Search

In this paper, we propose a method to increase vection strength through video image processing in the periphery, rather than the center, of the visual field. Specifically, we propose two methods. One is an image stretching process in the visual periphery and the other is an alpha-blending process with an expanding circle grating in the periphery of the field. We clarified the relationship between the processing conditions and vection strength and found that stretching in the left–right direction increased vection strength while stretching in the downward direction did not. When adding expanding grating by alpha-blending, vection strength and duration were increased in almost all cases. [ABSTRACT FROM AUTHOR]

This paper presents a new and high-performance inaccurate Full Adder Cell utilizing the Carbon Nanotube Field Effect Transistor (CNFET) technology. Comprehensive simulations are performed at the transistor and application levels to justify the performance of our design. Simulations performed using the HSPICE tool confirm the significant improvement in the performance of the proposed circuit delay, power-delay product (PDP) and energy-delay product (EDP) compared to competitor designs. Additionally, via a MATLAB tool, the image blending (alpha blending) application uses inaccurate Full Adder cells. Software simulations confirm the suitable quality of the final images according to the image quality evaluation criteria. [ABSTRACT FROM AUTHOR]

The post pandemic era has transformed the traditional classrooms into digital classrooms. The state-of-art writing is being replaced by digital writing which requires the use of keyboard, touchscreen, digital pen, stylus, etc. Despite the availability of many teaching tools, the need for touch screen supporting PCs and other touch based peripheral devices is high and quite expensive. To solve this issue, an interactive virtual writing tool using hand tracking mechanism is proposed. This paper proposes an Artificial Intelligence (AI) based Virtual Board which employs the blended mechanism involving the core concepts of information technology domain namely AI and object tracking. The proposed AI Virtual Board is an effective teaching tool to illustrate demonstration of the teaching concepts accurately. [ABSTRACT FROM AUTHOR]

This paper presents a new and high-performance inaccurate Full Adder Cell utilizing the Carbon Nanotube Field Effect Transistor (CNFET) technology. Comprehensive simulations are performed at the transistor and application levels to justify the performance of our design. Simulations performed using the HSPICE tool confirm the significant improvement in the performance of the proposed circuit delay, power-delay product (PDP) and energy-delay product (EDP) compared to competitor designs. Additionally, via a MATLAB tool, the image blending (alpha blending) application uses inaccurate Full Adder cells. Software simulations confirm the suitable quality of the final images according to the image quality evaluation criteria.

Steganography plays a big role in secret communication by concealing secret information in the carrier. This paper presents a graph signal processing-based robust image steganography technique for posting images over social networks. In the embedding, we first obtained a scrambled version of the secret image using quantum scrambling. Next, we applied graph wavelet transformation on both the cover image and scrambled secret image followed by α (alpha) blending on both image signals (cover image signal and scrambled image signal). Finally, inverse graph wavelet transformation of the resulting image was undertaken to obtain the stego image. In this paper, the use of graph wavelet transformation improved interpixel correlation, which resulted in the excellent visual quality of both the stego image and the extracted secret image. Our experiments show that the picture quality of both the cover image and the stego image is exactly the same. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel method to address the nighttime single image dehazing problem. Estimation of the ambient illumination map and transmission map are the key steps of modern dehazing approaches. For hazy scenes at night, ambient illumination is usually not globally isotropic as a nighttime scene typically contains multiple light sources. Frequently, Light source regions and non-light source regions exhibit distinct color features. However, existing nighttime dehazing methods have been attempting to process these two regions based on identical prior assumptions. Moreover, the commonly-used local maximum pixel method tends to over-estimate the ambient illumination. These two drawbacks result in color distortions and halo artifacts around the light source regions in the output images. In this work, we present a pixel-wise alpha blending method for estimating the transmission map, where the transmissions estimated from dark channel prior (non-light source region) and the proposed bright channel prior (light source region) are effectively blended into one transmission map guided by a brightness-aware weights map. Based on the Retinex theory, a channel difference guided filtering method is proposed to estimate the ambient illumination, which produces a spatially variant low-frequency passband that selectively retains the high-frequency edge details. Extensive experiments on the benchmarks demonstrate that our method outperforms the state-of-the-art methods for nighttime image dehazing, especially in terms of color consistency and halo artifacts reduction in the dehazed images.

High-level synthesis, HLS is a technology to convert the software into the hardware automatically. It is expected as a technology that can greatly reduce the load of the hardware development. However, the current HLS that cannot convert the software not considered the hardware configuration into the optimum hardware. One of characteristics of the hardware to be considered is the burst transfer of memory access. In this paper, we evaluate the burst transfer with a subject of alpha blending processing as a theme. It is necessary to describe the program, so that the HLS tool can implicitly infer the burst transfer, because HLS tool does not have a pragma designating the burst transfer. We consider the description method of the program to infer the burst transfer and clarify the influence of read/write burst transfer on alpha blending. [ABSTRACT FROM AUTHOR]

In this paper, we provide an efficient hybrid video blending scheme to improve the naturalness of composite video in Poisson equation-based composite methods. In image blending process, various blending methods are used depending on the purpose of image composition. The hybrid blending method proposed in this paper has the characteristics that there is no seam in the composite video and the color distortion of the object is reduced by properly utilizing the advantages of Poisson blending and alpha blending. First, after blending the source object by the Poisson blending method, the color difference between the blended object and the original object is compared. If the color difference is equal to or greater than the threshold value, the object of source video is alpha blended and is added together with the Poisson blended object. Simulation results show that the proposed method has not only better naturalness than Poisson blending and alpha blending, but also requires a relatively small amount of computation. [ABSTRACT FROM AUTHOR]

The digital watermarking scheme has obtained its prominence as a result of its capability to offer secure mechanism for copyright protection or prevention of illegal duplication and authenticity of digital contents. The major objective of developing an image watermarking technique is to satisfy imperceptibility and robustness requirements simultaneously. In order to achieve this objective, in this paper, a robust digital image watermarking technique based on a cascaded Discrete Orthogonal Stockwell Transform (DOST) using Discrete Wavelet Transform (DWT) and Singular Value Decomposition (SVD) in colour images is proposed. In this approach, Alpha blending is used to embed the watermark within the singular value of the cover image. The performance of the developed scheme is evaluated using Normalized Correlation Coefficient (NCC) and Peak Signal to Noise Ratio (PSNR) as performance metrics for robustness and imperceptibility. The results of the NCC values obtained for accessing the robustness of the watermarked image when subjected to Gaussian, Salt and Pepper and Speckle noise under three different host images and watermarks as shown respectively. Lena and Mandril, Pepper and Nepal Logo and A.B.U Logo and EC Logo are 0.9247, 0.9721, 0.9541, 0.9145, 0.9460, 0.9700, 0.8588, 0.9704 and 0.9614. The results of the PSNR value obtained for accessing the imperceptibility of the watermarked image is 79.69dB. Comparison of the developed scheme with referenced scheme in terms of perceptual quality of the watermarked image showed PSNR values of 47.40dB. This represents 40.52% improvement of imperceptibility Experimental results illustrate that the proposed technique enhanced the robustness and imperceptibility of the watermarking techniques in comparison with previous works and results found indicates the proposed technique is able to withstand a variety of image processing attacks. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, we propose novel GPU accelerated algorithms for interactive point-based rendering (PBR) and high-quality shading of transparent point surfaces. By introducing the concept of deferred blending we are able to formulate the smooth point interpolation problem as an image compositing post-processing task. Consequently, our new PBR algorithm does not suffer from an extra visibility-splatting pre-render pass, for conservative –-buffer visibility culling, as this is eventually performed together with the smooth point interpolation during image compositing. Moreover, this new deferred blending concept enables hardware accelerated transparent PBR with combined effects of multi-layer transparency, refraction, specular reflection, and per-fragment shading. Deferred blending is based on a separation of the point data into not self-overlapping minimal independent groups, a multi-target rendering pass and an image compositing post-processing stage. We present different grouping algorithms for off-line and on-line processing. For basic opaque surface rendering and simple transparency effects, our novel algorithm only needs a single geometry rendering pass. For high-quality transparent image synthesis one extra rendering pass is sufficient. Besides transparency, per-fragment reflective and refractive multi-layer effects (e.g. environment mapping) are supported in our algorithm. [Copyright &y& Elsevier]

Alpha colours were introduced for image compositing, using a pixel coverage model. Algebraically they resemble homogeneous coordinates, widely used in projective geometry calculations. We show why this is the case. This allows us to extend alpha beyond compositing, to all colour calculations regardless of whether pixels are involved and without the need for a coverage model. Our approach includes multi-channel spectral calculations and removes the need for 7 channel and 6 channel alpha colour operations. It provides a unified explanation of pre-multiplied and non pre-multiplied colours, including negative coordinates and infinite points in colour space. It permits filter and illumination operations. It unifies the three existing significant compositing models in a single framework. It achieves this with a physically-plausible energy basis. Keywords: projective geometry, homogeneous coordinates, image compositing, alpha blending, alpha compositing, colour representation, filtering, spectral colour, projective alpha colour [ABSTRACT FROM AUTHOR]

• End-to-end framework for gait recognition invariant to carried objects. • Alpha blending generative adversarial network for removing carried objects. • State-of-the-art accuracy for gait recognition under various carrying objects. Gait recognition invariant to carried objects (COs) is very difficult in a real-life scene because the COs can have various shapes and sizes, in addition to unpredictable carrying locations (e.g., front, back, and side, or multiple locations). Therefore, in this paper, we propose a robust method for gait recognition against various COs by reconstructing a gait template without COs. A straightforward approach is to directly generate a gait template without COs given a gait template with COs as the input using a conventional generative adversarial network. There is, however, a potential risk of unnecessarily altering parts that were originally unaffected by COs (e.g., leg parts for a person carrying a backpack). Because we do not want to touch such unaffected parts in the original template, we first estimate a gait template without COs, and then blend it with the original template by an estimated alpha matte that indicates the blending parameters. We then create an alpha-blended template from the original template and the generated template without COs based on the estimated alpha matte. We use two independent generators to estimate the alpha matte and the generated template without COs. Finally, we feed the alpha-blended gait template into a state-of-the-art discrimination network for gait recognition. The experimental results on three publicly available gait databases with real-life COs demonstrate the state-of-the-art performance of the proposed method. [ABSTRACT FROM AUTHOR]