-rotated texture.

The texture retrieval approach based on Gabor filters has been shown to be very useful for texture retrieval and is widely adopted. We examine this approach in detail and question if this is a suitable approach. We then propose an alternative approach that does not use filters. Our experimental results and analysis show that our proposed approach performs better than the commonly used approach based on Gabor filters.

Previously, we proposed the concept of connectivity to obtain discriminating shape descriptors. In this paper, we use connectivity to obtain superior distance histograms for multi-scale images. Experiments are performed to evaluate the distance histograms, based on connectivity, for shape-based retrieval of multi-scale images. Item S8 within the MPEG-7 still images content set is used for performing experiments. Experimental results show that the proposed method enhances retrieval performance significantly.

We propose a method for enhancing the accuracy of shape descriptors. The concept of connectivity to obtain discriminating shape descriptors, is introduced. We show how connectivity is applied to two popular shape descriptors. Experiments are performed to test the effect of using connectivity with generic Fourier descriptors and distance histograms. Item S8 within the MPEG-7 still images content set is used for performing experiments. This dataset consists of 3621 still images. The experimental results show that connectivity enhances the performance of the methods significantly.

Gabor filter is widely used to extract texture features from images for image retrieval. A number of parameters (number of scales and orientations and filter mask size) are used in the Gabor filter. In the reported work so far, these parameters seem to be chosen without proper explanations. In this paper, we investigate the effects of different Gabor filter parameters on texture retrieval.

A dynamic approximate fitness-based hybrid evolutionary algorithm is presented here. The proposed model partially replaces expensive fitness evaluation by an approximate model. A cluster-based intelligent guided technique is used to decide on use of expensive function evaluation and dynamically adapt the predicted model. Avoiding expensive function evaluation speeds of the optimisation process. Also additional information derived from the predicted model at lower computational expense, is exploited to improve solution. Experimental findings support the theoretical basis of the proposed framework.

Shape (object) description consists a key part of image content description in MPEG-7. Most of existing shape descriptors are usually either application dependent or non-robust, making them undesirable for generic shape description. In this paper, an Enhanced Generic Fourier Descriptor (EGFD) is presented to overcome the drawbacks of existing shape representation techniques. The EGFD is obtained based on our previously proposed Generic Fourier Descriptors (GFD). It is acquired by deriving GFD from the rotation and scale normalized shape. Experimental results show that the proposed EGFD outperforms GFD and Zernike moments descriptors (ZMD) significantly.

Shape (object) description consists a key part of image content description in MPEG-7. In the development of MPEG-7, Zernike moment descriptor (ZMD) has been adopted as region-based shape descriptor. However, because Zernike moments are defined in a unit disk and extracted from shape in polar space, less shape information is used for skewed and stretched shapes. As a result, the extracted ZMD is not robust to skew and stretching distortions. An enhanced Zernike moment descriptor (EZMD) is proposed to overcome this drawback. The EZMD is acquired by deriving ZMD from the rotation and scale normalized shape. The rotation and scale normalization effectively suppress the uneven shape distribution within the unit disk and compensates the skew and stretching. Consequently, more shape information is used in the feature extraction. Experimental results show that the proposed EZMD outperforms ZMD significantly.

Shape description is one of the key parts of image content description in MPEG-7. Most existing shape descriptors are usually either application dependent or non-robust, making them undesirable for generic shape description. A generic Fourier descriptor (GFD) is proposed to overcome the drawbacks of existing shape representation techniques. The proposed shape descriptor is derived by applying a 2D Fourier transform on a polar raster sampled shape image. The acquired shape descriptor is application independent and robust. Experimental results show the GFD outperforms the Zernike moment descriptor (ZMD) which has been proposed as the shape descriptor for MPEG-7.

As more and more information is captured and stored in digital form, many techniques and systems have been developed for indexing and retrieval of text documents, audio, images, and video. The retrieval is normally based on similarities between extracted feature vectors of the query and stored items. Feature vectors are usually multidimensional. When the number of stored objects and/or the number of dimensions of the feature vectors are large, it will be too slow to linearly search all stored feature vectors to find those that satisfy the query criteria. Techniques and data structures are thus required to organize feature vectors and manage the search process so that objects relevant to the query can be located quickly. This paper provides a survey of these techniques and data structures.

Shape representation is a fundamental issue in the newly emerging multimedia applications. In the content based image retrieval (CBIR), shape is an important low level image feature. Many shape representations have been proposed. However, for CBIR, a shape representation should satisfy several properties such as affine invariance, robustness, compactness, low computation complexity and perceptual similarity measurement. Against these properties, in this paper we attempt to study and compare several shape descriptors which have been widely adopted for CBIR, they are: Fourier descriptors (FD), curvature scale space (CSS) descriptors (CSSD), Zernike moment descriptors (ZMD) and grid descriptors (GD). The strengths and limitations of these methods are analyzed and clarified. Retrieval results are given to show the comparison.