Sea ice has a significant effect on climate change and ship navigation. Hence, it is crucial to draw sea-ice maps that reflect the geographical distribution of different types of sea ice. Many automatic sea-ice classification methods using synthetic aperture radar (SAR) images are based on the polarimetric characteristics or image texture features of sea ice. They either require professional knowledge to design the parameters and features or are sensitive to noise and condition changes. Moreover, ice changes over time are often ignored. In this article, we propose a new SAR sea-ice image classification method based on a combined learning of spatial and temporal features, derived from residual convolutional neural networks (ResNet) and long short-term memory (LSTM) networks. In this way, we achieve automatic and refined classification of sea-ice types. First, we construct a seven-type ice data set according to the Canadian Ice Service ice charts. We extract spatial feature vectors of a time series of sea-ice samples using a trained ResNet network. Then, using the feature vectors as inputs, the LSTM network further learns the variation of the set of sea-ice samples with time. Finally, the extracted high-level features are fed into a softmax classifier to output the most recent ice type. Taking both spatial features and time variation into consideration, our method can achieve a high classification accuracy of 95.7% for seven ice types. Our method can automatically produce more objective sea-ice interpretation maps, allowing detailed sea-ice distribution and improving the efficiency of sea-ice monitoring tasks.

In this paper, a dataset of images reconstructed from digital holograms is presented. The dataset consists of 19 samples, with 49 reconstructions for each one, from different viewpoints and distances. The proposed dataset can be utilized in several research fields related to holography, such as perceptual visual quality evaluation, image quality metrics assessment, data compression and development of new image enhancement techniques. The rendering process applied for the dataset generation is described and a presentation methodology for the reconstructed images is proposed.

Light field acquisition devices can capture static and dynamic information of the light field in space that is processed using computational imaging techniques for creating visual representation of the captured scene. The main applications are the creation of visual effects such as perspective change, refocusing, recoloring. Advances in light field technologies will provide the devices and tools needed for the development of new services in the virtual/augmented/merged reality domains. This paper presents an analysis of the effects of light field subsampling on the quality of experience in refocusing applications.

Plenoptic images are obtained from the projection of the light crossing a matrix of microlens arrays which replicates the scene from different direction into a camera device sensor. Plenoptic images have a different structure with respect to regular digital images, and novel algorithms for data compression are currently under research. This paper proposes an algorithm for the compression of plenoptic images. The micro images composing a plenoptic image are processed by an adaptive prediction tool, aiming at reducing data correlation before entropy coding takes place. The algorithm is compared with state-of-the-art image compression algorithms, namely, JPEG 2000 and JPEG XR. Obtained results demonstrate that the proposed algorithm improves the coding efficiency.

User expectations while accessing visual content from mobile devices are often neglected for reasons that are mainly related to the time varying nature of overlay networks. Fast spreading of smart phone devices is fostering novel applications enabling cooperative access to multimedia resources exploiting cooperation between devices by sharing network resources. This paper focuses on accessing remote images from smart phone devices in a cooperative scenario. A client-server architecture enabling network resource sharing for image download applications is proposed. Experimental analysis is based on subjective evaluation where user compares direct access to images with the proposed cooperative access. Results show that downloading time can be drastically reduced for an increased user experience.

Image data compressed with JPEG XR when transmitted over error-prone channels is severely distorted. In fact, due to the adaptive coding strategies used by the codec, even a single bit error causes a mismatch in the alignment of the reading position from the bitstream, leading to completely different images at the decoder side. We propose an extension to the JPEG XR algorithm, consisting in an error recovery process enabling the decoder to realign itself to the right bitstream position and to correctly decode the most part of the image. We have performed several experiments using different encoder parameter and different error probabilities while image distortion is measured by PSNR objective metric. The simplicity of the proposed algorithm adds very little computational overhead and seems very promising as confirmed by objective image quality results in experimental tests.

The paper aims on the study of a system for user authentication based on the use of JPEG2000 images as passwords. The proposed method is thought to solve the traditional problems related to the authentication process in the Internet environment by exploiting the human brain's remarkable ability in image recognition. The architecture proposed is user-friendly, secure and cost effective and it can be used both in heterogeneous network and with different devices. The whole system is described in M.T. Carta et al., (2006), this paper compares the security level of this image based authentication system with the traditional authentication methods. The image password demonstrates to be more secure than the common alphanumeric password and at the same time more easy-to-use.

This paper presents an innovative framework for user authentication based on images. Common user authentication based on passwords has the main drawback of the human difficulty in recalling them. Images are instead easier to remember than passwords. Moreover, modern compression and transmission techniques make image exchange between different devices (e.g. mobile phones, personal digital assistants, laptops, and workstations) in heterogeneous networks practically feasible. In the proposed approach, images are coded using the emerging JPEG2000 standard and taking advantage of many of its features (e.g. image scalability, embedded bitstream, image tiling, and interactivity protocol). The described image based authentication is more secure than the common approach based on passwords.

This paper presents a novel no-reference image blockiness index which exploits the properties of the Sobel operator. The blockiness index is a combination of two measures. The first quantifies the luminance variation of block boundaries pixels. The second quantifies the luminance variation of remaining pixels. Experimental results illustrating the performance of the proposed method show improvements over similar recently published methods.

This paper presents a new technique for video segmentation and tracking. As most of segmentation techniques it consists on an initial model generation process with a subsequent object tracking phase. The model generation is accomplished by means of a combination of temporal and spatial transitions detection approaches. The novelty of the method is that these approaches are performed block-by-block. This has the advantages to reduce problems relevant to the object connectivity and to drastically decrease the algorithm computational complexity respect to a pixel-by-pixel processing procedure. According to the proposed strategy, edged blocks are firstly extracted in an active region selected by the user. From these, the subset of blocks that represents the object contour is selected by minimizing a cost function that exploits a multiple edged block feature vector: motion, smoothness, continuity, strongness and position. The tracking task is then performed by estimating the model blocks motion. Experiments are presented that show comparable results accuracy respect to existing segmentation techniques while requiring a reduced computational complexity.

The transmission of block-coded visual information over packet networks introduces fidelity problems in terms of data losses, which result in wrong reconstruction of block sequences at the decoder. Concealment techniques aim at masking the visual effect of these errors, by exploiting either spatial or temporal available information. Both temporal and spatial approaches present drawbacks: the first is in general inefficient in handling complex or fast objects' motion, while the second is computationally expensive and is not able to recover high-frequency contents and small details. In this paper, a new solution is proposed that combines temporal and spatial approaches. The technique first replaces the lost block with the best matching pattern in a previously decoded frame (BMA), using the border information, and then applies a mesh-based warping (MBW) that reduces the artifacts caused by fast movements, rotations or deformations. The first step is achieved by a fast matching algorithm, for a high precision is not needed, while the second step uses an affine transform applied to a deformable mesh structure. Experimental results show that significant improvements can be achieved in comparison with traditional spatial or temporal concealment approaches, in terms of both subjective and objective reconstruction quality.

In this paper, the problem of DCT information recovery in the transmission of coded visual data over packet networks is addressed. The loss of a packet conveying coded block data leads to the unsuccessful reconstruction of the relevant area, with consequent degradation of the received image quality. The proposed method allows recovery of a subset of the missing DCT coefficients sufficient to achieve good reconstruction quality of the lost block, based on the available surrounding information. To this purpose, a neural predictor was carefully designed and suitably trained with an appropriate set of synthetic and natural patterns. An extensive testing phase, performed on a large set of images with different frequency characteristics, revealed that the method provides very good reconstruction capabilities.

In this paper, a mechanism for the recovery of lost data in the transmission of JPEG coded images over packet networks is presented. The loss of a packet conveying coded block data brings to the unsuccessful reconstruction of the relevant picture area. The proposed method allows to recover a subset of DCT coefficients by exploiting the structure of the correctly received neighboring blocks, in the very critical case when the loss concerns all the block coefficients. For this purpose a neural predictor was specifically designed and suitably trained with a set of carefully studied synthetic patterns. It directly works in the transformed domain, allowing a real time reconstruction of damaged blocks. The results achieved show that the method has very good reconstruction capability both on synthetic and natural test data.