Histograms of local appearance descriptors are a popular representation for visual recognition. They are highly discriminant with good resistance to local occlusions and to geometric and photometric variations, but th...
详细信息
Histograms of local appearance descriptors are a popular representation for visual recognition. They are highly discriminant with good resistance to local occlusions and to geometric and photometric variations, but they are not able to exploit spatial co- occurrence statistics over scales larger than the local input patches. We present a multilevel visual representation that remedies this. The starting point is the notion that to detect object parts in images, in practice it often suffices to detect co- occurrences of more local object fragments. This can be formalized by codingimage patches against a codebook of known fragments or a more general statistical model and locally histogramming the resulting labels to capture their co- occurrence statistics. Local patch descriptors are converted into somewhat less local histograms over label occurrences. The histograms are themselves local descriptor vectors so the process can be iterated to code ever larger assemblies of object parts and increasingly abstract or 'semantic' image properties. We call these higher-level descriptors "hyperfeatures". We formulate the hyperfeature model and study its performance under several different image coding methods including k-means based Vector Quantization, Gaussian Mixtures, and combinations of these with Latent Dirichlet Allocation. We find that the resulting high-level features provide improved performance in several object image and texture image classification tasks.
A method of coding super high definition (SHD) still images based on vector quantization of wavelet coefficients is proposed. A compression scheme for SHD images should achieve data compression without any visible pic...
详细信息
A method of coding super high definition (SHD) still images based on vector quantization of wavelet coefficients is proposed. A compression scheme for SHD images should achieve data compression without any visible picture quality deterioration. We demonstrate that the proposed method meets this requirement. In this coding technique, each vector of wavelet coefficients is coded by a series of vectors of decreasing magnitudes, resulting in a successive approximation process. It also exploits the structural similarities among the bands. This provides efficient coding together with the ability to guarantee arbitrary distortion levels for each band, which can be exploited to achieve subjectively optimum performance. Conventional image compression techniques such as transform, subband, and vector quantization have already been tested for the coding of SHD images. Simulation results show that the proposed method outperforms the other SHD image coding methods reported in the literature.
A new image coding technique is presented as derived from an image decomposition into a low frequency component and many high frequency directional components. The directional filters and their properties are introduc...
详细信息
A new image coding technique is presented as derived from an image decomposition into a low frequency component and many high frequency directional components. The directional filters and their properties are introduced. Then the implementation of the directional decomposition and the selection of the information to be coded are described. The combination of transform domain coding of the low frequency component and spatial domain coding of the directional components led to acceptable results with compression ratios higher than 30 to 1. Zusammenfassung Es wird ein neuartiger Coder vorgestellt, der auf der Zerlegung des Bildes in eine niederfrequente und mehrere hochfrequente Richtungskomponenten beruht. Die Richtungsfilter und deren Eigenschaften werden beschrieben. Im folgenden wird auf die Implementierung der Zerlegung in die Richtungscomponenten und die Auswahl der zu codierenden Information eingegangen. Eine Kombination der Transformationcodierung der niederfrequenten Komponente mit der Ortsbereichscodierung der Richtungskomponenten fuehrt zu akzeptablen Ergebnissen bei Bitraten unter 0.2 bit/Bildpunkt.
A new technique to recover the information loss in a block-based image coding system is developed in this paper, The proposed scheme is based on fuzzy logic reasoning and can be divided into three main steps: 1) hiera...
详细信息
A new technique to recover the information loss in a block-based image coding system is developed in this paper, The proposed scheme is based on fuzzy logic reasoning and can be divided into three main steps: 1) hierarchical compass interpolation/extrapolation (HCIE) in the spatial domain for initial recovery of lost blocks that mainly contain low-frequency information such as smooth background 2) coarse spectra interpretation by fuzzy logic reasoning for recovery of lost blocks that contain high-frequency information such as complex textures and fine features 3) sliding window iteration (SWI), which is performed in both spatial and spectral domains to efficiently integrate the results obtained in steps 1) and 2) such that the optimal result can be achieved in terms of surface continuity on block boundaries and a set of fuzzy inference rules. The proposed method, which is suitable for recovering both isolated and contiguous block losses, provides a new approach for error concealment of block-based image coding systems such as the JPEG coding standard and vector quantization-based coding algorithms, The principle of the proposed scheme can also be applied to block-based video compression schemes such as the H.261, MPEG, and HDTV standards, Simulation results are presented to illustrate the effectiveness of the proposed method,
Differential encoding techniques are fast and easy to implement. However, a major problem with the use of differential encoding for images is the rapid edge degradation encountered when using such systems. This makes ...
详细信息
Differential encoding techniques are fast and easy to implement. However, a major problem with the use of differential encoding for images is the rapid edge degradation encountered when using such systems. This makes differential encoding techniques of limited utility especially when coding medical or scientific images, where edge preservation is of utmost importance. We present a simple, easy to implement differential image coding system with excellent edge preservation properties. The coding system can be used over variable rate channels which makes it especially attractive for use in the packet network environment.
In this paper, we present the design of directional lapped transforms for image coding. A lapped transform, which can be implemented by a prefilter followed by a discrete cosine transform (DCT), can be factorized into...
详细信息
In this paper, we present the design of directional lapped transforms for image coding. A lapped transform, which can be implemented by a prefilter followed by a discrete cosine transform (DCT), can be factorized into elementary operators. The corresponding directional lapped transform is generated by applying each elementary operator along a given direction. The proposed directional lapped transforms are not only nonredundant and perfectly reconstructed, but they can also provide a basis along an arbitrary direction. These properties, along with the advantages of lapped transforms, make the proposed transforms appealing for image coding. A block-based directional transform scheme is also presented and integrated into HD Phtoto, one of the state-of-the-art image coding systems, to verify the effectiveness of the proposed transforms.
Summary form only given. BCJR based source coding of image residuals is investigated. From a trellis representation of the residual, a joint source-channel coding system is formed. Then the BCJR algorithm is applied t...
详细信息
This paper describes a new method of segmentation of time-varying image sequences whose goal is object-oriented image coding. The segmentation represents a partition of each frame of the sequence into a set of regions...
详细信息
This paper describes a new method of segmentation of time-varying image sequences whose goal is object-oriented image coding. The segmentation represents a partition of each frame of the sequence into a set of regions which are homogeneous with regard to motion criterion, The region borders correspond to spatial contours of objects in the frame. Each spatio-temporal region is characterized by its temporal component, which is a model-dependent vector of motion parameters, and a structural component representing the polygonal approximation of the spatial contour of the region. The construction of spatio-temporal segmentation includes two phases: the initialization step and temporal tracking. The initialization step is based on the spatial segmentation of the first frame of the sequence. Then homogeneous spatial regions are merged through motion estimation in accordance with a motion-based criterion. The temporal tracking consists of the projection of the segmentation along the time axis, and its adjustment. Special attention is paid to the processing of occlusions. A predictive coding scheme is proposed which is based on the temporal coherence of the segmentation. This scheme is promising for a low bit-rate image compression. The results for teleconference and TV sequences show the high visual quality of reconstructed only by prediction images. Moreover, the bit-rates for motion coding are very low: from 0.002 to 0.007 bit/pixel for teleconference sequence and from 0.004 to 0.021 bit/pixel for complex TV sequence. A scheme for encoding of the structural information is proposed which requires 0.083-0.17 bit per pixel depending on the content of the sequence.
In this paper, an edge-oriented progressive image coding scheme using a hierarchical edge extraction is presented, This scheme is based on the two-component model, that is, edges and smooth component, We introduce sea...
详细信息
In this paper, an edge-oriented progressive image coding scheme using a hierarchical edge extraction is presented, This scheme is based on the two-component model, that is, edges and smooth component, We introduce searching near an approximate location algorithm for the edge extraction to avoid detecting spurious edges, thus, one can reproduce a primary image which conveys a general grasp of the scene while achieving the compression ratios as high as 250:1 for a head-and-shoulder image, By adding the smooth component to the primary image, we obtain acceptable quality images at the compression ratios over 60:1, It is shown through the simulations that the proposed scheme results in performance improvements over MPEG-2 I-picture coding in terms of both the subjective quality and signal-to-noise ratio, The main contributors of the performance improvement are: 1) a compact representation of the edge information using a hierarchical edge extraction and 2) a residual coding with a variable block size discrete cosine transform (DCT) employing an edge-based block segmentation.
A new wavelet-based L-infinity-constrained fixed and embedded coding technique is proposed. The embedded bit stream can be truncated for any desired distortion bound at a corresponding bit rate, so that the target upp...
详细信息
A new wavelet-based L-infinity-constrained fixed and embedded coding technique is proposed. The embedded bit stream can be truncated for any desired distortion bound at a corresponding bit rate, so that the target upper bound on the elements of the reconstruction error signal is guaranteed. The original image can also be coded up to a fixed a priori user-defined distortion bound, ranging up to lossless coding. A lifting-based wavelet decorrelating transform is employed on the original image, and exact relations are established between spatial and wavelet domain distortions. The wavelet coefficients are quantized by symmetric uniform quantizers for fixed-distortion coding and by families of embedded uniform deadzone scalar quantizers for embedded coding. The quantized coefficients are finally losslessly encoded using a quadtree-based coding algorithm. Any floating-point lifting-based wavelet transform can be used, and a few of the popular wavelet transforms included in the JPEG2000 verification model are worked out as examples. We compare other L-infinity-constrained coding schemes and show that our proposed coder offers in addition a fully embedded L-infinity-oriented bit stream. We illustrate also that the proposed coder retains the same capabilities as the state-of-the-art embedded wavelet-based co-decs, while providing superior compression results and embeddedness with respect to the L-infinity distortion measure. (C) 2003 SPIE and IST.
暂无评论