Automatic Segmentation of the Lung Fields in Portable Chest Radiographs based on Bézier Interpolation of Salient Control Points

Size: px
Start display at page:

Download "Automatic Segmentation of the Lung Fields in Portable Chest Radiographs based on Bézier Interpolation of Salient Control Points"

Transcription

1 IEEE International Workshop on Imaging Systems and Techniques IST 2008 Chania, Greece, September 10 12, 2008 Automatic Segmentation of the Lung Fields in Portable Chest Radiographs based on Bézier Interpolation of Salient Control Points Dimitris K. Iakovidis Dept. of Informatics and Computer Technology Technological Educational Institute of Lamia Lamia, Greece George Papamichalis 1 st Dept. of Thoracic Surgery Chest Hospital of Athens Sotiria Athens, Greece Abstract Portable chest radiographs are performed on the most critically-ill patients, who need highly skilled patient care and the best diagnostic tools. However, such radiographs are usually of low quality, mainly due to misaligned body positioning during their acquisition, and subject to a higher misinterpretation rate than the ones obtained with a non-portable x-ray device. This paper presents a pioneering computational approach that copes with the segmentation of the lung fields in portable chest radiographs. The proposed methodology involves detection of salient points on the anatomic structures around the lung fields by subsequent application of simple intensity and edge feature extraction techniques. The salient points detected are interpolated using Bézier curves intuitively approximating the boundaries of the lung fields. Unlike current methodologies, the proposed one does not exclude the overlapping region of the heart from the lung fields, where abnormalities can also be present. The results illustrate the robustness of the proposed methodology on a set of real portable radiographs of patients with bacterial pulmonary infections. A qualitative comparison with a state of the art approach based on graph cuts validates its effectiveness. Keywords-image segmentation; portable chest radiography; salient points, Bézier curves; lung; infections I. INTRODUCTION Radiography is a valuable tool to chest screening providing useful information for the prevention and diagnosis of various diseases [1]. Plain chest radiographs are usually obtained in a controlled setup where the patients are positioned in a standard way at the x-ray device. However, in the case of critically ill patients, this is not always feasible as they may be in pain or disabled. To cope with this problem, portable x-ray devices are commonly used to obtain the radiographs from various relative distances and angles to the patient who is immobilized in bed - not necessarily in the preferred position. Portable radiographs are usually of low quality mainly because of misaligned body positioning during their acquisition [2]. Consequently, they are more difficult to read and subject to a higher misinterpretation rate. A methodology that would automatically analyze such radiographs would be an asset to the medical community. A variety of image processing and analysis methodologies has been proposed for the segmentation of plain chest radiographs. Many of them have focused on the segmentation of the lung fields, whereas fewer have focused on the segmentation of the rib cage or other anatomic structures of the chest [3]. The importance of the segmentation of the lung fields becomes obvious considering that it is a prerequisite for almost any computational radiographic image analysis task. Lung field segmentation approaches that have been proposed include rulebased methodologies [5]-[10], machine learning algorithms [11]-[13], active shape models [4][14]-[17], and graph cuts[18]. The studies [5]-[10] indicate that the segmentation performance of the existing rule-based methodologies usually degrades if the quality of the radiograph is poor or the positioning of the patient deviates from the standard. Machine learning algorithms and active shape models can be less affected by a patient s positioning; however, they both require training, which makes them dependent on the subjective choice of representative training samples. The methodologies reported in [14],[16],[17] have been mainly evaluated on radiographs of normal or minimally distorted lungs. Robustness against the presence of abnormalities that interfere with the interior intensities of the lungs has been demonstrated in [4],[15] using active shape models. The graph cuts algorithm proposed in [18] is the most recent of the limited approaches coping with unsupervised segmentation of abnormal lung fields. It is based on morphological operations for obtaining an initial estimate of the region of the lung boundaries, and dilates the contour obtained by graph cuts within a potential contour band. The evaluation of this algorithm on a limited set of standard radiographs of patients infected with severe acute respiratory syndrome (SARS) showed that although it exhibits some resistance to boundary discontinuities and noise, the detected boundaries of the lung fields are affected by the edges of the ribs and result in a rough output contour. To the best of our knowledge, the problem of lung field segmentation in portable chest radiographs has not been previously addressed. In this paper we accept the challenge of coping with automatic segmentation of the lung fields in portable chest radiographs, and we propose a novel methodology that is resistant to patient positioning, to boundary discontinuities, and to the presence of abnormalities interfering with the interior intensity of the lungs. This work was supported in part by the European Commission s Seventh Framework Information Society Technologies (IST) Programme, Unit ICT for Health, project DEBUGIT (no ) /08/$ IEEE 82

2 The proposed methodology involves detection of salient points on the anatomic structures around the lung fields by subsequent application of simple intensity and edge feature extraction techniques. The salient points detected, are interpolated using Bézier curves [19] smoothly approximating the boundaries of the lung fields. The rest of this paper consists of three sections. Section II presents the proposed lung field segmentation approach. Its performance is evaluated in Section III, and a summary of conclusions derived from this study is provided in the last section. Internal control points P 1 P 2 Piecewise linear interpolation Bézier interpolation P 3 II. PROPOSED APPROACH A. Overview The proposed methodology assumes that: (1) the patient s body may not necessarily be aligned with the portable x-ray device, since the patient may be immobilized in bed; (2) the spine lies roughly somewhere in the middle of the radiograph, considering that the radiograph displays both the patient s lungs; (3) the spine and the bones of the ribcage are the densest structures visible in a chest radiograph [20], and consequently they are generally characterized by higher intensities than other anatomic structures. Based on these assumptions, points belonging to the densest structures bounding the lung fields are detected. As indicated in [10] the local maxima of the horizontal and vertical image profiles - i.e. signals produced by averaging image intensities across columns and rows, respectively - can be useful for the detection of such points. However, in the case of portable radiographs the local maxima corresponding to the structures bounding the lung fields are not located in particular positions as in the case of the stationary radiographs used in [10]. To cope with this problem, the proposed approach involves additional steps (Subsection II.C: Steps 2 and 3) for selecting local maxima of the horizontal profiles corresponding to the spine and to the outer left and right boundaries of the lung fields. Local maxima with intensities deviating from the average intensities of each boundary are discarded as outliers. Considering that the region of the spine is typically characterized by the highest intensities in a radiograph, the inner lung field boundaries will be more or less identifiable by their edges. These edges will be less prevalent in regions where the lung fields exhibit higher intensities such as the region of the heart, and regions with abnormalities appearing as bright shadows next to the inner lung field boundaries. The determination of these edges becomes even more difficult if the airing of the lungs is poor during the acquisition of the radiograph, which is usually the case in portable radiography as practiced in intensive care units. However, even if the inner lung field edges are prevalent they could easily get confused with the edges of the ribs within the lung fields. In order to minimize the likelihood of such confusions, the intensities of the anatomic structures lying in the region of the spine are set to zero via a novel selective thresholding algorithm. This algorithm results in an auxiliary image referred to as thresholded (Subsection II.C: Step 4) which is utilized in the subsequent steps of the proposed methodology. The select- P 0 Figure 1. Bézier vs piecewise linear interpolation of four points. ive thresholding algorithm identifies the intensities of the anatomic structures lying in the region of the spine by accumuaccumulating the most frequent intensities of samples acquired from the detected spine points. Using only the most frequent intensities from each sample, the possibility of discarding intensities belonging to the lung fields is minimized. Moreover, all the intensities that are higher than those belonging to the region of the spine are also set to zero, since they are unlikely to belong to the lung fields. It is worth noting that the resulting thresholded image will have zero intensities not only between the lung fields, but also in other regions of similar densities, including the diaphragms which define the lower boundaries of the lung fields. The inner lung field boundaries are then determined by the maximum edge points between the spine and the lung fields (Subsection II.C: Step 5). The edges are obtained via convolution with directional Sobel edge detectors [21]. This way, unlike current approaches [3]-[13],[15]-[18], the proposed one does not exclude the overlapping region of the heart from the lung fields, where abnormalities can also be present [1]. A similar approach is followed for the detection of the lower lung field boundaries (Subsection II.C: Step 6). In both cases the resulting points are plenty but include many outliers, most of which can be discarded by using a k nearest neighbor approach. The remaining salient points from the outer, the inner and the lower boundaries of each lung field are smoothly interpolated using Bézier curves. The subsequent curves are finally manipulated so that they form continuous closed curves segmenting the lung fields. B. Bézier interpolation Given a set of control points P 0, P 1,,P n, a Bézier curve is estimated according to the equation where t [0,1]. B n n n i i ( t) = Pi (1 t) t (1) i= 0 i Bézier curves are intuitively controlled by the detected salient points, in the sense that the curve is attracted by the internal control points, without necessarily passing through them (Fig. 1). This provides several advantages over other 83

3 interpolation methods that include insensitivity to outliers, and production of smoother curves. C. Algorithmic implementation The salient control points of a radiograph I of N M pixels, are detected and interpolated as follows (Fig. 2): Step 1. Detect local maxima of horizontal profiles. a) Acquire s h consecutive non-overlapping rectangular samples of h M, h<n pixels from the whole image. b) For each sample calculate its average horizontal profile. c) Detect the local maxima of each profile (white points in Fig.2b). Step 2. Detect the central, the left and the right columns (indicated in black in Fig. 2b) a) Acquire s v non-overlapping rectangular samples of N w, w<m pixels from the whole image. b) For each sample calculate the average intensity. c) The central column C is the one with the maximum average intensity within columns M/2-M/4 and M/2+M/4. d) The left column L is the one with the maximum average intensity within columns 0 and M/2-M/4. e) The right column R is the one with the maximum average intensity within columns M/2+M/4 and M-1. Step 3. Approximate the spine, and the outer left and right boundaries of the left and the right lung field respectively. a) For each of the s h samples - The points closest to C are considered as spine points. - The points closest to the left side of column L+(C- L)/2 (left white column in Fig. 2b) are considered to belong to the outer left boundary of the left lung field. - The points closest to the right side of column R+(R-C)/2 (right white column in Fig. 2b) are considered to belong to the outer right boundary of the right lung field. b) For each set of detected points discard outliers. c) Interpolate the remaining points of each set (Fig. 2c). Step 4. Threshold all the intensities of I corresponding to anatomic structures lying in the region of the spine. a) For each spine point acquire a square sample of x 2 pixels. b) Calculate the intensity histogram of each sample. c) Sum up the largest histogram components of all samples into a single histogram. d) Find the last non-zero component m of the resulting histogram. e) Set the intensities that correspond to non-zero histogram components, and the intensities that are larger than m, to zero, to obtain a thresholded image T(I) (Fig. 2d). (a) (c) (e) (g) (i) (j) Figure 2. Steps of the proposed methodology for the segmentation of a portable chest radiograph. Step 5. Detect edge points of the inner right and left boundaries of the left and the right lung field respectively. a) Convolve I with the vertical 3 3 Sobel operator having the negative signs on the left to obtain a map E vl (I) of vertical left image edges (Fig. 2e). b) Convolve I with the vertical 3 3 Sobel operator having the negative signs on the right to obtain a map E vr (I) of vertical right image edges (Fig. 2f). c) For each row start from the spine point and move left to find the point of E vl (I) with the maximum intensity for which T(I) has zero intensity. (d) (f) (h) 84

4 d) For each row start from the spine point and move right to find the point of E vr (I) with the maximum intensity for which T(I) has zero intensity. e) Discard points deviating from the average horizontal position of its k nearest neighbors as outliers. f) Interpolate the detected points (Fig 2g). Step 6. Detect edge points of the lower boundaries of the lung fields. a) Convolve I with the horizontal 3 3 Sobel operator to obtain a map E h (I) of horizontal image edges (Fig. 2h). b) For each column start from row M-1 and move upwards to find the point of E h (I) with the maximum intensity for which T(I) has zero intensity. c) Discard points deviating from the average vertical position of its k nearest neighbors as outliers. d) Interpolate the detected points (Fig 2i). Finally, the interpolating Bézier curves estimated in steps 3c, 5f and 6d, are cropped or extended so that they form continuous closed curves segmenting the lung fields (Fig.2j). This algorithm was developed in Java using a custom image processing and analysis framework providing crossplatform compatibility. III. RESULTS The effectiveness of the proposed methodology was evaluated on a set of twenty four anonymous radiographs obtained with a portable x-ray device from patients with pulmonary bacterial infections hospitalized in an intensive care unit of the Chest Hospital of Athens Sotiria. Such infections produce abnormalities most usually manifested as consolidations that are visible as bright shadows interfering with the interior intensities of the lungs [1],[2]. The segmentation performance was assessed in terms of accuracy, sensitivity and specificity, which are defined by the following equations: TP + TN accuracy = (2) TP + TN + FP + FN TP sensitivity = (3) TP + FN TN specificity = (4) TN + FP where TP is the number of true positive pixels, TN is the number of true negative pixels, FP is the number of false positive pixels, and FN is the number of false negative pixels. The ground truth region of the lung fields has been designated by an expert. All radiographs used in the experiments have been digitized at 8 bits and have been downscaled to fit a pixel bounding box. The parameters used in the experimental study presented in this paper include w=h, x=32, and k=5. Figure 3 illustrates the results obtained with the proposed methodology using different values of h. As indicated by the overlapping Accuracy Sensitivity Specificity 100% 95% 90% 85% 80% 75% 70% 100% 95% 90% 85% 80% 75% 70% 100% 95% 90% 85% 80% 75% 70% (a) h (pixels) h (pixels) h (pixels) (c) Figure 3. Results obtained with the proposed methodology for a range of values h, in terms of average (a) accuracy, sensitivity, and (c) specificity. The error bars depict the corresponding standard deviations. error bars, the average segmentation performance is not affected significantly by the selection of h. Best segmentations were obtained for h=9 and h=17. The sensitivity and the specificity in the former case reached 95.3% and 94.3%, and in the latter 95.0% and 93.6%. Indicative segmentations are illustrated in Fig. 2j and Fig. 4. In both cases the lung fields appear misaligned; whereas the boundaries of the right lung 85

5 (a) Figure 4 Portable radiograph of a patient with bacterial pulmonary infection. (a) Original. Segmented using the proposed methodology. it achieves smoother delineation of the lung field boundaries than the state of the art methodology based on graph cuts [18]; unlike current methodologies, it does not exclude the overlapping region of the heart from the lung fields, where abnormalities can also be present. Future objectives include enhancement of the proposed methodology with shape prior information, further experimentation with larger datasets and comparisons with other state of the art methodologies. The perspectives of this research extend to the development of a multimodal data mining system for adverse events detection, which will be capable of co-evaluating radiographic findings of patients with bacterial infections [22]. (a) Figure 5. Segmentation of radiographs obtained from patients infected with SARS, using the proposed methodology. The original images have been obtained from [18], where segmentation results with various methodologies are also provided. field in Fig. 4 are hardly distinguishable even by an expert. As noted in the introduction, current lung field segmentation methodologies do not cope explicitly with the segmentation of portable chest radiographs. However, the state of the art methodology presented in [18], which has been proposed for lung field segmentation in standard radiographs, could be considered as the most relevant methodology to compare with, since it is also unsupervised and it copes with infected lung fields. The results from the application of the proposed methodology on the images presented in [18] are illustrated in Fig. 5. The obtained segmentations are less noisy than the ones presented in [18], illustrate higher sensitivity, whereas the region of the heart overlapping the lung fields has not been excluded, enabling the detection of possible abnormalities even behind the heart. IV. CONCLUSIONS We presented a novel methodology for automatic segmentation of portable chest radiographs. It is capable of detecting salient points which are intuitively interpolated via Bézier curves. The following major conclusions can be derived from the experimental evaluation of the proposed methodology: it produces accurate segmentation of portable radiographs regardless of the patients positioning; it generally remains unaffected by the presence of abnormalities originating from bacterial pulmonary infections; REFERENCES [1] N.L. Müller, T. Franquet, K.S. Lee, C. Isabela, and S. Silva, Imaging of Pulmonary Infections, Lippincott Williams & Wilkins, 2006 [2] F.S. Bongard, and D.Y. Sue, Current Critical Care Diagnosis & Treatment, 2nd ed., McGraw-Hill/Appleton & Lange, 2002 [3] B.V. Ginneken, B.T.H. Romeny, and M.A. Viergever, Computer-Aided Diagnosis in Chest Radiography: A Survey, IEEE Trans. Medical Imaging, vol. 20, no. 12, pp , Dec [4] B.V. Ginneken, S. Katsuragawa, B.T.H. Romeny, K. Doi, and M.A. Viergever, Automatic Detection of Abnormalities in Chest Radiographs Using Local Texture Analysis, IEEE Trans. Medical Imaging, vol. 21, no. 2, pp , Feb [5] P.H. Meyers, H.C. Nice, C.M. Becker, N.J. Nettleton, J.W. Sweeney, and G.R. Meckstroht, Automated Computer Analysis of Radiolographic Images, Radiology, vol. 13, pp , [6] J. Duryea, and J. Boone, A Fully Automatic Algorithm for the Segmentation of Lung Fields in Digital Chest Radiographic Images, Medical Physics, vol. 22, no. 2, pp , [7] H. Luo, R. Gaborski, R. Acharya, Automatic Segmentation of Lung Regions in Chest Radiographs: A Model Guided Approach, in Proc. Int. Conf. Image Processing (ICIP 2000), vol. 2, 2000, pp [8] B.V. Ginneken, and B.T.H. Romeny, Automatic Segmentation of Lung Fields in Chest Radiographs, Medical Physics, vol. 27, no. 10, pp , [9] I. Iglesias, P.G. Tahoces, M. Souto, A. Martinez de Alegria, M.J. Lado, and J.J. Vidal, Lung Segmentation on Postero-anterior Digital Chest Radiographs Using Active Contours, Fred A. et al. (Eds.): SSPR&SPR 2004, Lecture Notes in Computer Science, vol. 3138, pp , [10] X.-W. Xu, and K. Doi, Image Feature Analysis for Computer Aided Diagnosis: Accurate Determination of the Ribcage Boundary in Chest Radiographs, Medical Physics, vol. 22, no. 5, pp , [11] G. Coppini, S. Diciotti, M. Falchini, N. Villari, and G. Valli, Neural Networks for Computer-Aided Diagnosis: Detection of Lung Nodules in Chest Radiograms, IEEE Trans. on Information Technology in Biomedicine, vol. 7, no. 4, pp , Apr [12] N. Vittitoe, R. Vargas-Voracek, and C. Floyd Jr, Markov Random Field Modeling in Posteroanterior Chest Radiograph Segmentation, Medical Physics, vol 26, no. 8, pp , [13] B.V. Ginneken, M.B. Stegmann, M. Loog, Segmentation of Anatomical Structures in Chest Radiographs using Supervised Methods: A Comparative Study on a Public Database, Medical Image Analysis, vol. 10, pp , [14] T. Cootes, C. Taylor, D. Cooper, and J. Graham, Active Shape Models - Their Training and Application, Computer Vision and Image Understanding, vol 61, no. 1, pp , [15] X. Xie, X. Li, S. Wan, and Y. Gong, Mining X-Ray Images of SARS Patients, in G.J. Williams and S.J. Simoff (Eds.) Data Mining, Lecture Notes in Artificial Intelligence, vol. 3755, pp , [16] J. Liang, T. McInerney, and D. Terzopoulos, United Snakes. Medical Image Analysis, vol. 10, pp ,

6 [17] T. Yu, J. Luo, N. Ahuja, Shape Regularized Active Contour using Iterative Global Search and Local Optimization, in Proc. Computer Vision and Pattern Recognition Conference (CVPR 2005), vol.2, pp , [18] S. Chen, L. Cao, J. Liu, X. Tang, Automatic Segmentation of Lung Fields from Radiographic Images of SARS Patients Using a New Graph Cuts Algorithm, in Proc. Int. Conf. Pattern Recognition (ICPR 2006), vol. 1, pp , [19] R.H. Bartels, J.C. Beatty, and B.A. Barsky, Bézier Curves. Ch. 10 in An Introduction to Splines for Use in Computer Graphics and Geometric Modelling. San Francisco, CA: Morgan Kaufmann, pp , [20] Novelline, R.A. (1997) Squires s Fundamentals of Radiology. Cambridge: Harvard University Press. [21] R.C. Gonzalez, and R.E. Woods, Digital Image Processing, 3rd ed., Prentice Hall, Upper Saddle River, NJ, [22] C. Lovis, D. Colaert, V.N. Stroetmann, DebugIT for Patient Safety - Improving the Treatment with Antibiotics through Multimedia Data Mining of Heterogeneous Clinical Data, Stud Health Technol. Inform., vol. 136, ,

Hierarchical Shape Statistical Model for Segmentation of Lung Fields in Chest Radiographs

Hierarchical Shape Statistical Model for Segmentation of Lung Fields in Chest Radiographs Hierarchical Shape Statistical Model for Segmentation of Lung Fields in Chest Radiographs Yonghong Shi 1 and Dinggang Shen 2,*1 1 Digital Medical Research Center, Fudan University, Shanghai, 232, China

More information

Automated Lesion Detection Methods for 2D and 3D Chest X-Ray Images

Automated Lesion Detection Methods for 2D and 3D Chest X-Ray Images Automated Lesion Detection Methods for 2D and 3D Chest X-Ray Images Takeshi Hara, Hiroshi Fujita,Yongbum Lee, Hitoshi Yoshimura* and Shoji Kido** Department of Information Science, Gifu University Yanagido

More information

Cardio-Thoracic Ratio Measurement Using Non-linear Least Square Approximation and Local Minimum

Cardio-Thoracic Ratio Measurement Using Non-linear Least Square Approximation and Local Minimum Cardio-Thoracic Ratio Measurement Using Non-linear Least Square Approximation and Local Minimum Wasin Poncheewin 1*, Monravee Tumkosit 2, Rajalida Lipikorn 1 1 Machine Intelligence and Multimedia Information

More information

Towards full-body X-ray images

Towards full-body X-ray images Towards full-body X-ray images Christoph Luckner 1,2, Thomas Mertelmeier 2, Andreas Maier 1, Ludwig Ritschl 2 1 Pattern Recognition Lab, FAU Erlangen-Nuernberg 2 Siemens Healthcare GmbH, Forchheim christoph.luckner@fau.de

More information

Semi-Automatic Detection of Cervical Vertebrae in X-ray Images Using Generalized Hough Transform

Semi-Automatic Detection of Cervical Vertebrae in X-ray Images Using Generalized Hough Transform Semi-Automatic Detection of Cervical Vertebrae in X-ray Images Using Generalized Hough Transform Mohamed Amine LARHMAM, Saïd MAHMOUDI and Mohammed BENJELLOUN Faculty of Engineering, University of Mons,

More information

Lung segmentation on standard and mobile chest radiographs using oriented Gaussian derivatives filter

Lung segmentation on standard and mobile chest radiographs using oriented Gaussian derivatives filter Wan Ahmad et al. BioMedical Engineering OnLine (2015) 14:20 DOI 10.1186/s12938-015-0014-8 RESEARCH Open Access Lung segmentation on standard and mobile chest radiographs using oriented Gaussian derivatives

More information

Time Stamp Detection and Recognition in Video Frames

Time Stamp Detection and Recognition in Video Frames Time Stamp Detection and Recognition in Video Frames Nongluk Covavisaruch and Chetsada Saengpanit Department of Computer Engineering, Chulalongkorn University, Bangkok 10330, Thailand E-mail: nongluk.c@chula.ac.th

More information

doi: /

doi: / Yiting Xie ; Anthony P. Reeves; Single 3D cell segmentation from optical CT microscope images. Proc. SPIE 934, Medical Imaging 214: Image Processing, 9343B (March 21, 214); doi:1.1117/12.243852. (214)

More information

CHAPTER 6 DETECTION OF MASS USING NOVEL SEGMENTATION, GLCM AND NEURAL NETWORKS

CHAPTER 6 DETECTION OF MASS USING NOVEL SEGMENTATION, GLCM AND NEURAL NETWORKS 130 CHAPTER 6 DETECTION OF MASS USING NOVEL SEGMENTATION, GLCM AND NEURAL NETWORKS A mass is defined as a space-occupying lesion seen in more than one projection and it is described by its shapes and margin

More information

Detection of Rib Shadows in Digital Chest Radiographs

Detection of Rib Shadows in Digital Chest Radiographs Detection of Rib Shadows in Digital Chest Radiographs S. Sarkar 1 and S. Chaudhuri 2'* 1School of Biomedical Engineering, 2Department of Electrical Engineering, Indian Institute of Technology, Powai, Bombay-400076,

More information

Engineering Problem and Goal

Engineering Problem and Goal Engineering Problem and Goal Engineering Problem: Traditional active contour models can not detect edges or convex regions in noisy images. Engineering Goal: The goal of this project is to design an algorithm

More information

Assessing the Skeletal Age From a Hand Radiograph: Automating the Tanner-Whitehouse Method

Assessing the Skeletal Age From a Hand Radiograph: Automating the Tanner-Whitehouse Method Assessing the Skeletal Age From a Hand Radiograph: Automating the Tanner-Whitehouse Method M. Niemeijer a, B. van Ginneken a, C.A. Maas a, F.J.A. Beek b and M.A. Viergever a a Image Sciences Institute,

More information

Automatic Detection of Texture Defects using Texture-Periodicity and Gabor Wavelets

Automatic Detection of Texture Defects using Texture-Periodicity and Gabor Wavelets Abstract Automatic Detection of Texture Defects using Texture-Periodicity and Gabor Wavelets V Asha 1, N U Bhajantri, and P Nagabhushan 3 1 New Horizon College of Engineering, Bangalore, Karnataka, India

More information

Image Resizing Based on Gradient Vector Flow Analysis

Image Resizing Based on Gradient Vector Flow Analysis Image Resizing Based on Gradient Vector Flow Analysis Sebastiano Battiato battiato@dmi.unict.it Giovanni Puglisi puglisi@dmi.unict.it Giovanni Maria Farinella gfarinellao@dmi.unict.it Daniele Ravì rav@dmi.unict.it

More information

An Approach for Real Time Moving Object Extraction based on Edge Region Determination

An Approach for Real Time Moving Object Extraction based on Edge Region Determination An Approach for Real Time Moving Object Extraction based on Edge Region Determination Sabrina Hoque Tuli Department of Computer Science and Engineering, Chittagong University of Engineering and Technology,

More information

8/3/2017. Contour Assessment for Quality Assurance and Data Mining. Objective. Outline. Tom Purdie, PhD, MCCPM

8/3/2017. Contour Assessment for Quality Assurance and Data Mining. Objective. Outline. Tom Purdie, PhD, MCCPM Contour Assessment for Quality Assurance and Data Mining Tom Purdie, PhD, MCCPM Objective Understand the state-of-the-art in contour assessment for quality assurance including data mining-based techniques

More information

NIH Public Access Author Manuscript Proc Soc Photo Opt Instrum Eng. Author manuscript; available in PMC 2014 October 07.

NIH Public Access Author Manuscript Proc Soc Photo Opt Instrum Eng. Author manuscript; available in PMC 2014 October 07. NIH Public Access Author Manuscript Published in final edited form as: Proc Soc Photo Opt Instrum Eng. 2014 March 21; 9034: 903442. doi:10.1117/12.2042915. MRI Brain Tumor Segmentation and Necrosis Detection

More information

IRIS SEGMENTATION OF NON-IDEAL IMAGES

IRIS SEGMENTATION OF NON-IDEAL IMAGES IRIS SEGMENTATION OF NON-IDEAL IMAGES William S. Weld St. Lawrence University Computer Science Department Canton, NY 13617 Xiaojun Qi, Ph.D Utah State University Computer Science Department Logan, UT 84322

More information

A Laplacian Based Novel Approach to Efficient Text Localization in Grayscale Images

A Laplacian Based Novel Approach to Efficient Text Localization in Grayscale Images A Laplacian Based Novel Approach to Efficient Text Localization in Grayscale Images Karthik Ram K.V & Mahantesh K Department of Electronics and Communication Engineering, SJB Institute of Technology, Bangalore,

More information

Integration of Valley Orientation Distribution for Polyp Region Identification in Colonoscopy

Integration of Valley Orientation Distribution for Polyp Region Identification in Colonoscopy Integration of Valley Orientation Distribution for Polyp Region Identification in Colonoscopy Jorge Bernal, Javier Sánchez, and Fernando Vilariño Computer Vision Centre and Computer Science Department,

More information

Bangalore Institute of Technology, Bangalore, Karnataka, INDIA. University B.D.T Engineering College,V.T.U Karnataka, INDIA.

Bangalore Institute of Technology, Bangalore, Karnataka, INDIA. University B.D.T Engineering College,V.T.U Karnataka, INDIA. AN EFFICIENT LEARNING BASED ALGORITHM FOR LUNG BOUNDARY DETECTION FOR CHEST X-RAY Abstract We present an algorithm for the automatic delineation of lung boundary fields in chest radiographs. An attempt

More information

Detecting motion by means of 2D and 3D information

Detecting motion by means of 2D and 3D information Detecting motion by means of 2D and 3D information Federico Tombari Stefano Mattoccia Luigi Di Stefano Fabio Tonelli Department of Electronics Computer Science and Systems (DEIS) Viale Risorgimento 2,

More information

Automated segmentation methods for liver analysis in oncology applications

Automated segmentation methods for liver analysis in oncology applications University of Szeged Department of Image Processing and Computer Graphics Automated segmentation methods for liver analysis in oncology applications Ph. D. Thesis László Ruskó Thesis Advisor Dr. Antal

More information

Pictures at an Exhibition

Pictures at an Exhibition Pictures at an Exhibition Han-I Su Department of Electrical Engineering Stanford University, CA, 94305 Abstract We employ an image identification algorithm for interactive museum guide with pictures taken

More information

TEXT DETECTION AND RECOGNITION IN CAMERA BASED IMAGES

TEXT DETECTION AND RECOGNITION IN CAMERA BASED IMAGES TEXT DETECTION AND RECOGNITION IN CAMERA BASED IMAGES Mr. Vishal A Kanjariya*, Mrs. Bhavika N Patel Lecturer, Computer Engineering Department, B & B Institute of Technology, Anand, Gujarat, India. ABSTRACT:

More information

Automatic Lung Surface Registration Using Selective Distance Measure in Temporal CT Scans

Automatic Lung Surface Registration Using Selective Distance Measure in Temporal CT Scans Automatic Lung Surface Registration Using Selective Distance Measure in Temporal CT Scans Helen Hong 1, Jeongjin Lee 2, Kyung Won Lee 3, and Yeong Gil Shin 2 1 School of Electrical Engineering and Computer

More information

Small-scale objects extraction in digital images

Small-scale objects extraction in digital images 102 Int'l Conf. IP, Comp. Vision, and Pattern Recognition IPCV'15 Small-scale objects extraction in digital images V. Volkov 1,2 S. Bobylev 1 1 Radioengineering Dept., The Bonch-Bruevich State Telecommunications

More information

Automatic Rapid Segmentation of Human Lung from 2D Chest X-Ray Images

Automatic Rapid Segmentation of Human Lung from 2D Chest X-Ray Images Automatic Rapid Segmentation of Human Lung from 2D Chest X-Ray Images Abstract. In this paper, we propose a complete framework that segments lungs from 2D Chest X-Ray (CXR) images automatically and rapidly.

More information

An Automated Image-based Method for Multi-Leaf Collimator Positioning Verification in Intensity Modulated Radiation Therapy

An Automated Image-based Method for Multi-Leaf Collimator Positioning Verification in Intensity Modulated Radiation Therapy An Automated Image-based Method for Multi-Leaf Collimator Positioning Verification in Intensity Modulated Radiation Therapy Chenyang Xu 1, Siemens Corporate Research, Inc., Princeton, NJ, USA Xiaolei Huang,

More information

Problem Solving Assignment 1

Problem Solving Assignment 1 CS6240 Problem Solving Assignment 1 p. 1/20 Problem Solving Assignment 1 CS6240 Multimedia Analysis Daniel Dahlmeier National University of Singapore CS6240 Problem Solving Assignment 1 p. 2/20 Introduction

More information

Human pose estimation using Active Shape Models

Human pose estimation using Active Shape Models Human pose estimation using Active Shape Models Changhyuk Jang and Keechul Jung Abstract Human pose estimation can be executed using Active Shape Models. The existing techniques for applying to human-body

More information

Segmentation in Noisy Medical Images Using PCA Model Based Particle Filtering

Segmentation in Noisy Medical Images Using PCA Model Based Particle Filtering Segmentation in Noisy Medical Images Using PCA Model Based Particle Filtering Wei Qu a, Xiaolei Huang b, and Yuanyuan Jia c a Siemens Medical Solutions USA Inc., AX Division, Hoffman Estates, IL 60192;

More information

Detection of a Single Hand Shape in the Foreground of Still Images

Detection of a Single Hand Shape in the Foreground of Still Images CS229 Project Final Report Detection of a Single Hand Shape in the Foreground of Still Images Toan Tran (dtoan@stanford.edu) 1. Introduction This paper is about an image detection system that can detect

More information

CHAPTER 3 RETINAL OPTIC DISC SEGMENTATION

CHAPTER 3 RETINAL OPTIC DISC SEGMENTATION 60 CHAPTER 3 RETINAL OPTIC DISC SEGMENTATION 3.1 IMPORTANCE OF OPTIC DISC Ocular fundus images provide information about ophthalmic, retinal and even systemic diseases such as hypertension, diabetes, macular

More information

Perfectly Flat Histogram Equalization

Perfectly Flat Histogram Equalization Perfectly Flat Histogram Equalization Jacob Levman, Javad Alirezaie, Gul Khan Department of Electrical and Computer Engineering, Ryerson University jlevman jalireza gnkhan@ee.ryerson.ca Abstract In this

More information

Face Recognition Using Vector Quantization Histogram and Support Vector Machine Classifier Rong-sheng LI, Fei-fei LEE *, Yan YAN and Qiu CHEN

Face Recognition Using Vector Quantization Histogram and Support Vector Machine Classifier Rong-sheng LI, Fei-fei LEE *, Yan YAN and Qiu CHEN 2016 International Conference on Artificial Intelligence: Techniques and Applications (AITA 2016) ISBN: 978-1-60595-389-2 Face Recognition Using Vector Quantization Histogram and Support Vector Machine

More information

GENERAL AUTOMATED FLAW DETECTION SCHEME FOR NDE X-RAY IMAGES

GENERAL AUTOMATED FLAW DETECTION SCHEME FOR NDE X-RAY IMAGES GENERAL AUTOMATED FLAW DETECTION SCHEME FOR NDE X-RAY IMAGES Karl W. Ulmer and John P. Basart Center for Nondestructive Evaluation Department of Electrical and Computer Engineering Iowa State University

More information

SURVEY ON IMAGE PROCESSING IN THE FIELD OF DE-NOISING TECHNIQUES AND EDGE DETECTION TECHNIQUES ON RADIOGRAPHIC IMAGES

SURVEY ON IMAGE PROCESSING IN THE FIELD OF DE-NOISING TECHNIQUES AND EDGE DETECTION TECHNIQUES ON RADIOGRAPHIC IMAGES SURVEY ON IMAGE PROCESSING IN THE FIELD OF DE-NOISING TECHNIQUES AND EDGE DETECTION TECHNIQUES ON RADIOGRAPHIC IMAGES 1 B.THAMOTHARAN, 2 M.MENAKA, 3 SANDHYA VAIDYANATHAN, 3 SOWMYA RAVIKUMAR 1 Asst. Prof.,

More information

An Efficient Single Chord-based Accumulation Technique (SCA) to Detect More Reliable Corners

An Efficient Single Chord-based Accumulation Technique (SCA) to Detect More Reliable Corners An Efficient Single Chord-based Accumulation Technique (SCA) to Detect More Reliable Corners Mohammad Asiful Hossain, Abdul Kawsar Tushar, and Shofiullah Babor Computer Science and Engineering Department,

More information

Detection & Classification of Lung Nodules Using multi resolution MTANN in Chest Radiography Images

Detection & Classification of Lung Nodules Using multi resolution MTANN in Chest Radiography Images The International Journal Of Engineering And Science (IJES) ISSN (e): 2319 1813 ISSN (p): 2319 1805 Pages 98-104 March - 2015 Detection & Classification of Lung Nodules Using multi resolution MTANN in

More information

Robust and accurate change detection under sudden illumination variations

Robust and accurate change detection under sudden illumination variations Robust and accurate change detection under sudden illumination variations Luigi Di Stefano Federico Tombari Stefano Mattoccia Errico De Lisi Department of Electronics Computer Science and Systems (DEIS)

More information

Understanding Tracking and StroMotion of Soccer Ball

Understanding Tracking and StroMotion of Soccer Ball Understanding Tracking and StroMotion of Soccer Ball Nhat H. Nguyen Master Student 205 Witherspoon Hall Charlotte, NC 28223 704 656 2021 rich.uncc@gmail.com ABSTRACT Soccer requires rapid ball movements.

More information

Patient-Specific Model Based Segmentation of Lung Computed Tomographic Images

Patient-Specific Model Based Segmentation of Lung Computed Tomographic Images JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 32, 1373-1394 (2016) Patient-Specific Model Based Segmentation of Lung Computed Tomographic Images DHALIA SWEETLIN J 1, KHANNA NEHEMIAH H 2 AND KANNAN A 3

More information

A Method of Annotation Extraction from Paper Documents Using Alignment Based on Local Arrangements of Feature Points

A Method of Annotation Extraction from Paper Documents Using Alignment Based on Local Arrangements of Feature Points A Method of Annotation Extraction from Paper Documents Using Alignment Based on Local Arrangements of Feature Points Tomohiro Nakai, Koichi Kise, Masakazu Iwamura Graduate School of Engineering, Osaka

More information

A Comparison of wavelet and curvelet for lung cancer diagnosis with a new Cluster K-Nearest Neighbor classifier

A Comparison of wavelet and curvelet for lung cancer diagnosis with a new Cluster K-Nearest Neighbor classifier A Comparison of wavelet and curvelet for lung cancer diagnosis with a new Cluster K-Nearest Neighbor classifier HAMADA R. H. AL-ABSI 1 AND BRAHIM BELHAOUARI SAMIR 2 1 Department of Computer and Information

More information

Image Segmentation Based on Watershed and Edge Detection Techniques

Image Segmentation Based on Watershed and Edge Detection Techniques 0 The International Arab Journal of Information Technology, Vol., No., April 00 Image Segmentation Based on Watershed and Edge Detection Techniques Nassir Salman Computer Science Department, Zarqa Private

More information

User-Defined B-Spline Template-Snakes

User-Defined B-Spline Template-Snakes User-Defined B-Spline Template-Snakes Tim McInerney 1,2 and Hoda Dehmeshki 1 1 Dept. of Math, Physics and Computer Science, Ryerson Univ., Toronto, ON M5B 2K3, Canada 2 Dept. of Computer Science, Univ.

More information

Using the Apriori Algorithm for Medical Image Classification SORINA GHITA

Using the Apriori Algorithm for Medical Image Classification SORINA GHITA Using the Apriori Algorithm for Medical Image Classification SORINA GHITA Introduction Today, the analysis of an image is done by a radiologist and is time consuming. Also, the amount of images is growing

More information

SEMI-BLIND IMAGE RESTORATION USING A LOCAL NEURAL APPROACH

SEMI-BLIND IMAGE RESTORATION USING A LOCAL NEURAL APPROACH SEMI-BLIND IMAGE RESTORATION USING A LOCAL NEURAL APPROACH Ignazio Gallo, Elisabetta Binaghi and Mario Raspanti Universitá degli Studi dell Insubria Varese, Italy email: ignazio.gallo@uninsubria.it ABSTRACT

More information

Keywords: Thresholding, Morphological operations, Image filtering, Adaptive histogram equalization, Ceramic tile.

Keywords: Thresholding, Morphological operations, Image filtering, Adaptive histogram equalization, Ceramic tile. Volume 3, Issue 7, July 2013 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Blobs and Cracks

More information

Head Frontal-View Identification Using Extended LLE

Head Frontal-View Identification Using Extended LLE Head Frontal-View Identification Using Extended LLE Chao Wang Center for Spoken Language Understanding, Oregon Health and Science University Abstract Automatic head frontal-view identification is challenging

More information

Edge Detection Lecture 03 Computer Vision

Edge Detection Lecture 03 Computer Vision Edge Detection Lecture 3 Computer Vision Suggested readings Chapter 5 Linda G. Shapiro and George Stockman, Computer Vision, Upper Saddle River, NJ, Prentice Hall,. Chapter David A. Forsyth and Jean Ponce,

More information

CORRELATION BASED CAR NUMBER PLATE EXTRACTION SYSTEM

CORRELATION BASED CAR NUMBER PLATE EXTRACTION SYSTEM CORRELATION BASED CAR NUMBER PLATE EXTRACTION SYSTEM 1 PHYO THET KHIN, 2 LAI LAI WIN KYI 1,2 Department of Information Technology, Mandalay Technological University The Republic of the Union of Myanmar

More information

ADVANCED IMAGE PROCESSING METHODS FOR ULTRASONIC NDE RESEARCH C. H. Chen, University of Massachusetts Dartmouth, N.

ADVANCED IMAGE PROCESSING METHODS FOR ULTRASONIC NDE RESEARCH C. H. Chen, University of Massachusetts Dartmouth, N. ADVANCED IMAGE PROCESSING METHODS FOR ULTRASONIC NDE RESEARCH C. H. Chen, University of Massachusetts Dartmouth, N. Dartmouth, MA USA Abstract: The significant progress in ultrasonic NDE systems has now

More information

Edge Detection in Angiogram Images Using Modified Classical Image Processing Technique

Edge Detection in Angiogram Images Using Modified Classical Image Processing Technique Edge Detection in Angiogram Images Using Modified Classical Image Processing Technique S. Deepak Raj 1 Harisha D S 2 1,2 Asst. Prof, Dept Of ISE, Sai Vidya Institute of Technology, Bangalore, India Deepak

More information

OCR For Handwritten Marathi Script

OCR For Handwritten Marathi Script International Journal of Scientific & Engineering Research Volume 3, Issue 8, August-2012 1 OCR For Handwritten Marathi Script Mrs.Vinaya. S. Tapkir 1, Mrs.Sushma.D.Shelke 2 1 Maharashtra Academy Of Engineering,

More information

Introduction to digital image classification

Introduction to digital image classification Introduction to digital image classification Dr. Norman Kerle, Wan Bakx MSc a.o. INTERNATIONAL INSTITUTE FOR GEO-INFORMATION SCIENCE AND EARTH OBSERVATION Purpose of lecture Main lecture topics Review

More information

Automatically Algorithm for Physician s Handwritten Segmentation on Prescription

Automatically Algorithm for Physician s Handwritten Segmentation on Prescription Automatically Algorithm for Physician s Handwritten Segmentation on Prescription Narumol Chumuang 1 and Mahasak Ketcham 2 Department of Information Technology, Faculty of Information Technology, King Mongkut's

More information

Chapters 1 7: Overview

Chapters 1 7: Overview Chapters 1 7: Overview Photogrammetric mapping: introduction, applications, and tools GNSS/INS-assisted photogrammetric and LiDAR mapping LiDAR mapping: principles, applications, mathematical model, and

More information

Segmentation and Modeling of the Spinal Cord for Reality-based Surgical Simulator

Segmentation and Modeling of the Spinal Cord for Reality-based Surgical Simulator Segmentation and Modeling of the Spinal Cord for Reality-based Surgical Simulator Li X.C.,, Chui C. K.,, and Ong S. H.,* Dept. of Electrical and Computer Engineering Dept. of Mechanical Engineering, National

More information

Medical images, segmentation and analysis

Medical images, segmentation and analysis Medical images, segmentation and analysis ImageLab group http://imagelab.ing.unimo.it Università degli Studi di Modena e Reggio Emilia Medical Images Macroscopic Dermoscopic ELM enhance the features of

More information

Identifying Layout Classes for Mathematical Symbols Using Layout Context

Identifying Layout Classes for Mathematical Symbols Using Layout Context Rochester Institute of Technology RIT Scholar Works Articles 2009 Identifying Layout Classes for Mathematical Symbols Using Layout Context Ling Ouyang Rochester Institute of Technology Richard Zanibbi

More information

An Edge-Based Approach to Motion Detection*

An Edge-Based Approach to Motion Detection* An Edge-Based Approach to Motion Detection* Angel D. Sappa and Fadi Dornaika Computer Vison Center Edifici O Campus UAB 08193 Barcelona, Spain {sappa, dornaika}@cvc.uab.es Abstract. This paper presents

More information

CONTENT ADAPTIVE SCREEN IMAGE SCALING

CONTENT ADAPTIVE SCREEN IMAGE SCALING CONTENT ADAPTIVE SCREEN IMAGE SCALING Yao Zhai (*), Qifei Wang, Yan Lu, Shipeng Li University of Science and Technology of China, Hefei, Anhui, 37, China Microsoft Research, Beijing, 8, China ABSTRACT

More information

Scene Text Detection Using Machine Learning Classifiers

Scene Text Detection Using Machine Learning Classifiers 601 Scene Text Detection Using Machine Learning Classifiers Nafla C.N. 1, Sneha K. 2, Divya K.P. 3 1 (Department of CSE, RCET, Akkikkvu, Thrissur) 2 (Department of CSE, RCET, Akkikkvu, Thrissur) 3 (Department

More information

Assessing the Local Credibility of a Medical Image Segmentation

Assessing the Local Credibility of a Medical Image Segmentation Assessing the Local Credibility of a Medical Image Segmentation Joshua H. Levy, Robert E. Broadhurst, Surajit Ray, Edward L. Chaney, and Stephen M. Pizer Medical Image Display and Analysis Group (MIDAG),

More information

Norbert Schuff VA Medical Center and UCSF

Norbert Schuff VA Medical Center and UCSF Norbert Schuff Medical Center and UCSF Norbert.schuff@ucsf.edu Medical Imaging Informatics N.Schuff Course # 170.03 Slide 1/67 Objective Learn the principle segmentation techniques Understand the role

More information

Analysis of Image and Video Using Color, Texture and Shape Features for Object Identification

Analysis of Image and Video Using Color, Texture and Shape Features for Object Identification IOSR Journal of Computer Engineering (IOSR-JCE) e-issn: 2278-0661,p-ISSN: 2278-8727, Volume 16, Issue 6, Ver. VI (Nov Dec. 2014), PP 29-33 Analysis of Image and Video Using Color, Texture and Shape Features

More information

Comparison between Various Edge Detection Methods on Satellite Image

Comparison between Various Edge Detection Methods on Satellite Image Comparison between Various Edge Detection Methods on Satellite Image H.S. Bhadauria 1, Annapurna Singh 2, Anuj Kumar 3 Govind Ballabh Pant Engineering College ( Pauri garhwal),computer Science and Engineering

More information

X-ray Categorization and Spatial Localization of Chest Pathologies

X-ray Categorization and Spatial Localization of Chest Pathologies X-ray Categorization and Spatial Localization of Chest Pathologies Uri Avni 1, Hayit Greenspan 1 and Jacob Goldberger 2 1 BioMedical Engineering Tel-Aviv University, Israel 2 School of Engineering, Bar-Ilan

More information

Comparison of segmentation using fast marching and geodesic active contours methods for bone

Comparison of segmentation using fast marching and geodesic active contours methods for bone Journal of Physics: Conference Series PAPER OPEN ACCESS Comparison of segmentation using fast marching and geodesic active contours methods for bone To cite this article: A Bilqis and R Widita 206 J. Phys.:

More information

Texture Sensitive Image Inpainting after Object Morphing

Texture Sensitive Image Inpainting after Object Morphing Texture Sensitive Image Inpainting after Object Morphing Yin Chieh Liu and Yi-Leh Wu Department of Computer Science and Information Engineering National Taiwan University of Science and Technology, Taiwan

More information

Object Purpose Based Grasping

Object Purpose Based Grasping Object Purpose Based Grasping Song Cao, Jijie Zhao Abstract Objects often have multiple purposes, and the way humans grasp a certain object may vary based on the different intended purposes. To enable

More information

Segmentation of Mushroom and Cap Width Measurement Using Modified K-Means Clustering Algorithm

Segmentation of Mushroom and Cap Width Measurement Using Modified K-Means Clustering Algorithm Segmentation of Mushroom and Cap Width Measurement Using Modified K-Means Clustering Algorithm Eser SERT, Ibrahim Taner OKUMUS Computer Engineering Department, Engineering and Architecture Faculty, Kahramanmaras

More information

A Method for the Identification of Inaccuracies in Pupil Segmentation

A Method for the Identification of Inaccuracies in Pupil Segmentation A Method for the Identification of Inaccuracies in Pupil Segmentation Hugo Proença and Luís A. Alexandre Dep. Informatics, IT - Networks and Multimedia Group Universidade da Beira Interior, Covilhã, Portugal

More information

A Robust Wipe Detection Algorithm

A Robust Wipe Detection Algorithm A Robust Wipe Detection Algorithm C. W. Ngo, T. C. Pong & R. T. Chin Department of Computer Science The Hong Kong University of Science & Technology Clear Water Bay, Kowloon, Hong Kong Email: fcwngo, tcpong,

More information

Object Tracking Algorithm based on Combination of Edge and Color Information

Object Tracking Algorithm based on Combination of Edge and Color Information Object Tracking Algorithm based on Combination of Edge and Color Information 1 Hsiao-Chi Ho ( 賀孝淇 ), 2 Chiou-Shann Fuh ( 傅楸善 ), 3 Feng-Li Lian ( 連豊力 ) 1 Dept. of Electronic Engineering National Taiwan

More information

Text Detection in Indoor/Outdoor Scene Images

Text Detection in Indoor/Outdoor Scene Images Text Detection in Indoor/Outdoor Scene Images B. Gatos, I. Pratikakis, K. Kepene and S.J. Perantonis Computational Intelligence Laboratory, Institute of Informatics and Telecommunications, National Center

More information

EE368 Project Report CD Cover Recognition Using Modified SIFT Algorithm

EE368 Project Report CD Cover Recognition Using Modified SIFT Algorithm EE368 Project Report CD Cover Recognition Using Modified SIFT Algorithm Group 1: Mina A. Makar Stanford University mamakar@stanford.edu Abstract In this report, we investigate the application of the Scale-Invariant

More information

K-Means Clustering Using Localized Histogram Analysis

K-Means Clustering Using Localized Histogram Analysis K-Means Clustering Using Localized Histogram Analysis Michael Bryson University of South Carolina, Department of Computer Science Columbia, SC brysonm@cse.sc.edu Abstract. The first step required for many

More information

Modern Medical Image Analysis 8DC00 Exam

Modern Medical Image Analysis 8DC00 Exam Parts of answers are inside square brackets [... ]. These parts are optional. Answers can be written in Dutch or in English, as you prefer. You can use drawings and diagrams to support your textual answers.

More information

Extraction and recognition of the thoracic organs based on 3D CT images and its application

Extraction and recognition of the thoracic organs based on 3D CT images and its application 1 Extraction and recognition of the thoracic organs based on 3D CT images and its application Xiangrong Zhou, PhD a, Takeshi Hara, PhD b, Hiroshi Fujita, PhD b, Yoshihiro Ida, RT c, Kazuhiro Katada, MD

More information

I. INTRODUCTION. Figure-1 Basic block of text analysis

I. INTRODUCTION. Figure-1 Basic block of text analysis ISSN: 2349-7637 (Online) (RHIMRJ) Research Paper Available online at: www.rhimrj.com Detection and Localization of Texts from Natural Scene Images: A Hybrid Approach Priyanka Muchhadiya Post Graduate Fellow,

More information

Estimation of common groundplane based on co-motion statistics

Estimation of common groundplane based on co-motion statistics Estimation of common groundplane based on co-motion statistics Zoltan Szlavik, Laszlo Havasi 2, Tamas Sziranyi Analogical and Neural Computing Laboratory, Computer and Automation Research Institute of

More information

A Survey of Light Source Detection Methods

A Survey of Light Source Detection Methods A Survey of Light Source Detection Methods Nathan Funk University of Alberta Mini-Project for CMPUT 603 November 30, 2003 Abstract This paper provides an overview of the most prominent techniques for light

More information

Computer-Aided Diagnosis in Abdominal and Cardiac Radiology Using Neural Networks

Computer-Aided Diagnosis in Abdominal and Cardiac Radiology Using Neural Networks Computer-Aided Diagnosis in Abdominal and Cardiac Radiology Using Neural Networks Du-Yih Tsai, Masaru Sekiya and Yongbum Lee Department of Radiological Technology, School of Health Sciences, Faculty of

More information

Figure 1: Workflow of object-based classification

Figure 1: Workflow of object-based classification Technical Specifications Object Analyst Object Analyst is an add-on package for Geomatica that provides tools for segmentation, classification, and feature extraction. Object Analyst includes an all-in-one

More information

An Objective Evaluation Methodology for Handwritten Image Document Binarization Techniques

An Objective Evaluation Methodology for Handwritten Image Document Binarization Techniques An Objective Evaluation Methodology for Handwritten Image Document Binarization Techniques K. Ntirogiannis, B. Gatos and I. Pratikakis Computational Intelligence Laboratory, Institute of Informatics and

More information

Detection of Edges Using Mathematical Morphological Operators

Detection of Edges Using Mathematical Morphological Operators OPEN TRANSACTIONS ON INFORMATION PROCESSING Volume 1, Number 1, MAY 2014 OPEN TRANSACTIONS ON INFORMATION PROCESSING Detection of Edges Using Mathematical Morphological Operators Suman Rani*, Deepti Bansal,

More information

Towards Projector-based Visualization for Computer-assisted CABG at the Open Heart

Towards Projector-based Visualization for Computer-assisted CABG at the Open Heart Towards Projector-based Visualization for Computer-assisted CABG at the Open Heart Christine Hartung 1, Claudia Gnahm 1, Stefan Sailer 1, Marcel Schenderlein 1, Reinhard Friedl 2, Martin Hoffmann 3, Klaus

More information

Color Lesion Boundary Detection Using Live Wire

Color Lesion Boundary Detection Using Live Wire Color Lesion Boundary Detection Using Live Wire Artur Chodorowski a, Ulf Mattsson b, Morgan Langille c and Ghassan Hamarneh c a Chalmers University of Technology, Göteborg, Sweden b Central Hospital, Karlstad,

More information

RESTORATION OF DEGRADED DOCUMENTS USING IMAGE BINARIZATION TECHNIQUE

RESTORATION OF DEGRADED DOCUMENTS USING IMAGE BINARIZATION TECHNIQUE RESTORATION OF DEGRADED DOCUMENTS USING IMAGE BINARIZATION TECHNIQUE K. Kaviya Selvi 1 and R. S. Sabeenian 2 1 Department of Electronics and Communication Engineering, Communication Systems, Sona College

More information

2 Michael E. Leventon and Sarah F. F. Gibson a b c d Fig. 1. (a, b) Two MR scans of a person's knee. Both images have high resolution in-plane, but ha

2 Michael E. Leventon and Sarah F. F. Gibson a b c d Fig. 1. (a, b) Two MR scans of a person's knee. Both images have high resolution in-plane, but ha Model Generation from Multiple Volumes using Constrained Elastic SurfaceNets Michael E. Leventon and Sarah F. F. Gibson 1 MIT Artificial Intelligence Laboratory, Cambridge, MA 02139, USA leventon@ai.mit.edu

More information

Implemented by Valsamis Douskos Laboratoty of Photogrammetry, Dept. of Surveying, National Tehnical University of Athens

Implemented by Valsamis Douskos Laboratoty of Photogrammetry, Dept. of Surveying, National Tehnical University of Athens An open-source toolbox in Matlab for fully automatic calibration of close-range digital cameras based on images of chess-boards FAUCCAL (Fully Automatic Camera Calibration) Implemented by Valsamis Douskos

More information

Image Segmentation. Shengnan Wang

Image Segmentation. Shengnan Wang Image Segmentation Shengnan Wang shengnan@cs.wisc.edu Contents I. Introduction to Segmentation II. Mean Shift Theory 1. What is Mean Shift? 2. Density Estimation Methods 3. Deriving the Mean Shift 4. Mean

More information

C-NBC: Neighborhood-Based Clustering with Constraints

C-NBC: Neighborhood-Based Clustering with Constraints C-NBC: Neighborhood-Based Clustering with Constraints Piotr Lasek Chair of Computer Science, University of Rzeszów ul. Prof. St. Pigonia 1, 35-310 Rzeszów, Poland lasek@ur.edu.pl Abstract. Clustering is

More information

Utilizing Salient Region Features for 3D Multi-Modality Medical Image Registration

Utilizing Salient Region Features for 3D Multi-Modality Medical Image Registration Utilizing Salient Region Features for 3D Multi-Modality Medical Image Registration Dieter Hahn 1, Gabriele Wolz 2, Yiyong Sun 3, Frank Sauer 3, Joachim Hornegger 1, Torsten Kuwert 2 and Chenyang Xu 3 1

More information

Sampling-Based Ensemble Segmentation against Inter-operator Variability

Sampling-Based Ensemble Segmentation against Inter-operator Variability Sampling-Based Ensemble Segmentation against Inter-operator Variability Jing Huo 1, Kazunori Okada, Whitney Pope 1, Matthew Brown 1 1 Center for Computer vision and Imaging Biomarkers, Department of Radiological

More information

ADAPTIVE GRAPH CUTS WITH TISSUE PRIORS FOR BRAIN MRI SEGMENTATION

ADAPTIVE GRAPH CUTS WITH TISSUE PRIORS FOR BRAIN MRI SEGMENTATION ADAPTIVE GRAPH CUTS WITH TISSUE PRIORS FOR BRAIN MRI SEGMENTATION Abstract: MIP Project Report Spring 2013 Gaurav Mittal 201232644 This is a detailed report about the course project, which was to implement

More information

Automatic Extraction of Femur Contours from Hip X-ray Images

Automatic Extraction of Femur Contours from Hip X-ray Images Automatic Extraction of Femur Contours from Hip X-ray Images Ying Chen 1, Xianhe Ee 1, Wee Kheng Leow 1, and Tet Sen Howe 2 1 Dept of Computer Science, National University of Singapore, 3 Science Drive

More information