The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In this paper, we present an IoT-based power-efficient color frame transmission and generation algorithm for video surveillance application. The conventional way is to transmit all R, G and B components of all frames. Using our proposed technique, instead of sending all components, first one color frame is sent followed by a series of gray-scale frames. After a certain number of gray-scale frames,...
Feature extraction becomes increasingly important as data grows high dimensional. Autoencoder as a neural network based feature extraction method achieves great success in generating abstract features of high dimensional data. However, it fails to consider the relationships of data samples which may affect experimental results of using original and new features. In this paper, we propose a Relation...
In traditional (k, n) threshold secret image sharing (SIS), a secret image is encrypted into n shadow images (also called shares) distributed to n associated participants. The secret image can be recovered by collecting any k or more shadow images, i.e., SIS is loss-tolerant. In SIS research domain, visual cryptography scheme (VCS) also called visual secret sharing (VSS) and Shamir's polynomial-based...
Real-world data such as medical images and sensor measurements is usually high-dimensional and limited. Using such datasets directly in machine learning tasks can lead to poor generalization. Feature learning is a general approach for transforming high-dimensional data points to a representational space with lower dimensionality. Machine learning models can be trained efficiently with such representations...
This paper introduces a spike camera with a distinct video capture scheme and proposes two methods of decoding the spike stream for texture reconstruction. The spike camera captures light and accumulates the converted luminance intensity at each pixel. A spike is fired when the accumulated intensity exceeds the dispatch threshold. The spike stream generated by the camera indicates the luminance variation...
Traditional intra prediction schemes usually only use the nearest adjacent reference lineto generate the prediction. Although the nearest reference line generally has the strongeststatistical correlation with current block, the farther non-adjacent reference lines can stillprovide potentialb etter prediction in some cases. Thus, in this paper, not only the nearestreference line but also the farther...
ISO recently published a new image compression standard, JPEG XT, which extends the popular JPEG standard towards higher dynamic range, compression of alpha channels and lossless coding. In part 7 ofJPEG XT, a two-layer lossy image compression for HDR images isintroduced that reconstructs HDR signals by the combination of a baselayer following the legacy JPEG standard, and an extension layer thatenlarges...
We propose a novel informed source separation method for audio object coding based on a recent sampling theory for smooth signals on graphs. Assuming that only one source is active at each time-frequency point, we compute an ideal map indicating which source is active at each time-frequency point at the encoder. This map is then sampled with a compressive graph signal sampling strategy that guarantees...
We present a novel method for constructing Variational Autoencoder (VAE). Instead of using pixel-by-pixel loss, we enforce deep feature consistency between the input and the output of a VAE, which ensures the VAE's output to preserve the spatial correlation characteristics of the input, thus leading the output to have a more natural visual appearance and better perceptual quality. Based on recent...
Active one-shot scanning techniques have been widely used for various applications. Stereo-based active one-shot scanning embeds a positional information regarding the image plane of a projector onto a projected pattern to retrieve correspondences entirely from a captured image. Many combinations of patterns and decoding algorithms for active one-shot scanning have been proposed. If the capturing...
Video communication through wireless channel has always been a challenging issue. Transmitting the compressed video through erroneous channel may lead to packet loss, eventually degrading the image quality. Thus an error detection and concealment scheme is applied at the decoder. This paper presents the error detection and concealment technique. The research work includes the spatio-temporal error...
In this paper, we propose a novel patch-based face hallucination method that consists of two patch-based sparse autoencoder (SAE) networks and a deep fully connected network (namely traversal network). The SAE networks are used to capture the intrinsic features of low-resolution (LR) images and high-resolution (HR) images in the hidden layers, while the traversal network is used to map features from...
In the last few years, visual privacy has become a major problem. Because of this, encrypted image processing has received a lot of attention within the scientific and business communities. Data hiding in encrypted images (DHEI) is an effective technique to embed data in the encrypted domain. The owner of an image encrypts it with a secret key and it is still possible to embed additional data without...
A novel perceptual multiple description coding with randomly offset quantizers (PMDROQ) is proposed. In the proposed PMDROQ method, the input image is partitioned into M subsets, and then obtaining M descriptions. In each description, one subset is directly encoded and decoded with different-small perceptual quantization stepsizes in DCT domain, while other subsets are predictively coded and decoded...
At low bit-rates, the conventional image coding standards, e.g., JPEG and JPEG 2000, do not have good compression performance due to the insufficiency of coding bits. A common solution to this problem is downsampling before encoding and reconstruction after decoding. Inspired by the wavelet domain downsampling-based compression scheme, we establish an enhanced low bit-rates coding framework by making...
In order to share a secret information among a group of participants, the method of secret sharing is used. The secret sharing method that is used to share or encrypt images is called Visual Cryptography. The main problems that subsist in Visual Cryptography are pixel expansion and poor image quality. Research are being conducted to solve the above mentioned problems. In this research, effective technique...
High Dynamic Range (HDR) videos are commonly compressed using existing Low Dynamic Range (LDR) coding standards. This necessarily implies a Tone Mapping (TM) stage which aims at reducing the input video range while preserving the most significant scene details. In most cases, a residual sequence is encoded and used at the decoder side to recover the HDR content. The challenge is to efficiently encode...
H.265/High Efficiency Video Coding (HEVC) is the latest next generation video compression standard posterior to H.264/AVC. However, despite its superior coding efficiency to the previous video coding standards, the complexity to implement it is an obstacle to overcome. Especially, combining the separate encoder and decoder has a disadvantage on the aspect of the size and power consumption. To solve...
User authentication based on biometrie system has several advantages over traditional systems which are only password-based. This architecture, known as fingerprint-cryptosystem has cryptography and fingerprint merged together, that securely stores the private key for cryptosystem. The private key of AES system is 128 bit long and is usually alphanumeric. Thus for a user to remember such a long password...
In this article an approach for realization of steganographic embedding by using functional transformation for adaptive positional number is considered.
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.