Qualification: 
Ph.D, M.Tech
Email: 
p_hema@cb.amrita.edu

Dr. Hema Menon P. currently serves as Assistant Professor at the department of Computer Science and Engineering, Amrita School of Engineering, Coimbatore. Her areas of research include Image Processing and Medical Image Processing.

Publications

Publication Type: Journal Article

Year of Publication Publication Type Title

2017

Journal Article

V. Gayathri and Dr. Hema Menon P., “Vasculature detection from retinal color fundus images using linear prediction residual algorithm”, International Journal of Pure and Applied Mathematics, vol. 114, no. 12 Special Issue, pp. 171-178, 2017.[Abstract]


Automatic vasculature detection from color fundus images of retina has a significant role in automated diagnosis. Retinal vasculature identification has received importance off late, as it is an important anatomical structure in the analysis of retinopathy. Retinal vasulature can be obtained using any of the basic edge detection techniques but the challenge faced here is in identification of minituare blood vessels . In this paper the applicability of linear prediction residual algorithm for vasculature detection has been analysed. In this case the pixels which fail the prediction are considered as the vasculature edges and are then extracted from the fundus image. The results obtained show that minute blood vessels have also been identified using the proposed approach.

More »»

2017

Journal Article

N. Madhesh and Dr. Hema Menon P., “Automated segmentation of brain parts from MRI image slices”, International Journal of Pure and Applied Mathematics, vol. 114, no. 11 Special Issue, pp. 36-46, 2017.[Abstract]


Segmentation of brain images has been a prominent area of research in the field of medical imaging in the recent past. This work concentrates on segmentation of brain images acquired using Magnetic Resonance Imaging (MRI) technique. Brain image consists of many different parts that are of interest to practitioners. Automatic segmentation of all these parts has been a challenging task. In this paper a system for localizing the region of interest and automated segmentation of brain parts by using histogram of oriented gradients and SVM Classifier has been presented. The system is trained using specific parts of the brain image separately. Once properly trained, the system can segment the part with which it has been trained from the test dataset. Here, for discussion the region of interest around ventricles in axial view and corpus callosum in sagittal view has been considered.

More »»

2017

Journal Article

R. Nilakant, Dr. Hema Menon P., and Vikram, K., “A survey on advanced segmentation techniques for brain MRI image segmentation”, International Journal on Advanced Science, Engineering and Information Technology, vol. 7, no. 4, pp. 1448-1456, 2017.[Abstract]


This paper presents a survey of advanced methods for segmenting the MRI (Magnetic Resonance Imaging) image of the brain. Segmentation of the brain is a challenging task because it requires more emphasized methods to differentiate each of the regions present in the brain image. The intensity differences between the different regions in the brain MRI image are very less, making it difficult to automate the entire segmentation process. Hence, a thorough understanding of the existing segmentation algorithm is essential for accurate segmentation. The segmentation algorithms surveyed in this work are Neural Network Model, Self- Organizing Maps, Radial Basis Function, Back Propagation, Fuzzy C-Means, Deformable Models, Level Set Models, Genetic Algorithm, Differential Evolutionary Algorithm, Hybrid Clustering and Artificial Intelligence. Such a survey would be helpful for researchers working in the field of brain image segmentation. The paper discusses the complexities in the segmentation algorithm and also the challenges in segmenting the brain MRI images. The segmentation outputs and analysis of the existing literature has also been discussed. The major criteria and their advantages in the segmentation of each algorithm have been reported accordingly in the observations.

More »»

2015

Journal Article

A. S. Nitheesh and Dr. Hema Menon P., “Contour based obstacle detection using stereo vision”, International Journal of Applied Engineering Research, vol. 10, no. 13, pp. 33351-33354, 2015.[Abstract]


Stereo Vision based depth estimation is being widely used in designing autonomous robots. Block matching is the commonly used method to find the depth of objects. While the outputs obtained is satisfactory, the complexity of the method, including rectification of each and every frame using the camera parameters, becomes very high. Such process cannot be efficiently carried out by development boards like Beagle Board or Raspberry Pi. This necessitates the need for developing a method which is computationally less intensive. This paper presents a method to estimate the depth of objects in a given scene by extracting their contours. Using the contours, disparity of the objects are found out, which is then used for estimating the object’s depth. The system is implemented and tested in a BeagleBoard-xM and theexecution time is compared with that of a personal computer. © Research India Publications.

More »»

2015

Journal Article

Dr. Hema Menon P. and Narayanankutty, K. A., “Comparative performance of different perceptual contrast fusion techniques using MLS”, International Journal of Biomedical Engineering and Technology, vol. 18, no. 1, pp. 52-71, 2015.[Abstract]


This paper exploits the different perceptual contrast information in images reported for fusion which can produce a composite image which is visually or perceptually having better quality. The various types of measures that are used for extracting the perceptual contrast information are reviewed. A comparative analysis of the results obtained based on perceptual quality metric using a single registration technique, namely the MLS, reported earlier by the authors has been done. It has also been suggested that the quality assessment of the fused images has to be based on the three parameters: edge information, image histogram and structural similarity index measure. Comparison of the fusion results has been done using these three parameters and also the PSNR and quality index metric. Copyright © 2015 Inderscience Enterprises Ltd.

More »»

2015

Journal Article

Dr. Hema Menon P., Sreeja, S., Narayanankutty, K. A., and Sasikumar, G., “Edge preserving image fusion using linear prediction”, International Journal of Applied Engineering Research, vol. 10, no. 11, pp. 29917-29926, 2015.[Abstract]


This paper focuses on enhancing the visual quality of images through edge preserving image fusion techniques. Edges in an image are considered to be one of the most prominent features for analysis. This necessitates the need for preserving the edge information in the input images under consideration in the fused output. In this work a new method is utilized in image fusion using Liner Prediction for extracting the edges. In Linear Prediction method the smooth prediction errors are minimized and steep changes are amplified and therefore, edge information can be accurately extracted when applied to image edge detection.The edges from both the input images are extracted and this edge information is used in the selection of the pixel values in the fused output image. Fused image thus obtained is found to retain maximum edges from the input images. The quality of results thus obtained is assessed using the SSIMand Fusion Mutual Information of Edges. © Research India Publications.

More »»

2014

Journal Article

S. KS and Dr. Hema Menon P., “Detection of Exudative Maculopathy from Retinal Fundus Images”, International Journal of Computer Applications, vol. 97, no. 18, pp. 48–49, 2014.[Abstract]


Diabetic retinopathy is a group of eye problems caused due to diabetes. Longer time a person has diabetes; the higher is his or her chances of developing diabetic retinopathy. One of the stages of diabetic retinopathy is Exudative Maculopathy. Spontaneous progression and regression of exudates causes Exudative Maculopathy.This work focuses on extraction of exudates from retinal fundus images using image processing techniques.

More »»

2014

Journal Article

Dr. Hema Menon P., Narayanankutty, K. A., and Indulekha, T. S., “Feature Point Selection using Structural Graph Matching for MLS based Image Registration”, International Journal of Computer Applications, vol. 100, no. 4, pp. 18-23, 2014.[Abstract]


Image registration is a method of determining a mapping or a transformation that relates positions in one image, to the corresponding positions in the other images under considerations. The process of registration depends on the homologous control points that are selected from the source and the target images. This paper focuses on the use of the structural information of an image, for selecting control points, as it remains the same even when it undergoes most of the transformation and illumination changes. The points thus obtained are then given to the Moving Least Squares (MLS) based registration technique reported earlier by the authors

More »»

2014

Journal Article

J. Cheriyan and Dr. Hema Menon P., “Extraction and 3D reconstruction of Retinal Blood Vessels from Single Fundus Image”, International Journal of Innovative Research in Advanced Engineering (IJIRAE), vol. 3, no. 7, 2014.[Abstract]


3D modelling has gained lot of importance in the field of medical Image analysis. 3D models give the depth information of the object which is very useful in visualization. The analysis of the blood vessels in the retinal image is helpful for identifying the different diseases such as stages of diabetic retinopathy, glaucoma etc.3D retinal blood vessels would be helpful in explaining to patients about the progression of a disease in the eye and for diagnostic records. This paper presents
a simple algorithm to model the 3D structure of blood vessel, which is an extension of the previous work [1]. In this work 3D model of blood vessel is obtained by using gradient method, unsharp masking and shape from shading. Simulation results on a set of retinal images verify the effectiveness of the proposed method

More »»

2014

Journal Article

V. Gayathri, Dr. Hema Menon P., and Narayanankutty, K. A., “Edge Extraction Algorithm using Linear Prediction Model on Dental X-ray Images”, International Journal of Computer Applications, vol. 100, no. 19, 2014.[Abstract]


This paper focuses edge extraction from dental x-ray images for the root canal procedure, using the linear prediction (LP). The major issues of processing the dental X-ray images are caused due to the misalignment and the variation in the contrast, by the very modality of acquisition. Also the differences in the shapes and orientations of the teeth pose yet another difficulty in the processing. Thus, in order to overcome these challenges, the LP residual based approach is used in this paper to obtain better root canal edge information. In the present work, the input image is processed by the 10th order LP method to obtain LP residual image. The LP residual of the input image is found to provide better edges as compared to the conventional methods. Also the edge map obtained by the LP method is compared with previous work [7] on zero frequency resonator (ZFR) based edge extraction and is found to give a better edge map. Effectiveness of the LP residual method is confirmed by the visual inspection of the edge map and also from the subjective evaluation

More »»

2012

Journal Article

J. Cheriyan, Narayankutty, K. A., and Dr. Hema Menon P., “Ellipsoid Based Method for Rotating the Human Retinal Fundus Image”, Journal of Asian Scientific Research, vol. 2, no. 5, pp. 307-309, 2012.[Abstract]


A major imaging technique for the eye is the fundus camera, and images obtained from this camera are 2D in nature. 2D image of retina does not give a realistic effect .3D modelling of the retina helps the surgeons to design an appropriate treatment plan and procedures prior to actual retinal surgery. Fundus image is a 2D data and OCT give intraretinal layer information. Fusing the depth information of OCT in to the fundus image, requires OCT data in to it. We have illustrated an ellipsoid based method to generate 3D visualization of the retina to view retinal surface exactly as a 3D image.

More »»

2012

Journal Article

J. Cheriyan, Dr. Hema Menon P., and Narayanankutty, K. A., “3d reconstruction of human retina from fundus image–a survey”, International Journal on Modern Engineering Research, vol. 2, no. 5, pp. 3089–3092, 2012.[Abstract]


Imaging techniques for the eye include fundus camera, OCT etc of which the most widely used and economical one is the use of fundus camera. Images obtained from this camera are 2D in nature. Analysis of 2D data requires a lot of expertize. This makes it necessary for a 3D reconstruction of the 2D fundus image which would help doctors in their analysis and treatment plan. 3D retinal image would also be helpful in explaining to patients, the progression of disease. In this paper a survey on various methods for 3D reconstruction of retinal fundus image has been discussed.

More »»

2011

Journal Article

D. Devasruthi, Dr. Hema Menon P., and Narayanankutty, K. A., “FE-BEMD and exemplar based hybrid image inpainting for occlusion removal”, International Journal of Computer Applications, vol. 28, no. 8, pp. 38-44, 2011.[Abstract]


In this paper, a hybrid method for occlusion removal using Finite element based Bi-dimensional Empirical Mode Decomposition (FE-BEMD) and Exemplar based image inpainting is discussed. Initially, the image is decomposed into Intrinsic Mode Functions (IMFs) and a Residue using FEBEMD. Then the Exemplar based image inpainting algorithm is
applied to each of the IMFs and residue and the results are added together to get the inpainted image. The results obtained shows that the proposed method works well for removing large objects as well as small damages like scratches from images

More »»

2010

Journal Article

Dr. Hema Menon P. and Narayanankutty, K. A., “Applicability of non-rigid medical image registration using moving least squares”, International Journal of Computer Applications (Impact Factor: 0.835), vol. 1, no. 6, pp. 79-86, 2010.[Abstract]


A drawback of the non-rigid registration is its unpredictable nature of the deformation on the target image. Mapping every point on images can cause deformations even to regions, which are expected to remain rigid. A non-rigid registration is therefore desirable, that produces only local deformations where needed, while still preserving the overall rigidity. This work focuses on one such method called the Moving Least Squares (MLS) transformation and compares the results with Thin Plate Splines (TPS). An intensity based non-rigid registration algorithm is applied apriory, if the input medical images are from two different patients in order to facilitate for the selection of homologous control points in them. We compare the performance of both the techniques by calculating the Target Registration Error (TRE) at certain points and results are encouraging.

More »»

2009

Journal Article

K. S. Arun and Dr. Hema Menon P., “Content based medical image retrieval by combining rotation invariant contourlet features and fourier descriptors”, International Journal of Recent Trends in Engineering, vol. 2, no. 2, pp. 35-39, 2009.[Abstract]


Designing and modeling methods for medical image search is a challenging task. Content based medical image retrieval, which aims at searching the image database using invariant features, is an important research area for manipulating large amount of medical image databases. This paper focuses on the problem of texture and shape feature extraction. A novel approach by successfully combining rotation invariant contourlet transform and Fourier descriptors is proposed. Rotation invariant contourlet transform is used for texture feature extraction and Fourier descriptor extracts shape features. The retrieval performance of this method is tested using a large medical image database and measured using commonly used performance measurement.

More »»

Publication Type: Conference Paper

Year of Publication Publication Type Title

2016

Conference Paper

Dr. Hema Menon P. and Narayanankutty, K. Ab, “MRI/CT image fusion using Gabor texture features”, in Advances in Intelligent Systems and Computing, 2016, vol. 530, pp. 47-60.[Abstract]


Image fusion has been extensively used in the field of medical imaging by medical practitioners for analysis of images. The aim of image fusion is to combine information from different images in the output fused image without adding artefacts. The output has to contain all information form the individual images without introducing artifacts. In images that contains more textural properties, it will be more effective in terms of fusion, if we include all the textures contained in the corresponding individual images. Keeping the above objective in mind, we propose the use of Gabor filter for analysing the texture, because under this method the filter parameters can be tunned depending upon the textures in the corresponding images. The fusion is performed on the individual textural components to the two input images and then all the fused texture images are combined together to get the final fused image. To this the fused residual image obtained by combining the residue of the two images can be added to increase the information content. This approach was tested on MRI and CT images considering both mono-modal and multi-modal cases and the results are promising. © Springer International Publishing AG 2016.

More »»

2016

Conference Paper

Dr. Hema Menon P. and Rajeshwari, B., “Enhancement of dental digital X-ray images based on the image quality”, in Advances in Intelligent Systems and Computing, 2016, vol. 530, pp. 33-45.[Abstract]


Medical Image Enhancement has made revolution in medical field, in improving the image quality helping doctors in their analysis. Among the various modalities available, the Digital X-rays have been extensively utilized in the medical world of imaging, especially in Dentistry, as it is reliable and affordable. The output scan pictures are examined by practitioners for scrutiny and clarification of tiny setbacks. A technology which is automated with the help of computers to examine the X-Ray images would be of great help to practitioners in their diagnosis. Enhancing the visual quality of the image becomes the prerequisite for such an automation process. The image quality being a subjective measure, the choice of the methods used for enhancement depends on the image under concern and the related application. This work aims at developing a system that automates the process of image enhancement using methods like Histogram Equalization(HE), Gamma Correction(GC),and Log Transform(LT). The decision of the enhancement parameters and the method used is chosen, with the help of the image statistics (like mean, variance, and standard deviation). This proposed system also ranks the algorithms in the order of their visual quality and thus the best possible enhanced output image can be used for further processing. Such an approach would give the practitioners flexibility in choosing the enhanced output of their choice. © Springer International Publishing AG 2016.

More »»

2016

Conference Paper

R. Hiralal and Dr. Hema Menon P., “A survey of brain MRI image segmentation methods and the issues involved”, in Advances in Intelligent Systems and Computing, 2016, vol. 530, pp. 245-259.[Abstract]


This paper presents a survey on the existing methods for segmentation of brain MRI images. Segmentation of brain MRI images has been widely used as a preprocessing, for projects that involve analysis and automation, in the field of medical image processing. MRI image segmentation is a challenging task because of the similarity between different tissue structures in the brain image. Also the number of homogeneous regions present in an image varies with the image slice and orientation. The selection of an appropriate method for segmentation therefore depends on the image characteristics. This study has been done in the perspective of enabling the selection of a segmentation method for MRI brain images. The survey has been categorized based on the techniques used in segmentation. © Springer International Publishing AG 2016.

More »»

2014

Conference Paper

G. V. and Dr. Hema Menon P., “Root Canal Edge Extraction Using Zero Frequency Resonance Filter in dental X-Ray Images”, in Proceedings of International Conference on Signal and Speech Processing (ICSSP-14), 2014, pp. 71-75.

2011

Conference Paper

A. J. Cheriyan, Dr. Hema Menon P., and Narayanankutty, K. A., “3D reconstruction of human retina from a single fundus image”, in Proceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011, Las Vegas, NV, 2011, vol. 1, pp. 252-257.[Abstract]


A major imaging technique for the eye is the fundus camera, and images obtained from this camera are 2D in nature. 3D retinal image would be helpful in explaining to patients, about the progression of a disease in the eye, and for diagnostic records. This work focusses on the 3D reconstruction of retinal image from a single fundus image. The reconstruction is achieved using the shape from shading (SFS) method, and the focussing information. The results obtained are fascinating and are presented.

More »»

2010

Conference Paper

Dr. Hema Menon P., John, M., and Narayanankutty, K. A., “Generation of medical atlas from brain MR images through segmentation”, in 2010 International Conference on Intelligent and Advanced Systems, ICIAS 2010, Kuala Lumpur, 2010.[Abstract]


This work aims at creating a structural atlas for brain MR images, which would help to solve clinical problems, faced during the training periods and can also be referred as a data set for medical diagnosis. Medical images taken as inputs are correlated with predefined atlas image for diagnosing the presence of anomalies. The images are segmented and labeled by using various techniques like thresholding, region growing and level sets methods. As an innovative approach a Moving Least Square based segmentation has also been performed and the results are fascinating. Use of this method is found to reduce the segmentation time drastically. An interactive user interface has been developed for the clinicians use.

More »»

2009

Conference Paper

Dr. Hema Menon P. and S., A. K., “Image Retrieval System for DICOM Images”, in National Conference on Frontier Research Areas in Computing, 2009.

2009

Conference Paper

N. K. Jacob and Dr. Hema Menon P., “Text Extraction from Document Images with Complex Background”, in National Conference on Signal Processing Communications and VLSI Design NCSCV’09, 2009.

2009

Conference Paper

N. K. Jacob and Dr. Hema Menon P., “Text Extraction from Camera Captured Document Images”, in National Conference on Frontier Research areas in Computing, 2009.

2007

Conference Paper

Dr. Hema Menon P., “Font Style Identification using Gabor Filters”, in UGC-SAP(DRS) National Conference on Mathematics Computing and Modelling, 2007, vol. 1.

2006

Conference Paper

Dr. Hema Menon P., “Script identification from document images using gabor filters”, in IEEE- International Conference on Signal and Image Processing, 2006, vol. 2.

Faculty Research Interest: 
207
PROGRAMS
OFFERED
5
AMRITA
CAMPUSES
15
CONSTITUENT
SCHOOLS
A
GRADE BY
NAAC, MHRD
9th
RANK(INDIA):
NIRF 2017
150+
INTERNATIONAL
PARTNERS