Search Results

You are looking at 1 - 10 of 39 items for :

  • pixel intensity x
Clear All
Open access

D. Selvathi, N. Emimal and Henry Selvaraj

Abstract

The medical imaging field has grown significantly in recent years and demands high accuracy since it deals with human life. The idea is to reduce human error as much as possible by assisting physicians and radiologists with some automatic techniques. The use of artificial intelligent techniques has shown great potential in this field. Hence, in this paper the neuro fuzzy classifier is applied for the automated characterization of atheromatous plaque to identify the fibrotic, lipidic and calcified tissues in Intravascular Ultrasound images (IVUS) which is designed using sixteen inputs, corresponds to sixteen pixels of instantaneous scanning matrix, one output that tells whether the pixel under consideration is Fibrotic, Lipidic, Calcified or Normal pixel. The classification performance was evaluated in terms of sensitivity, specificity and accuracy and the results confirmed that the proposed system has potential in detecting the respective plaque with the average accuracy of 98.9%.

Open access

Montfort Bagalwa and Katcho Karume

Abstract

In this paper we analyzed the 2011-2012 eruption of Nyamulagira volcano using MODIS Data. Eruptions have been occurring every 3–4 years throughout the last century. Satellite infrared data, collected by MODIS sensor to estimate pixels thermal anomaly of hot spots were analized, the radiance emitted at 3,959 and 12.02μm for each pixel and the thermal emissions at Nyamulagira feall into three distinct radiating regimes released during the 2011–2012 eruption. Initial activity was detected on 6 November, at 19:55 UTC, with a large thermal anomaly with 28 pixels approximately on the north flank of the volcano. The anomaly was limited to the north flank. The anomaly reached a maximum size of 1188 pixels in January 2012. The size and intensity of the anomaly rapidly diminished to first April 2012 were no more than 2 piixels indicate the end of eruption.

Open access

Wojciech Drzewiecki

of Correlations. PLoS ONE 10(4): e0121945. DOI: 10.1371/journal.pone.0121945 Drzewiecki, W. (2016). Comparison of Selected Machine Learning Algorithms for Sub-Pixel Imperviousness Change Assessment. In: 2016 Baltic Geodetic Congress (Geomatics), 67-72. DOI: 10.1109/BGC.Geomatics.2016.21 Drzewiecki, W. (2016). Improving sub-pixel imperviousness change prediction by ensembling heterogeneous non-linear regression models. Geodesy and Cartography, 65, 2, 193-218. DOI: 10.1515/geocart-2016-0016 Dunn, O. J. (1961). Multiple

Open access

Dongliang Su, Jian Wu, Zhiming Cui, Victor S. Sheng and Shengrong Gong

This paper proposes a novel invariant local descriptor, a combination of gradient histograms with contrast intensity (CGCI), for image matching and object recognition. Considering the different contributions of sub-regions inside a local interest region to an interest point, we divide the local interest region around the interest point into two main sub-regions: an inner region and a peripheral region. Then we describe the divided regions with gradient histogram information for the inner region and contrast intensity information for the peripheral region respectively. The contrast intensity information is defined as intensity difference between an interest point and other pixels in the local region. Our experimental results demonstrate that the proposed descriptor performs better than SIFT and its variants PCA-SIFT and SURF with various optical and geometric transformations. It also has better matching efficiency than SIFT and its variants PCA-SIFT and SURF, and has the potential to be used in a variety of realtime applications.

Open access

Iman Avazpour, Ros Roslan, Peyman Bayat, M. Saripan, Abdul Nordin and Raja Abdullah

Segmenting CT images of bronchogenic carcinoma with bone metastases using PET intensity markers approach

Background. The evolution of medical imaging plays a vital role in the management of patients with cancer. In oncology, the impact of PET/CT imaging has been contributing widely to the patient treatment by its large advantages over anatomical imaging from screening to staging. PET images provide the functional activity inside the body while CT images demonstrate the anatomical information. Hence, the existence of cancer cells can be recognized in PET image but since the structural location and position cannot be defined on PET images, we need to retrieve the information from CT images.

Methods. In this study, we highlight the localization of bronchogenic carcinoma by using high activity points on PET image as references to extract regions of interest on CT image. Once PET and CT images have been registered using cross correlation, coordinates of the candidate points from PET are fed into seeded region growing algorithm to define the boundary of lesion on CT. The region growing process continues until a significant change in bilinear pixel values is reached.

Results. The method has been tested over eleven images of a patient having bronchogenic carcinoma with bone metastases. The results show that the mean standard error for over segmented pixels is 33% while for the under segmented pixels is 3.4%.

Conclusions. Although very simple in implementation, region growing can result in good precision ROIs. The region growing method highly depends on where the growing process starts. Here, by using the data acquired from other modality, we tried to guide the segmentation process to achieve better segmentation results.

Open access

Jakub Oravec, Ján Turán and Ľuboš Ovseník

Abstract

This paper proposes an image encryption algorithm which uses four scans of an image during the diffusion stage in order to achieve total diffusion between intensities of image pixels. The condition of total diffusion is fulfilled by a suitable combination of techniques of ciphertext chaining and plaintext related diffusion. The proposed encryption algorithm uses two stages which utilize chaotic logistic map for generation of pseudo-random sequences. The paper also briefly analyzes approaches described by other researchers and evaluates experimental results of the proposed solution by means of commonly used measures. Properties of our proposal regarding modifications of plain images prior to encryption or modifications of encrypted images prior to decryption are illustrated by two additional experiments. The obtained numeric results are compared with those achieved by other proposals and briefly discussed.

Open access

Jakub Oravec, Ján Turán, L’uboš Ovseník and Tomáš Huszaník

Abstract

This paper describes an image encryption algorithm which utilizes chaotic logistic map. Values generated by this map are used in two steps of algorithm which shuffles image pixels and then changes their intensities. Design of the encryption scheme considers possibility of various attacks, such as statistical, differential or phase space reconstruction attacks. Robustness against last mentioned type of attacks is introduced by selective skipping of values generated by the map. This skipping depends on key entered by user. The paper also verifies properties of proposed algorithm by common measures and by set of statistical tests that examine randomness of computed encrypted images. Results are compared with other approaches and they are also briefly discussed.

Open access

Juan Huang, Dana Křemenáková, Jiří Militký, Guocheng Zhu and Guocheng Zhu

(In partial fulfillment of course requirement for MatE 115). San Jose State University, California. [15]Huang, J., Křemenáková, D., Jacub, W., Zhu, G. C., Wang, Y. (2014). Enhancement of Side Emission of Plastic Optical Fibers with TiO2 Particles and CO2 Laser Treatment. Journal of the Textile Institute. Under review. [16]Křemenáková, D., Militký, J. (2013). Evaluation of Side Emitting Optical Fiber Illumination Intensity. 8th International Conference - TEXSCI 2013.

Open access

Z. Faizal Khan and A. Kannan

Abstract

The performance of assessment in medical image segmentation is highly correlated with the extraction of anatomic structures from them, and the major task is how to separate the regions of interests from the background and soft tissues successfully. This paper proposes a fuzzy logic based bitplane method to automatically segment the background of images and to locate the region of interest of medical images. This segmentation algorithm consists of three steps, namely identification, rule firing, and inference. In the first step, we begin by identifying the bitplanes that represent the lungs clearly. For this purpose, the intensity value of a pixel is separated into bitplanes. In the second step, the triple signum function assigns an optimum threshold based on the grayscale values for the anatomical structure present in the medical images. Fuzzy rules are formed based on the available bitplanes to form the membership table and are stored in a knowledge base. Finally, rules are fired to assign final segmentation values through the inference process. The proposed new metrics are used to measure the accuracy of the segmentation method. From the analysis, it is observed that the proposed metrics are more suitable for the estimation of segmentation accuracy. The results obtained from this work show that the proposed method performs segmentation effectively for the different classes of medical images.

Open access

Mehryar Emambakhsh, Hossein Ebrahimnezhad and Mohammad Sedaaghi

Integrated region-based segmentation using color components and texture features with prior shape knowledge

Segmentation is the art of partitioning an image into different regions where each one has some degree of uniformity in its feature space. A number of methods have been proposed and blind segmentation is one of them. It uses intrinsic image features, such as pixel intensity, color components and texture. However, some virtues, like poor contrast, noise and occlusion, can weaken the procedure. To overcome them, prior knowledge of the object of interest has to be incorporated in a top-down procedure for segmentation. Consequently, in this work, a novel integrated algorithm is proposed combining bottom-up (blind) and top-down (including shape prior) techniques. First, a color space transformation is performed. Then, an energy function (based on nonlinear diffusion of color components and directional derivatives) is defined. Next, signeddistance functions are generated from different shapes of the object of interest. Finally, a variational framework (based on the level set) is employed to minimize the energy function. The experimental results demonstrate a good performance of the proposed method compared with others and show its robustness in the presence of noise and occlusion. The proposed algorithm is applicable in outdoor and medical image segmentation and also in optical character recognition (OCR).