A New Efficient Optimal 2D Views Selection Method Based on Pivot Selection Techniques for 3D Indexing and Retrieval

In this paper, we propose a region-based image retrieval system using EHD (Edge Histogram Descriptor) and CLD (Color Layout Descriptor) of MPEG-7 descriptors. The combined descriptor can efficiently describe edge and color features in terms of sub-image regions. That is, the basic unit for the selection of the region-of-interest (ROI) in the image is the sub-image block of the EHD, which corresponds to 16 (i.e., 4x4) non-overlapping image blocks in the image space. This implies that, to have a one-to-one region correspondence between EHD and CLD, we need to take an 8x8 inverse DCT (IDCT) for the CLD. Experimental results show that the proposed retrieval scheme can be used for image retrieval with the ROI based image retrieval for MPEG-7 indexed images.

The MPEG-7 standard defines a set of descriptors that extract low-level features such as color, texture and object shape from an image and generate metadata that represents the extracted information. In this paper we propose a new image retrieval technique for image indexing based on the MPEG-7 scalable color descriptor. We use some specifications of the scalable color descriptor (SCD) for the implementation of the color histograms. The MPEG-7 standard defines 1 l norm − based matching in the SCD. But in our approach, for distance measurement, we achieve a better result by using cosine similarity coefficient for color histograms. This approach has significantly increased the accuracy of obtaining results for image retrieval. Experiments based on scalable color descriptors are illustrated. We also present the color spaces supported by the different image and video coding standards such as JPEG-2000, MPEG-1, 2, 4 and MPEG-7. In addition, this paper outlines the broad details of MPEG-7 Color Descriptors.

A new dominant color structure descriptor (DCSD) is proposed in this paper. It is designed to provide an efficient way to represent both color and spatial structure information with single compact descriptor. The descriptor combines the compactness of dominant color descriptor (DCD) and the retrieval accuracy of color structure descriptor (CSD) to enhance the retrieval performance in a highly efficient manner. The feature extraction and similarity measure of the descriptor are designed to address the problems of the existing descriptors while utilize the advantages of them. Experimental results show that DCSD has a significant improvement on both retrieval performance and descriptor size over DCD. An eight-color DCSD (DCSD 8) gives an averaged normalized modified retrieval rate (ANMRR) of 0.0993 using MPEG-7 common color dataset, outperforming compact configurations of scalable color descriptor and color structure descriptor with smaller descriptor size.

It is known that the rotation, scaling and translation invariant property of image moments has a high significance in image recognition. For this reason, the seven invariant moments presented by Hu are widely used in the field of image analysis. These moments are of finite order; therefore, they do not comprise a complete set of image descriptors. For this reason, we introduce in this paper another series of invariant moments of infinite order, which are based on normalized central moments. The non-orthogonal property of these moments causes the redundancy of information. To overcome this problem, we propose a new construction technique of non-separable orthogonal polynomials in two variables based on a recurrence formula and we present a new set of orthogonal moments, which are invariant to translation, scaling and rotation. The presented approaches are tested in several well-known computer vision datasets including moment’s invariability, image retrieval and classification of objects, this latter based on fuzzy K-means clustering algorithm. The performance of these invariant moments for classification and image retrieval is compared with some recent invariant moments such as invariants of multi-channel orthogonal radial-substituted Chebyshev moments, invariants of quaternion radial-substituted Chebyshev moments, invariants of rotational moments in Radon space and Legendre–Fourier moments in Radon space. The experimental results made using four databases of images, namely Columbia Object Image Library (COIL-20) database, MPEG7-CE shape database, COIL-100 database and ORL database, show that our orthogonal invariant moments have done better than the other descriptors tested.

Medical image processing is a vital component of modern healthcare, with content-based medical image retrieval (CBMIR) playing an increasingly important role. However, existing CBMIR methods still face challenges in handling multimodal datasets and large-scale image collections effectively. This paper proposes a novel CBMIR framework based on a hybrid bag-of-features model designed for improved scalability, interpretability, and retrieval performance. The approach integrates Bag-of-Visual-Words (BoVW) with shape and texture descriptors to enhance feature richness. Region of interest extraction is performed using the dynamic delaunay triangulation method to eliminate irrelevant regions and focus on diagnostically significant areas. Binary robust invariant scalable keypoints and K-means clustering are used to generate the BoVW, while edge histogram descriptors and gray-level co-occurrence matrix are employed to extract shape and texture features. The final retrieval is performed using a Euclidean distance similarity measure. Experimental evaluation on the IRMA 2009 and Kvasir datasets demonstrates that the proposed framework achieves competitive accuracy and robustness compared to existing methods. These results support the framework’s potential to address key limitations in CBMIR, especially in clinical environments where interpretability and computational efficiency are essential.

We describe the preliminary results of an ongoing work on content-based 3D retrieval, based on the selection of the best view of 3D objects according to semantic criteria. Experiments show that a single view is sufficient to achieve good performance, if it is the view in which the relevant shape features are maximally exposed.

Image and video indexing have become important with recent increase in digital image collections. A majority of proposed indexing techniques in the literature are based on features extracted from the entire image. In this paper, images are segmented by the K-mean clustering algorithm in order to allow searching, and retrieving at region level. Farther, the regions are classified into object and non-object classes as we may retrieve regions based on features tailored for the corresponding type. The object class contains clumped regions while the non-object class contains regions that scattered in the entire image scenes as constrained by (Chi) <SUP>2</SUP> statistic. The performance of the retrieval of four region indexing techniques, Histogram and three Wavelet-based techniques, are evaluated. The four indexing techniques are suitable for general domain image collections. The evaluation result has shown that, although, the three wavelet-based region indexing techniques provide a good comparable performances for non-object region queries, the histogram-based region indexing technique outperforms the three wavelet-based region indexing techniques for object region queries. The histogram technique is more suitable for indexing object regions. In the other hand the wavelet-based techniques are more suitable for non-object region indexing.

Development of various multimedia applications hinges on the availability of fast and efficient storage, browsing, indexing, and retrieval techniques. Given that video is typically stored efficiently in a compressed format, if we can analyze the compressed representation directly, we can avoid the costly overhead of decompressing and operating at the pixel level. Compressed domain parsing of video has been presented in earlier work where a video clip is divided into shots, subshots, and scenes. In this paper, we describe key frame selection, feature extraction, and indexing and retrieval techniques that are directly applicable to MPEG compressed video. We develop a frame-type independent representation of the various types of frames present in an MPEG video in which al frames can be considered equivalent. Features are derived from the available DCT, macroblock, and motion vector information and mapped to a low-dimensional space where they can be accessed with standard database techniques. The spatial information is used as primary index while the temporal information is used to enhance the robustness of the system during the retrieval process. The techniques presented enable fast archiving, indexing, and retrieval of video. Our operational prototype typically takes a fraction of a second to retrieve similar video scenes from our database, with over 95% success.

In recent years, the searching and indexing techniques for multimedia data are getting more attention in the area of multimedia databases. As many research works were done on the content-based retrieval of image and video data, less attention was received to the content-based retrieval of audio data. Audio is one of important multimedia information and there is a growing need for automatic audio indexing and retrieval techniques in recent years. Audio data contain abundant semantics and the audio signal processing can reduce computational complexity, so effective and efficient indexing and retrieval techniques for audio data are getting more attention. In this paper, problems of audio retrieval are discussed firstly. Then, main audio characteristics and features are introduced. Finally the combination of Support Vector Machine and General Model is described and the hybrid model is used in audio retrieval. Experiments show that the hybrid model is effective for audio classification.

We investigate possible improvements in seismic imaging. We discuss how the Fresnel zone relates to the migration aperture and introduce the concept of the Fresnel aperture, which is the direct time-domain equivalent, at the receivers’ surface, of the subsurface Fresnel zone. Through these concepts we propose a new and efficient method for optimal aperture selection and migration. For complex media, multipathing will occur and multiple Fresnel apertures can exist for a given image point. In practice, due to inaccuracies and smoothing of the background velocity macromodel, inaccuracies in the ray-tracing method used for Green’s function computations and possible noise corruption of the data, the true Fresnel apertures will, in many cases, be replaced by ‘false’ ones, with apparently new Fresnel apertures being added. Hence, contributions from these ‘false’ Fresnel apertures cause a noise-corrupted image of the subsurface. It is now assumed that the single scattered events are quite robust with respect to the above-mentioned distortions, and that their corresponding Fresnel apertures will remain essentially undistorted, with the strongest amplitudes. Based on this main assumption, we propose a method, analogous with velocity analysis, where the strong-amplitude Fresnel apertures can be picked interactively and at least semi-automatically. However, as in velocity analysis, a certain amount of user interaction has to be assumed. When this technique is combined with a prestack Kirchhoff-type depth-migration method, we call it Fresnel-aperture PSDM. This imaging method has been applied to data from both the Marmousi model and the North Sea. In both cases the improvements, when compared to conventional imaging, were considerable.

Recent advances in technology have made tremendous amounts of multimedia information available to the general population. An efficient way of dealing with this new development is to develop browsing tools that distill multimedia data as information oriented summaries. Such an approach will not only suit resource poor environments such as wireless and mobile, but also enhance browsing on the wired side for applications like digital libraries and repositories. Automatic summarization and indexing techniques will give users an opportunity to browse and select multimedia document of their choice for complete viewing later. In this paper, we present a technique by which we can automatically gather the frames of interest in a video for purposes of summarization. Our proposed technique is based on using Delaunay Triangulation for clustering the frames in videos. We represent the frame contents as multi-dimensional point data and use Delaunay Triangulation for clustering them. We propose a novel video summarization technique by using Delaunay clusters that generates good quality summaries with fewer frames and less redundancy when compared to other schemes. In contrast to many of the other clustering techniques, the Delaunay clustering algorithm is fully automatic with no user specified parameters and is well suited for batch processing. We demonstrate these and other desirable properties of the proposed algorithm by testing it on a collection of videos from Open Video Project. We provide a meaningful comparison between results of the proposed summarization technique with Open Video storyboard and K-means clustering. We evaluate the results in terms of metrics that measure the content representational value of the proposed technique.

This paper proposes the use of content base image retrieval (CBIR) techniques for indexing and retrieval of handwritten documents in Thai language. Issues associated with Thai handwritten documents are the lack of spacing between words, multi-level alphabets and different writing styles. This causes low recognition rate based on automated techniques such as Optical Character Recognition (OCR). This paper also examined off-line signature recognition techniques in order to adapt to Thai handwriting system for matching data. The objective of the proposal is to develop a semiautomated method to index and retrieve Thai handwritten documents based on sampled keywords by combining CBIR and signature recognition techniques.

Wireless Sensor Networks (WSN) are special types of wireless networks where hundreds or thousands of sensor nodes are working together. Since the lifetime of each sensor is equivalent to a battery, the energy issue is considered a major challenge. Clustering has been proposed as a strategy to extend the lifetime of wireless sensor networks. Many clustering algorithms consider the residual energy and distance between the nodes in the selection of cluster heads and others rotate the selection of cluster heads periodically. We propose in this article a CH selection followed by making clusters using the K-means algorithm and we present the PRIM algorithm to transmit the packets in multi-hop transmission between CHs and BS and choose the optimal path. The clustering scheme allows to decrease intra-cluster communications and to gain energy efficiency for sensor nodes. Computer simulation results show that our method aims to extend the lifetime of the wireless sensor network efficiently compared to other existing methods.

This paper introduces multimedia indexing and retrieval techniques to enable the extraction of botanical characteristics for semi-automatic plant recognition. The identification of plants requires recognition and determination of plant species by using specific features such as bloom color, inflorescences, shape of blooms, number of petals and shape of leaves. Our indexing and retrieval techniques will be integrated into an existing medicinal plant database, MedPhytreg. An evaluation study finishes the paper.

This paper proposes a score-based indexing technique for biometric databases. A fixed-length index is computed for each image in the database by calculating its match scores against a preselected set of representative images. Further, an efficient storage mechanism (i.e. index space) is developed to arrange the biometric images like traditional database records so that a rapid search is possible. During identification, the retrieval technique finds a list of similar candidates for the query image from the database using voting scheme. Finally, to identify the genuine match from the retrieved similar candidates, we perform a one-one match between the query and each similar candidate using modified Hausdorff distance measure. Experimental results on different databases show a significant performance improvement in terms of response time and identification accuracy compared to the existing indexing methods.