Abstract: As 3D video is explored as a hot research topic in the last few decades, free-viewpoint TV (FTV) is no doubt a promising field for its better visual experience and incomparable interactivity. View synthesis is obviously a crucial technology for FTV; it enables to render images in unlimited numbers of virtual viewpoints with the information from limited numbers of reference view. In this paper, a novel hybrid synthesis framework is proposed and blending priority is explored. In contrast to the commonly used View Synthesis Reference Software (VSRS), the presented synthesis process is driven in consideration of the temporal correlation of image sequences. The temporal correlations will be exploited to produce fine synthesis results even near the foreground boundaries. As for the blending priority, this scheme proposed that one of the two reference views is selected to be the main reference view based on the distance between the reference views and virtual view, another view is chosen as the auxiliary viewpoint, just assist to fill the hole pixel with the help of background information. Significant improvement of the proposed approach over the state-of –the-art pixel-based virtual view synthesis method is presented, the results of the experiments show that subjective gains can be observed, and objective PSNR average gains range from 0.5 to 1.3 dB, while SSIM average gains range from 0.01 to 0.05.
Abstract: The stereo matching problem, while having been present for several decades, continues to be an active area of research. The goal of this research is to find correspondences between elements found in a set of stereoscopic images. With these pairings, it is possible to infer the distance of objects within a scene, relative to the observer. Advancements in this field have led to experimentations with various techniques, from graph-cut energy minimization to artificial neural networks. At the basis of these techniques is a cost function, which is used to evaluate the likelihood of a particular match between points in each image. While at its core, the cost is based on comparing the image pixel data; there is a general lack of consistency as to what image data representation to use. This paper presents an experimental analysis to compare the effectiveness of more common image data representations. The goal is to determine the effectiveness of these data representations to reduce the cost for the correct correspondence relative to other possible matches.
Abstract: Fishery lights on the surface could be detected by the Day and Night Band (DNB) of the Visible Infrared Imaging Radiometer Suite (VIIRS) on the Suomi National Polar-orbiting Partnership (Suomi-NPP). The DNB covers the spectral range of 500 to 900 nm and realized a higher sensitivity. The DNB has a difficulty of identification of fishing lights from lunar lights reflected by clouds, which affects observations for the half of the month. Fishery lights and lights of the surface are identified from lunar lights reflected by clouds by a method using the DNB and the infrared band, where the detection limits are defined as a function of the brightness temperature with a difference from the maximum temperature for each level of DNB radiance and with the contrast of DNB radiance against the background radiance. Fishery boats or structures on islands could be detected by the Synthetic Aperture Radar (SAR) on the polar orbit satellites using the reflected microwave by the surface reflecting targets. The SAR has a difficulty of tradeoff between spatial resolution and coverage while detecting the small targets like fishery boats. A distribution of fishery boats and island activities were detected by the scan-SAR narrow mode of Radarsat-2, which covers 300 km by 300 km with various combinations of polarizations. The fishing boats were detected as a single pixel of highly scattering targets with the scan-SAR narrow mode of which spatial resolution is 30 m. As the look angle dependent scattering signals exhibits the significant differences, the standard deviations of scattered signals for each look angles were taken into account as a threshold to identify the signal from fishing boats and structures on the island from background noise. It was difficult to validate the detected targets by DNB with SAR data because of time lag of observations for 6 hours between midnight by DNB and morning or evening by SAR. The temporal changes of island activities were detected as a change of mean intensity of DNB for circular area for a certain scale of activities. The increase of DNB mean intensity was corresponding to the beginning of dredging and the change of intensity indicated the ending of reclamation and following constructions of facilities.
Abstract: With the development of HyperSpectral Imagery
(HSI) technology, the spectral resolution of HSI became denser,
which resulted in large number of spectral bands, high correlation
between neighboring, and high data redundancy. However, the
semantic interpretation is a challenging task for HSI analysis
due to the high dimensionality and the high correlation of the
different spectral bands. In fact, this work presents a dimensionality
reduction approach that allows to overcome the different issues
improving the semantic interpretation of HSI. Therefore, in order
to preserve the spatial information, the Tensor Locality Preserving
Projection (TLPP) has been applied to transform the original HSI.
In the second step, knowledge has been extracted based on the
adjacency graph to describe the different pixels. Based on the
transformation matrix using TLPP, a weighted matrix has been
constructed to rank the different spectral bands based on their
contribution score. Thus, the relevant bands have been adaptively
selected based on the weighted matrix. The performance of the
presented approach has been validated by implementing several
experiments, and the obtained results demonstrate the efficiency
of this approach compared to various existing dimensionality
reduction techniques. Also, according to the experimental results,
we can conclude that this approach can adaptively select the
relevant spectral improving the semantic interpretation of HSI.
Abstract: In this paper, a scalable augmented reality framework for handheld devices is presented. The presented framework is enabled by using a server-client data communication structure, in which the search for tracking targets among a database of images is performed on the server-side while pixel-wise 3D tracking is performed on the client-side, which, in this case, is a handheld mobile device. Image search on the server-side adopts a residual-enhanced image descriptors representation that gives the framework a scalability property. The tracking algorithm on the client-side is based on a gravity-aligned feature descriptor which takes the advantage of a sensor-equipped mobile device and an optimized intensity-based image alignment approach that ensures the accuracy of 3D tracking. Automatic content streaming is achieved by using a key-frame selection algorithm, client working phase monitoring and standardized rules for content communication between the server and client. The recognition accuracy test performed on a standard dataset shows that the method adopted in the presented framework outperforms the Bag-of-Words (BoW) method that has been used in some of the previous systems. Experimental test conducted on a set of video sequences indicated the real-time performance of the tracking system with a frame rate at 15-30 frames per second. The presented framework is exposed to be functional in practical situations with a demonstration application on a campus walk-around.
Abstract: This paper presents the results of a study to test whether the Javanese character manuscript image preprocessing model that have been more widely applied, can also be applied to segment of the Batak characters manuscripts. The treatment process begins by converting the input image into a binary image. After the binary image is cleaned of noise, then the segmentation lines using projection profile is conducted. If unclear histogram projection is found, then the smoothing process before production indexes line segments is conducted. For each line image which has been produced, then the segmentation scripts in the line is applied, with regard of the connectivity between pixels which making up the letters that there is no characters are truncated. From the results of manuscript preprocessing system prototype testing, it is obtained the information about the system truth percentage value on pieces of Pustaka Batak Podani Ma AjiMamisinon manuscript ranged from 65% to 87.68% with a confidence level of 95%. The value indicates the truth percentage shown the initial processing model in Javanese characters manuscript image can be applied also to the image of the Batak characters manuscript.
Abstract: Foliage diseases in plants can cause a reduction in both quality and quantity of agricultural production. Intelligent detection of plant diseases is an essential research topic as it may help monitoring large fields of crops by automatically detecting the symptoms of foliage diseases. This work investigates ways to recognize the late blight disease from the analysis of tomato digital images, collected directly from the field. A pair of multilayer perceptron neural network analyzes the digital images, using data from both RGB and HSL color models, and classifies each image pixel. One neural network is responsible for the identification of healthy regions of the tomato leaf, while the other identifies the injured regions. The outputs of both networks are combined to generate the final classification of each pixel from the image and the pixel classes are used to repaint the original tomato images by using a color representation that highlights the injuries on the plant. The new images will have only green, red or black pixels, if they came from healthy or injured portions of the leaf, or from the background of the image, respectively. The system presented an accuracy of 97% in detection and estimation of the level of damage on the tomato leaves caused by late blight.
Abstract: Image steganography is the best aspect of information hiding. In this, the information is hidden within an image and the image travels openly on the Internet. The Least Significant Bit (LSB) is one of the most popular methods of image steganography. In this method, the information bit is hidden at the LSB of the image pixel. In one bit LSB steganography method, the total numbers of the pixels and the total number of message bits are equal to each other. In this paper, the LSB method of image steganography is used for watermarking. The watermarking is an application of the steganography. The watermark contains 80*88 pixels and each pixel requirs 8 bits for its binary equivalent form so, the total number of bits required to hide the watermark are 80*88*8(56320). The experiment was performed on standard 256*256 and 512*512 size images. After the watermark insertion, histogram analysis was performed. A noise factor (salt and pepper) of 0.02 was added to the stego image in order to evaluate the robustness of the method. The watermark was successfully retrieved after insertion of noise. An experiment was performed in order to know the imperceptibility of stego and the retrieved watermark. It is clear that the LSB watermarking scheme is robust to the salt and pepper noise.
Abstract: In this paper, an approach is presented to investigate the performance of Pixel Factor Mapping (PFM) and Extended PMM (Pixel Mapping Method) through the qualitative and quantitative approach. These methods are tested against a number of well-known image similarity metrics and statistical distribution techniques. The PFM has been performed in spatial domain as well as frequency domain and the Extended PMM has also been performed in spatial domain through large set of images available in the internet.
Abstract: Hyperspectral imagery (HSI) typically provides a
wealth of information captured in a wide range of the
electromagnetic spectrum for each pixel in the image. Hence, a
pixel in HSI is a high-dimensional vector of intensities with a
large spectral range and a high spectral resolution. Therefore, the
semantic interpretation is a challenging task of HSI analysis. We
focused in this paper on object classification as HSI semantic
interpretation. However, HSI classification still faces some issues,
among which are the following: The spatial variability of spectral
signatures, the high number of spectral bands, and the high cost
of true sample labeling. Therefore, the high number of spectral
bands and the low number of training samples pose the problem of
the curse of dimensionality. In order to resolve this problem, we
propose to introduce the process of dimensionality reduction trying
to improve the classification of HSI. The presented approach is a
semi-supervised band selection method based on spatial hypergraph
embedding model to represent higher order relationships with
different weights of the spatial neighbors corresponding to the
centroid of pixel. This semi-supervised band selection has been
developed to select useful bands for object classification. The
presented approach is evaluated on AVIRIS and ROSIS HSIs
and compared to other dimensionality reduction methods. The
experimental results demonstrate the efficacy of our approach
compared to many existing dimensionality reduction methods for
HSI classification.
Abstract: This paper presents advanced time average digital holography by means of frequency shift and phase modulation. This technique can measure amplitudes of vibrations at ultimate dynamic range while the amplitude distribution evaluation is done independently in every pixel. The main focus of the paper is to gain insight into behavior of the method at low amplitudes of vibrations. In order to reach that, a set of experiments was performed. Results of the experiments together with novel noise suppression show the limit of the method to be below 0.1 nm.
Abstract: In this study, it was aimed to determine a route for identification of rice cultivation areas within Thrace and Marmara regions of Turkey using remote sensing and GIS. Landsat 8 (OLI-TIRS) imageries acquired in production season of 2013 with 181/32 Path/Row number were used. Four different seasonal images were generated utilizing original bands and different transformation techniques. All images were classified individually using supervised classification techniques and Land Use Land Cover Maps (LULC) were generated with 8 classes. Areas (ha, %) of each classes were calculated. In addition, district-based rice distribution maps were developed and results of these maps were compared with Turkish Statistical Institute (TurkSTAT; TSI)’s actual rice cultivation area records. Accuracy assessments were conducted, and most accurate map was selected depending on accuracy assessment and coherency with TSI results. Additionally, rice areas on over 4° slope values were considered as mis-classified pixels and they eliminated using slope map and GIS tools. Finally, randomized rice zones were selected to obtain maximum-minimum value ranges of each date (May, June, July, August, September images separately) NDVI, LSWI, and LST images to test whether they may be used for rice area determination via raster calculator tool of ArcGIS. The most accurate classification for rice determination was obtained from seasonal LSWI LULC map, and considering TSI data and accuracy assessment results and mis-classified pixels were eliminated from this map. According to results, 83151.5 ha of rice areas exist within study area. However, this result is higher than TSI records with an area of 12702.3 ha. Use of maximum-minimum range of rice area NDVI, LSWI, and LST was tested in Meric district. It was seen that using the value ranges obtained from July imagery, gave the closest results to TSI records, and the difference was only 206.4 ha. This difference is normal due to relatively low resolution of images. Thus, employment of images with higher spectral, spatial, temporal and radiometric resolutions may provide more reliable results.
Abstract: 3D model-based vehicle matching provides a new way
for vehicle recognition, localization and tracking. Its key is to
construct an evaluation function, also called fitness function, to
measure the degree of vehicle matching. The existing fitness functions
often poorly perform when the clutter and occlusion exist in traffic
scenarios. In this paper, we present a practical and efficient fitness
function. Unlike the existing evaluation functions, the proposed
fitness function is to study the vehicle matching problem from
both local and global perspectives, which exploits the pixel gradient
information as well as the silhouette information. In view of the
discrepancy between 3D vehicle model and real vehicle, a weighting
strategy is introduced to differently treat the fitting of the model’s
wireframes. Additionally, a normalization operation for the model’s
projection is performed to improve the accuracy of the matching.
Experimental results on real traffic videos reveal that the proposed
fitness function is efficient and robust to the cluttered background
and partial occlusion.
Abstract: Recent developments on multi-agent system have brought a new research field on image processing. Several algorithms are used simultaneously and improved in deferent applications while new methods are investigated. This paper presents a new automatic method for edge detection using several agents and many different actions. The proposed multi-agent system is based on parallel agents that locally perceive their environment, that is to say, pixels and additional environmental information. This environment is built using Vector Field Convolution that attract free agent to the edges. Problems of partial, hidden or edges linking are solved with the cooperation between agents. The presented method was implemented and evaluated using several examples on different synthetic and medical images. The obtained experimental results suggest that this approach confirm the efficiency and accuracy of detected edge.
Abstract: Although most digital cameras acquire images in a raw
format, based on a Color Filter Array that arranges RGB color
filters on a square grid of photosensors, most image compression
techniques do not use the raw data; instead, they use the rgb result
of an interpolation algorithm of the raw data. This approach is
inefficient and by performing a lossless compression of the raw data,
followed by pixel interpolation, digital cameras could be more power
efficient and provide images with increased resolution given that the
interpolation step could be shifted to an external processing unit. In
this paper, we conduct a survey on the use of lossless compression
algorithms with raw Bayer images. Moreover, in order to reduce the
effect of the transition between colors that increase the entropy of
the raw Bayer image, we split the image into three new images
corresponding to each channel (red, green and blue) and we study
the same compression algorithms applied to each one individually.
This simple pre-processing stage allows an improvement of more than
15% in predictive based methods.
Abstract: Real Time Video Tracking is a challenging task for computing professionals. The performance of video tracking techniques is greatly affected by background detection and elimination process. Local regions of the image frame contain vital information of background and foreground. However, pixel-level processing of local regions consumes a good amount of computational time and memory space by traditional approaches. In our approach we have explored the concurrent computational ability of General Purpose Graphic Processing Units (GPGPU) to address this problem. The Gaussian Mixture Model (GMM) with adaptive weighted kernels is used for detecting the background. The weights of the kernel are influenced by local regions and are updated by inter-frame variations of these corresponding regions. The proposed system has been tested with GPU devices such as GeForce GTX 280, GeForce GTX 280 and Quadro K2000. The results are encouraging with maximum speed up 10X compared to sequential approach.
Abstract: Medical digital images usually have low resolution because of nature of their acquisition. Therefore, this paper focuses on zooming these images to obtain better level of information, required for the purpose of medical diagnosis. For this purpose, a strategy for selecting pixels in zooming operation is proposed. It is based on the principle of analog clock and utilizes a combination of point and neighborhood image processing. In this approach, the hour hand of clock covers the portion of image to be processed. For alignment, the center of clock points at middle pixel of the selected portion of image. The minute hand is longer in length, and is used to gain information about pixels of the surrounding area. This area is called neighborhood pixels region. This information is used to zoom the selected portion of the image. The proposed algorithm is implemented and its performance is evaluated for many medical images obtained from various sources such as X-ray, Computerized Tomography (CT) scan and Magnetic Resonance Imaging (MRI). However, for illustration and simplicity, the results obtained from a CT scanned image of head is presented. The performance of algorithm is evaluated in comparison to various traditional algorithms in terms of Peak signal-to-noise ratio (PSNR), maximum error, SSIM index, mutual information and processing time. From the results, the proposed algorithm is found to give better performance than traditional algorithms.
Abstract: In this era of online communication, which transacts data in 0s and 1s, confidentiality is a priced commodity. Ensuring safe transmission of encrypted data and their uncorrupted recovery is a matter of prime concern. Among the several techniques for secure sharing of images, this paper proposes a k out of n region incrementing image sharing scheme for color images. The highlight of this scheme is the use of simple Boolean and arithmetic operations for generating shares and the Lagrange interpolation polynomial for authenticating shares. Additionally, this scheme addresses problems faced by existing algorithms such as color reversal and pixel expansion. This paper regenerates the original secret image whereas the existing systems regenerates only the half toned secret image.
Abstract: Wetting efficiency of microstructures or nanostructures patterned on Si wafers is a real challenge in integrated circuits manufacturing. In fact, bad or non-uniform wetting during wet processes limits chemical reactions and can lead to non-complete etching or cleaning inside the patterns and device defectivity. This issue is more and more important with the transistors size shrinkage and concerns mainly high aspect ratio structures. Deep Trench Isolation (DTI) structures enabling pixels’ isolation in imaging devices are subject to this phenomenon. While low-frequency acoustic reflectometry principle is a well-known method for Non Destructive Test applications, we have recently shown that it is also well suited for nanostructures wetting characterization in a higher frequency range. In this paper, we present a high-frequency acoustic reflectometry characterization of DTI wetting through a confrontation of both experimental and modeling results. The acoustic method proposed is based on the evaluation of the reflection of a longitudinal acoustic wave generated by a 100 µm diameter ZnO piezoelectric transducer sputtered on the silicon wafer backside using MEMS technologies. The transducers have been fabricated to work at 5 GHz corresponding to a wavelength of 1.7 µm in silicon. The DTI studied structures, manufactured on the wafer frontside, are crossing trenches of 200 nm wide and 4 µm deep (aspect ratio of 20) etched into a Si wafer frontside. In that case, the acoustic signal reflection occurs at the bottom and at the top of the DTI enabling its characterization by monitoring the electrical reflection coefficient of the transducer. A Finite Difference Time Domain (FDTD) model has been developed to predict the behavior of the emitted wave. The model shows that the separation of the reflected echoes (top and bottom of the DTI) from different acoustic modes is possible at 5 Ghz. A good correspondence between experimental and theoretical signals is observed. The model enables the identification of the different acoustic modes. The evaluation of DTI wetting is then performed by focusing on the first reflected echo obtained through the reflection at Si bottom interface, where wetting efficiency is crucial. The reflection coefficient is measured with different water / ethanol mixtures (tunable surface tension) deposited on the wafer frontside. Two cases are studied: with and without PFTS hydrophobic treatment. In the untreated surface case, acoustic reflection coefficient values with water show that liquid imbibition is partial. In the treated surface case, the acoustic reflection is total with water (no liquid in DTI). The impalement of the liquid occurs for a specific surface tension but it is still partial for pure ethanol. DTI bottom shape and local pattern collapse of the trenches can explain these incomplete wetting phenomena. This high-frequency acoustic method sensitivity coupled with a FDTD propagative model thus enables the local determination of the wetting state of a liquid on real structures. Partial wetting states for non-hydrophobic surfaces or low surface tension liquids are then detectable with this method.
Abstract: Information security plays a major role in uplifting the standard of secured communications via global media. In this paper, we have suggested a technique of encryption followed by insertion before transmission. Here, we have implemented two different concepts to carry out the above-specified tasks. We have used a two-point crossover technique of the genetic algorithm to facilitate the encryption process. For each of the uniquely identified rows of pixels, different mathematical methodologies are applied for several conditions checking, in order to figure out all the parent pixels on which we perform the crossover operation. This is done by selecting two crossover points within the pixels thereby producing the newly encrypted child pixels, and hence the encrypted cover image. In the next lap, the first and second order derivative operators are evaluated to increase the security and robustness. The last lap further ensures reapplication of the crossover procedure to form the final stego-image. The complexity of this system as a whole is huge, thereby dissuading the third party interferences. Also, the embedding capacity is very high. Therefore, a larger amount of secret image information can be hidden. The imperceptible vision of the obtained stego-image clearly proves the proficiency of this approach.