The display of information characterizing the distribution of thermal gradients is associated with the formation of a twodimensional image. A thermal image is most often a group of objects with varying intensities. This picture is due to physical aspects. Most often, the thermal background does not have a clear boundary, and therefore the use of conventional methods for detecting special features in the form of angles or borders is not applicable. In the previously described works, a method was proposed for identifying special features based on the search for the midline, for closed objects. This approach did not take into account the possibility of changing the degree of growth of the line displacement, which may be correct provided that a pair of objects of different temperatures adjoin each other and there is information about this. The article proposes to develop a modification of the search method an equidistant curve that allows you to introduce a curve growth function. The difference from the original approach is the possibility of regulating the degree of movement of the internal or external borders in the direction of the neighbor. The approach proposed in the work includes the operations of filtering, changing the color space, changing the color range, and searching for stable signs. The task is relevant and may also be applicable in tasks: increasing the clarity of x-ray images; eliminate blur in photos; preprocessing images obtained in the visible spectrum; deblurring images obtained in motion, etc. In the article on a set of test data shows the applicability of the proposed approach for identifying stable features in thermal imaging images. The data obtained by FLIR C2 and SEEK thermal imaging cameras cover a wide range of possible applications from analysis of data obtained outside buildings, as well as technical processes occurring inside mechanisms.
Modern devices based on the analysis of thermal images are used in the construction of technical systems and the analysis of processes occurring into objects. In the modern world, the analysis of information about temperature changes allows you to solve many problems, drive a car in poor visibility conditions (fog, smog, twilight or night), create security systems and control access to objects, analyze internal processes, including such as: chemical reactions; friction analysis; checking the operation of complex technical systems (bearings, electrical, lubrication, cooling); living organisms (analysis of processes tissue death); temperature audit of buildings; analysis of the operation of internal combustion engines; braking and friction analysis systems; other. The image formed by the thermal imager has a low resolution. In order to analyze complex processes, it is necessary to develop methods and algorithms for combining images into a single information field. The problem of stitching images is encountered in many areas of technology, but for IR it is the most difficult. The article proposes an approach that allows you to identify local features in IR images, which allows you to increase the accuracy of stitching pairs of images into a single composition. The proposed algorithm based on layer-by-layer image analysis. The analysis is based on the search for local features, followed by a change in the bitrate of the image and the study of stationary edges. An example of highlighting local features is shown on a set of test images captured by a thermal imaging camera. The scope of this approach is the task of combining images obtained only in the infrared range.
The objects in the medical images are not visible due to low contrast and the noise. In general, X-ray, computed tomography (CT), and magnetic resonance imaging (MRI) images are often affected by blurriness, lack of contrast, which are very important for the accuracy of medical diagnosis. It is difficult to segmentation in such case without losing the details of the objects. The goal of image enhancement is to improve certain details of an image and to improve its visual quality. So, image enhancement technology is one of the key procedures in image segmentation for medical imaging. This article presents a two-stage approach, combining novel and traditional algorithms, for the enhancement and segmentation of images of bones obtained from CT. The first stage is a new combined local and global transform domain-based image enhancement algorithm. The basic idea of using local alfa-rooting method is to apply it to different disjoint blocks of different sizes. We used image enhancement non-reference quality measure for optimization alfa-rooting parameters. The second stage applies the modified active contour method based on an anisotropic gradient. The simulation results of the proposed algorithm are compared with other state-of-the-art segmentation methods, and its superiority in the presence of noise and blurred edges on the database of CT images is illustrated.
The paper proposes an algorithm to improve the accuracy of searching the boundaries of objects. We analyze X-ray images. Most often, images obtained in the X-ray range are subject to distortion. Noise and blurring are caused by the nature of the source and the imperfection of the sensor. In our work, we propose the use of a multicomponent processing algorithm. This type of processing is based on step-by-step image analysis. At the first stage, the stage of image blur recovery is performed (deblurring). At the next stage, the operation of filtering images (denoising) and processing the boundaries of objects is performed. The first two steps are performed using adaptive local processing with nonoverlapping windows. At the next stage, the multicriteria processing method is used for the one-dimensional and two-dimensional signals. The first approach is used to reduce the effect of the noise component at the boundaries of objects and is also used as a boundary detector. The second criterion is used to reduce the effect of the noise component in locally stationary areas. The efficiency of the proposed algorithm is shown using the example of medical X-ray data processing and the results of computed tomography. Using the example of the developed software for the analysis of CT images and the restoration of the lost elements of the bone structure, an example of the application of the proposed approaches for performing primary data processing operations is shown.
The acquisition of complex data of the recorded scene is an important task for video analysis of the processes occurring. The use of IR images allows obtaining data on additional characteristics that are not visible in the optical range. The data obtained by IR sensors can be in the near and far range, which makes it possible to see objects in the dark or to obtain data on their temperature. In the second case, the boundaries of objects are vague and difficult to correlate with the usual optical ranges. To do this a combination of data obtained by a pair of cameras is used. In this paper, we propose using the algorithm for stitching IR images based on data obtained in the optical range. To this end, an approach will be applied that includes parallel analysis of data on: saliency maps; search for boundaries and key points; reduction of bit resolution of images with preservation of borders; image matching; filtering data and restoring the sharpness of object boundaries. As an example, the result of combining data obtained under poor lighting conditions and the results of combining television images will be presented.
Medical visualization and analysis of medical data is an actual direction. Medical images are used in microbiology, genetics, roentgenology, oncology, surgery, ophthalmology, etc. Initial data processing is a major step towards obtaining a good diagnostic result. The paper considers the approach allows an image filtering with preservation of objects borders. The algorithm proposed in this paper is based on sequential data processing. At the first stage, local areas are determined, for this purpose the method of threshold processing, as well as the classical ICI algorithm, is applied. The second stage uses a method based on based on two criteria, namely, L2 norm and the first order square difference. To preserve the boundaries of objects, we will process the transition boundary and local neighborhood the filtering algorithm with a fixed-coefficient. For example, reconstructed images of CT, x-ray, and microbiological studies are shown. The test images show the effectiveness of the proposed algorithm. This shows the applicability of analysis many medical imaging applications.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.