Papers by Keyword: Image Processing

Abstract: With combining Unmanned Aerial Vehicle (UAV) and the high-precision of the low altitude Remote Sensing (RS) technology, UAV RS technology has become an important compleme-nt for satellite and manned aircraft RS, so it has drawn great attention of people at home and abroad. Most of UAV RS image technologies use small digital cameras to shoot so that it causes some proble-ms such as lower magnitude, more and larger morphing image. The image processing and mosaicing system of UAV RS implements the function of image identifying, selection of image group control points, geometric correction, mosaicing, seam lines eliminating automatically and rapidly with Interactive Data Language (IDL), and is targeted to solve the practical application problems such as preprocessing, mosaicing, seam-lines removing of civil UAV RS image.

Abstract: Digital X-ray photography technology is under the control of the computer, to use one-dimensional or 2D X-ray detector to convert the captured image into digital signals directly to using image processing technology. It can realize the function of image analysis. We introduce X-ray photography technology into the terminal identification in track and field, and use the clustering algorithm to improve computer image clustering algorithm. Through capturing the digital signal of human head, arms and legs, it enhances the terminal recognition method in track and field. Finally we use MATLAB to calculate the captured image value of X-ray photography. Through calculation, motion capture and recognition of X-ray image are enhanced obviously. It provides a theoretical basis for researching on motion capture technology in track and field.

Abstract: The study of evaporation of water droplets over horizontal heated surfaces is an intense area of research because of its wide application in various fields of heat transfer. The characterization of the behavior of water droplets is important in studying the cooling effects produced over impinging surfaces. The present study focuses on analyzing the shape and size of the droplets by applying image processing techniques. In the present work, a fixed volume of single water droplet is made to impinge on a horizontal Aluminium surface using a designed microcontroller based syringe pump. The formation and the dynamics of bubbles are recorded using a high speed camera. Image processing technique is used to determine the droplet parameters such as contact angle, spreading radius and to study the shape of the droplet. The surface temperature is measured using a Thermocouple connected to an online Data acquisition system. The effect of the characteristics of droplet on the decrease in surface temperature can be seen from the temperature – time graph and the processed photographs taken using high speed camera. The decrease in base plate temperature is found to be depending on the behavior and the properties of the droplet.

Abstract: Braking system is one of the important systems in Automobiles. It is essential to decelerate the vehicle and stop it when essential. The temperature of the brake pad (stator) and disc (rotor) increases because of frictional force between them. Higher temperatures may lead to brake fading or failure of braking system. In the present study droplet cooling of commercially available Brake pad is analyzed with surface temperatures in the range of 80°C - 150°C. The brake pad material analyzed is a composite material with Fe₂O₃, BaO, CaO, SiO₂, SO₃ and MgO as major constituents. The percentage of the constituents are found using Scanning Electron Microscope (SEM). The brake pad is artificially heated using cartridge heater and a fixed volume of water is dropped on to the brake pad surface using a syringe pump. The characteristics of droplet on the surface of the brake pad are recorded using a High speed camera. The temperature is measured continuously using a K type thermocouple and is recorded using an online data acquisition system. The characteristic of droplet enhanced cooling is presented.

Abstract: With increased expectations for engineering products of high quality and safety standards, the need for accurate, fast and objective quality determination of these characteristics in engineering products continues to grow. Embedded vision provides one alternative for an automated, non-destructive, fast and cost-effective technique to accomplish these requirements. In this work, the authors are developed an integrated system which has two major components: an Embedded Vision System (EVS) and a Real Time Monitoring System (RTMS). This work describes design and development of prototyped Production Line System (PLS) based on a practical and fast approach using EVS and LabVIEW with IMAQ Vision Assistant as image processing tool. Experimental results show that this integrated system is faster and produces a lower error rate than humans produce in the quality inspection process.

Abstract: In this paper, the design and architecture of general digital image processing circuit (GFDIPC) based on a Xilinx Virtex-5 FPGA processor is presented. The GFDIPC applications on thermal imaging, image fusion, real-time video stabilization and time-delay test for image processing system are described. The design of FPGA in each application follows the principle of functional modularity, pipeline processing and parallel computing, which brings FPGA high efficiency and high real-time performance.

Abstract: Digital photographic visibility system (DPVS) based on binocular targets is a method using digital camera and image processing technology for visibility detection. In order to obtain accurate results, the function and installation methods for main components of video visibility detection system including artificial objects, cameras and other parts are designed delicately. Also the article explains the image processing algorithm. From this analysis, the detection system engineering and implementation are not complicated. In 2013, this video visibility detection method has been applied to enhance foggy area security system in Anhui Province, Bengbu - Huainan expressway, and achieved good results.

Abstract: Finger vein authentication is a novel biometrics technology for personal identification. In this paper, universality, collectability, acceptability, circumvention, uniqueness, permanency and performance of finger vein distribution pattern are analyzed. Thereinto, universality, collectability, acceptability and circumvention of finger vein pattern are described simply through the citation of relational literature, and uniqueness, permanency, performance of finger vein pattern are particularly studied by experimental means. The experimental result shows that there are favorable general performance for finger vein pattern in biometrics, finger vein can be applied effectively in personal identity authentication, finger vein identification technology have a well applying prospect and developmental potential.

Abstract: The use of mammography as a method for the early detection of breast cancer reduces mortality from it. To aid in the diagnosis there are several free image processing software with the purpose of extracting characteristics such as microcalcification, nodules or edges of important structures. The objective of this study is to indicate which filters are best to aid in the processing of the images in three of these free software. The free software ImageJ, ImageTool and Mipav were used for the processing of 60 mammographic images from the Mini-MIAS database focusing the mean, median and Gaussian filters. The Haralick descriptors (second angular moment, contrast, entropy and correlation) and difference of values of gray levels (standard deviation, mean, minimum and maximum) were extracted from the resulting images. Then the results were compared taking into consideration the purpose of the processing. It was observed that it's best to use the mean and median filters from the Mipav software if the purpose of the processing is to leave the images with higher contrast levels. However, if the purpose is to obtain higher entropy levels, the ImageTool software should be used. It was also observed a similar processing time among the three software. The filter choice will depend on the type of noise to be removed from the image. For "Salt and Pepper" noise the mean filter should be used, while for the impulsive noise, the median one should be used. The results allowed the conclusion that the choice of the software to perform the processing of the mammographic images depends on the purpose of the processing application, if it's to increase the contrast in the image or if it's to extract other characteristics of diagnostic interest.

Abstract: fingerprint image preprocessing and is one of the branch of image processing and pattern recognition, after several years of development the increasing maturity of the technology. Due to the uniqueness and invariability of fingerprints, and the feasibility and practicability of the fingerprint identification technology, fingerprint identification has become the most popular, the most convenient, one of the most reliable personal identity authentication technology. Although on this technology has a variety of molding products, but because many of the core technology by commercial interests and confidentiality need without open, as well as the development of the society put forward higher requirements on the performance of the system, so in this field of research, still has important theoretical significance and practical value.