arXiv subjects

Shadrokh Samavi

Publications and source records attributed to Shadrokh Samavi.

At least 91 records · Page 5Linked to original sources

arXiv2018

Lossless Image Compression Algorithm for Wireless Capsule Endoscopy by Content-Based Classification of Image Blocks

Recent advances in capsule endoscopy systems have introduced new methods and capabilities. The capsule endoscopy system, by observing the entire digestive tract, has significantly improved diagnosing gastrointestinal disorders and diseases. The system has challenges such as the need to enhance the quality of the transmitted images, low frame rates of transmission, and battery lifetime that need to be addressed. One of the important parts of a capsule endoscopy system is the image compression unit. Better compression of images increases the frame rate and hence improves the diagnosis process. In this paper a high precision compression algorithm with high compression ratio is proposed. In this algorithm we use the similarity between frames to compress the data more efficiently.

cs.CV↗

arXiv2018

Reversible Image Watermarking for Health Informatics Systems Using Distortion Compensation in Wavelet Domain

Reversible image watermarking guaranties restoration of both original cover and watermark logo from the watermarked image. Capacity and distortion of the image under reversible watermarking are two important parameters. In this study a reversible watermarking is investigated with focusing on increasing the embedding capacity and reducing the distortion in medical images. Integer wavelet transform is used for embedding where in each iteration, one watermark bit is embedded in one transform coefficient. We devise a novel approach that when a coefficient is modified in an iteration, the produced distortion is compensated in the next iteration. This distortion compensation method would result in low distortion rate. The proposed method is tested on four types of medical images including MRI of brain, cardiac MRI, MRI of breast, and intestinal polyp images. Using a one-level wavelet transform, maximum capacity of 1.5 BPP is obtained. Experimental results demonstrate that the proposed method is superior to the state-of-the-art works in terms of capacity and distortion.

cs.CV↗

arXiv2018

Segmentation of Bleeding Regions in Wireless Capsule Endoscopy Images an Approach for inside Capsule Video Summarization

Wireless capsule endoscopy (WCE) is an effective means of diagnosis of gastrointestinal disorders. Detection of informative scenes by WCE could reduce the length of transmitted videos and can help with the diagnosis. In this paper we propose a simple and efficient method for segmentation of the bleeding regions in WCE captured images. Suitable color channels are selected and classified by a multi-layer perceptron (MLP) structure. The MLP structure is quantized such that the implementation does not require multiplications. The proposed method is tested by simulation on WCE bleeding image dataset. The proposed structure is designed considering hardware resource constrains that exist in WCE systems.

cs.CV↗

arXiv2018

Classification of Informative Frames in Colonoscopy Videos Using Convolutional Neural Networks with Binarized Weights

Colorectal cancer is one of the common cancers in the United States. Polyp is one of the main causes of the colonic cancer and early detection of polyps will increase chance of cancer treatments. In this paper, we propose a novel classification of informative frames based on a convolutional neural network with binarized weights. The proposed CNN is trained with colonoscopy frames along with the labels of the frames as input data. We also used binarized weights and kernels to reduce the size of CNN and make it suitable for implementation in medical hardware. We evaluate our proposed method using Asu Mayo Test clinic database, which contains colonoscopy videos of different patients. Our proposed method reaches a dice score of 71.20% and accuracy of more than 90% using the mentioned dataset.

eess.IV↗

arXiv2018

Polyp Segmentation in Colonoscopy Images Using Fully Convolutional Network

Colorectal cancer is a one of the highest causes of cancer-related death, especially in men. Polyps are one of the main causes of colorectal cancer and early diagnosis of polyps by colonoscopy could result in successful treatment. Diagnosis of polyps in colonoscopy videos is a challenging task due to variations in the size and shape of polyps. In this paper we proposed a polyp segmentation method based on convolutional neural network. Performance of the method is enhanced by two strategies. First, we perform a novel image patch selection method in the training phase of the network. Second, in the test phase, we perform an effective post processing on the probability map that is produced by the network. Evaluation of the proposed method using the CVC-ColonDB database shows that our proposed method achieves more accurate results in comparison with previous colonoscopy video-segmentation methods.

eess.IV↗

arXiv2018

Context aware saliency map generation using semantic segmentation

Saliency map detection, as a method for detecting important regions of an image, is used in many applications such as image classification and recognition. We propose that context detection could have an essential role in image saliency detection. This requires extraction of high level features. In this paper a saliency map is proposed, based on image context detection using semantic segmentation as a high level feature. Saliency map from semantic information is fused with color and contrast based saliency maps. The final saliency map is then generated. Simulation results for Pascal-voc11 image dataset show 99% accuracy in context detection. Also final saliency map produced by our proposed method shows acceptable results in detecting salient points.

cs.CV↗

arXiv2018

RIBBONS: Rapid Inpainting Based on Browsing of Neighborhood Statistics

Image inpainting refers to filling missing places in images using neighboring pixels. It also has many applications in different tasks of image processing. Most of these applications enhance the image quality by significant unwanted changes or even elimination of some existing pixels. These changes require considerable computational complexities which in turn results in remarkable processing time. In this paper we propose a fast inpainting algorithm called RIBBONS based on selection of patches around each missing pixel. This would accelerate the execution speed and the capability of online frame inpainting in video. The applied cost-function is a combination of statistical and spatial features in all neighboring pixels. We evaluate some candidate patches using the proposed cost function and minimize it to achieve the final patch. Experimental results show the higher speed of 'Ribbons' in comparison with previous methods while being comparable in terms of PSNR and SSIM for the images in MISC dataset.

eess.IV↗

arXiv2017

Image Inpainting by Hyperbolic Selection of Pixels for Two Dimensional Bicubic Interpolations

Image inpainting is a restoration process which has numerous applications. Restoring of scanned old images with scratches, or removing objects in images are some of inpainting applications. Different approaches have been used for implementation of inpainting algorithms. Interpolation approaches only consider one direction for this purpose. In this paper we present a new perspective to image inpainting. We consider multiple directions and apply both one-dimensional and two-dimensional bicubic interpolations. Neighboring pixels are selected in a hyperbolic formation to better preserve corner pixels. We compare our work with recent inpainting approaches to show our superior results.

eess.IV↗

arXiv2017

Polyp detection inside the capsule endoscopy: an approach for power consumption reduction

Capsule endoscopy is a novel and non-invasive method for diagnosis, which assists gastroenterologists to monitor the digestive track. Although this new technology has many advantages over the conventional endoscopy, there are weaknesses that limits the usage of this technology. Some weaknesses are due to using small-size batteries. Radio transmitter consumes the largest portion of energy; consequently, a simple way to reduce the power consumption is to reduce the data to be transmitted. Many works are proposed to reduce the amount of data to be transmitted consist of specific compression methods and reduction in video resolution and frame rate. We proposed a system inside the capsule for detecting informative frames and sending these frames instead of several non-informative frames. In this work, we specifically focused on hardware friendly algorithm (with capability of parallelism and pipeline) for implementation of polyp detection. Two features of positive contrast and customized edges of polyps are exploited to define whether the frame consists of polyp or not. The proposed method is devoid of complex and iterative structure to save power and reduce the response time. Experimental results indicate acceptable rate of detection of our work.

eess.IV↗

arXiv2017

Real time ridge orientation estimation for fingerprint images

Fingerprint verification is an important bio-metric technique for personal identification. Most of the automatic verification systems are based on matching of fingerprint minutiae. Extraction of minutiae is an essential process which requires estimation of orientation of the lines in an image. Most of the existing methods involve intense mathematical computations and hence are performed through software means. In this paper a hardware scheme to perform real time orientation estimation is presented which is based on pipelined architecture. Synthesized circuits proved the functionality and accuracy of the suggested method.

cs.CV↗

arXiv2017

Adaptive Real-Time Removal of Impulse Noise in Medical Images

Noise is an important factor that degrades the quality of medical images. Impulse noise is a common noise, which is caused by malfunctioning of sensor elements or errors in the transmission of images. In medical images due to presence of white foreground and black background, many pixels have intensities similar to impulse noise and distinction between noisy and regular pixels is difficult. In software techniques, the accuracy of the noise removal is more important than the algorithm's complexity. But for hardware implementation having a low complexity algorithm with an acceptable accuracy is essential. In this paper a low complexity de-noising method is proposed that removes the noise by local analysis of the image blocks. The proposed method distinguishes non-noisy pixels that have noise-like intensities. All steps are designed to have low hardware complexity. Simulation results show that for different magnetic resonance images, the proposed method removes impulse noise with an acceptable accuracy.

cs.CV↗

arXiv2017

Power Aware Visual Sensor Network for Wildlife Habitat Monitoring

One of the fundamental issue in wireless sensor network is conserving energy and thus extending the lifetime of the network. In this paper we investigate the coverage problem in camera sensor networks by developing two algorithms which consider network lifetime. Also, it is assumed that camera sensors spread randomly over a large area in order to monitor a designated air space. To increase the lifetime of the network, the density of distributed sensors could be such that a subset of sensors can cover the required air space. As a sensor dies another sensor should be selected to compensate for the dead one and reestablish the complete coverage. This process should be continued until complete coverage is not achievable by the existing sensors. Thereafter, a graceful degradation of the coverage is desirable. The goal is to elongate the lifetime of the network while maintaining a maximum possible coverage of the designated air space. Since the selection of a subset of sensors for complete coverage of the target area is an NP-complete problem we present a class of heuristics for this case. This is done by prioritizing the sensors based on their visual and communicative properties.

eess.SY↗

arXiv2017

Reduction of Look Up Tables for Computation of Reciprocal of Square Roots

Among many existing algorithms, convergence methods are the most popular means of computing square root and the reciprocal of square root of numbers. An initial approximation is required in these methods. Look up tables (LUT) are employed to produce the initial approximation. In this paper a number of methods are suggested to reduce the size of the look up tables. The precision of the initial approximation plays an important role in the quality of the final result. There are constraints for the use of a LUT in terms of its size and its access time. Therefore, the optimization of the LUTs must be done in a way to minimize hardware while offering acceptable convergence speed and exactitude.

math.NA↗

arXiv2017

Hardware design for binarization and thinning of fingerprint images

Two critical steps in fingerprint recognition are binarization and thinning of the image. The need for real time processing motivates us to select local adaptive thresholding approach for the binarization step. We introduce a new hardware for this purpose based on pipeline architecture. We propose a formula for selecting an optimal block size for the thresholding purpose. To decrease minutiae false detection, the binarized image is dilated. We also present in this paper a new pipeline structure for implementing the thinning algorithm

cs.CV↗

arXiv2017

Hierarchical Watermarking Framework Based on Analysis of Local Complexity Variations

Increasing production and exchange of multimedia content has increased the need for better protection of copyright by means of watermarking. Different methods have been proposed to satisfy the tradeoff between imperceptibility and robustness as two important characteristics in watermarking while maintaining proper data-embedding capacity. Many watermarking methods use image independent set of parameters. Different images possess different potentials for robust and transparent hosting of watermark data. To overcome this deficiency, in this paper we have proposed a new hierarchical adaptive watermarking framework. At the higher level of hierarchy, complexity of an image is ranked in comparison with complexities of images of a dataset. For a typical dataset of images, the statistical distribution of block complexities is found. At the lower level of the hierarchy, for a single cover image that is to be watermarked, complexities of blocks can be found. Local complexity variation (LCV) among a block and its neighbors is used to adaptively control the watermark strength factor of each block. Such local complexity analysis creates an adaptive embedding scheme, which results in higher transparency by reducing blockiness effects. This two level hierarchy has enabled our method to take advantage of all image blocks to elevate the embedding capacity while preserving imperceptibility. For testing the effectiveness of the proposed framework, contourlet transform (CT) in conjunction with discrete cosine transform (DCT) is used to embed pseudo-random binary sequences as watermark. Experimental results show that the proposed framework elevates the performance the watermarking routine in terms of both robustness and transparency.

cs.MM↗

arXiv2017

Vessel Segmentation and Catheter Detection in X-Ray Angiograms Using Superpixels

Coronary artery disease (CAD) is the leading causes of death around the world. One of the most common imaging methods for diagnosing this disease is X-ray angiography. Diagnosing using these images is usually challenging due to non-uniform illumination, low contrast, presence of other body tissues, presence of catheter etc. These challenges make the diagnoses task of cardiologists tougher and more prone to misdiagnosis. In this paper we propose a new automated framework for coronary arteries segmentation, catheter detection and center-line extraction in x-ray angiography images. Our proposed segmentation method is based on superpixels. In this method at first three different superpixel scales are exploited and a measure for vesselness probability of each superpixel is determined. A majority voting is used for obtaining an initial segmentation map from these three superpixel scales. This initial segmentation is refined by finding the orthogonal line on each ridge pixel of vessel region. In this framework we use our catheter detection and tracking method which detects the catheter by finding its ridge in the first frame and traces in other frames by fitting a second order polynomial on it. Also we use the image ridges for extracting the coronary arteries centerlines. We evaluated our method qualitatively and quantitatively on two different challenging datasets and compared it with one of the previous well-known coronary arteries segmentation methods. Our method could detect the catheter and reduced the false positive rate in addition to achieving better segmentation results. The evaluation results prove that our method performs better in a much shorter time.

cs.CV↗

arXiv2017

Blind Stereo Image Quality Assessment Inspired by Brain Sensory-Motor Fusion

The use of 3D and stereo imaging is rapidly increasing. Compression, transmission, and processing could degrade the quality of stereo images. Quality assessment of such images is different than their 2D counterparts. Metrics that represent 3D perception by human visual system (HVS) are expected to assess stereoscopic quality more accurately. In this paper, inspired by brain sensory/motor fusion process, two stereo images are fused together. Then from every fused image two synthesized images are extracted. Effects of different distortions on statistical distributions of the synthesized images are shown. Based on the observed statistical changes, features are extracted from these synthesized images. These features can reveal type and severity of distortions. Then, a stacked neural network model is proposed, which learns the extracted features and accurately evaluates the quality of stereo images. This model is tested on 3D images of popular databases. Experimental results show the superiority of this method over state of the art stereo image quality assessment approaches

cs.CV↗

arXiv2017

Real-Time Impulse Noise Removal from MR Images for Radiosurgery Applications

In the recent years image processing techniques are used as a tool to improve detection and diagnostic capabilities in the medical applications. Medical applications have been so much affected by these techniques which some of them are embedded in medical instruments such as MRI, CT and other medical devices. Among these techniques, medical image enhancement algorithms play an essential role in removal of the noise which can be produced by medical instruments and during image transfer. It has been proved that impulse noise is a major type of noise, which is produced during medical operations, such as MRI, CT, and angiography, by their image capturing devices. An embeddable hardware module which is able to denoise medical images before and during surgical operations could be very helpful. In this paper an accurate algorithm is proposed for real-time removal of impulse noise in medical images. All image blocks are divided into three categories of edge, smooth, and disordered areas. A different reconstruction method is applied to each category of blocks for the purpose of noise removal. The proposed method is tested on MR images. Simulation results show acceptable denoising accuracy for various levels of noise. Also an FPAG implementation of our denoising algorithm shows acceptable hardware resource utilization. Hence, the algorithm is suitable for embedding in medical hardware instruments such as radiosurgery devices.

cs.AR↗