For almost a decade, Content-Based image Retrieval has been an active research area, yet one fundamental problem remains largely unsolved: how to measure perceptual similarity. To measure perceptual similarity, most r...
详细信息
For almost a decade, Content-Based image Retrieval has been an active research area, yet one fundamental problem remains largely unsolved: how to measure perceptual similarity. To measure perceptual similarity, most researchers employ the Minkowski-type metric. Our extensive data-mining experiments on visual data show that, unfortunately, the Minkowski metric is not very effective in modeling perceptual similarity. Our experiments also show that the traditional "static" feature weighting approaches are not sufficient for retrieving various similar images. In this paper, we report our discovery of a perceptual distance function through mining a large set of visual data. We call the discovered function dynamic partial distance function (DPF). When we empirically compare DPF to Minkowski-type distance functions, DPF performs significantly better in finding similar images. The effectiveness of DPF can be well explained by similarity theories in cognitive psychology.
The spatial resolution of the human visual system (HVS) decreases rapidly away from the point of fixation (foveation point). By exploiting this fact, we propose a watermarking approach that embeds the watermark energy...
详细信息
The spatial resolution of the human visual system (HVS) decreases rapidly away from the point of fixation (foveation point). By exploiting this fact, we propose a watermarking approach that embeds the watermark energy into the image peripheral according to foveation-based HVS contrast thresholds. Compared to the other HVS-based watermarking methods, the simulation results demonstrate an improvement in the robustness of the proposed approach against image degradations, such as JPEG compression, cropping and additive Gaussian, noise, in terms of subjective measures, based on foveation. In addition, the method proposed for still images is adapted for video and the robustness of the adapted method is tested against ITU H.263+ coding.
Current research on artificial vision and pattern recognition tends to concentrate either on numerical processing (filtering, morphological, spectral) or in symbolic or subsymbolic processing (neural networks, fuzzy l...
详细信息
ISBN:
(纸本)0819444855
Current research on artificial vision and pattern recognition tends to concentrate either on numerical processing (filtering, morphological, spectral) or in symbolic or subsymbolic processing (neural networks, fuzzy logic, knowledge-based systems). In this work we combine both kinds of processing in a hybrid imageprocessing architecture. The numerical processing part implements the most usual facilities (equalization, convolution filters, morphological filters, segmentation and description) in a way adequate to transform the input image into a polygonal outline. Then recognition is performed with a rule-based system implemented in Prolog. This allows a neat high-level representation of the patterns to recognize as a set of logical relations (predicates), and also the recognition procedure is represented as a set of logical rules. To integrate the numerical and logical components of our system, we embedded a Prolog interpreter as a software component within a visual programming language. Thus, our architecture features both the speed and versatility of a visual language application, and the abstraction level and modularity of a logical description.
Video quality metrics are intended to replace human evaluation with evaluation by machine. To accurately simulate human judgement, they must include some aspects of the human visual system. In this paper we present a ...
详细信息
ISBN:
(纸本)0780376226
Video quality metrics are intended to replace human evaluation with evaluation by machine. To accurately simulate human judgement, they must include some aspects of the human visual system. In this paper we present a class of low-complexity video quality metrics based on the Standard Spatial Observer (SSO). In these metrics, the basic SSO model is improved with several additional features from the current human vision models. To evaluate the metrics, we make use of the data set recently produced by the Video Quality Experts Group (VQEG), which consists of subjective ratings of 160 samples of digital video covering a wide range of quality. For each metric we examine the correlation between its predictions and the subjective ratings. The results show that SSO-based models with local masking obtain the same degree of accuracy as the best metric considered by VQEG (P5), and significantly better correlations than the other VQEG models. The results suggest that local masking is a key feature to improve the correlation of the basic SSO model.
In thus work, a neural controller for delay compensation in image samples detected by an active vision system of robotic heads, in ocular tracking tasks is presented. This control architecture based on CMAC (Cerebella...
详细信息
ISBN:
(纸本)0780370872
In thus work, a neural controller for delay compensation in image samples detected by an active vision system of robotic heads, in ocular tracking tasks is presented. This control architecture based on CMAC (Cerebellar Model Articulation Controller) model has de capacity of learning favored trajectories with less prediction error. This property is very important in robotic tasks of controlling the grasping or assembling of objects by a robotic arm. The main advantage of this cerebellar model is that the output is evaluated by means of a small number of memory cells that implies a high answer speed. Indeed, this visual robotic control avoids -as the human system - to know the kinematics of the process. This prediction module has been integrated in an architecture of visual-motor coordination based on VAM (Vector Associative Maps) models.
XYZ functions and cone sensitivities appear to play little role in visual perception in that colour computation does not appear to be carried out in cone or XYZ coordinates. In its first incarnation, spectral sharpeni...
详细信息
ISBN:
(纸本)0892082399
XYZ functions and cone sensitivities appear to play little role in visual perception in that colour computation does not appear to be carried out in cone or XYZ coordinates. In its first incarnation, spectral sharpening was proposed as a method for finding the color space, a linear combination of the cones, that best supported adaptation by a von Kries type model. The term sharpening is used because the resultant sensitivities have narrower support compared with the cones. In this paper we show that spectral sharpening also helps us to understand metamerism and color matching.
In real-time multicast communication scalability, reliability, and feedback implosion are of paramount importance. In this work we have developed an efficient feedback-free, entirely receiver-driven, and reliable visu...
详细信息
We propose a content-based method for coding entertainment movie sequences using texture replacement at the encoder and texture synthesis and mapping at the decoder. Our method reduces the bit rate of the compressed m...
详细信息
We propose a content-based method for coding entertainment movie sequences using texture replacement at the encoder and texture synthesis and mapping at the decoder. Our method reduces the bit rate of the compressed movie sequences significantly and yields higher visual quality of the textured background regions in the decoded movie sequences with mapped texture than that of the regions in the sequences simply encoded and decoded. Moreover, our method is efficient in terms of speed and may be applied as an overlay onto any standards-compliant coding system.
A measure is developed for comparing complex scenes produced by single-chip digital color cameras. The proposed measure is based on the CIELAB color space with appropriate considerations to the sensitivity of the Huma...
详细信息
A measure is developed for comparing complex scenes produced by single-chip digital color cameras. The proposed measure is based on the CIELAB color space with appropriate considerations to the sensitivity of the Human visual System (HVS) when viewing a complex scene. For comparison purposes, the error measures proposed have been implemented using the ΔE*ab, ΔE*94 and the recently recommended CIEDED2000 color differences.
image quality is known to be multivalued with some visual attributes or "nesses." One example of a "ness" is colorfulness. Published research has shown that the image quality versus colorfulness fu...
详细信息
image quality is known to be multivalued with some visual attributes or "nesses." One example of a "ness" is colorfulness. Published research has shown that the image quality versus colorfulness function reaches a maximum and increasing colorfulness beyond the optimum level actually degrades image quality. The present formulations of image quality models - e.g. Minkowski metrics and the Generalized Weighted Mean Hypothesis - implicitly assume that a monotonic relationship exists between image quality and the values of the independent "nesses." This paper proposes an extension to these popular image quality model formulations to represent the non-monotonic case. The new image quality model extension is compared to results of image quality versus colorfulness scaling of printed images.
暂无评论