Qualification: 
M.Tech
Email: 
r_manjusha@cb.amrita.edu

Manjusha R. currently serves as Assistant Professor at the Department of Computer Science and Engineering, School of Engineering, Amrita Vishwa Vidyapeetham, Coimbatore Campus. Her areas of research include Image Processing.

Publications

Publication Type: Conference Proceedings

Year of Publication Title

2020

Y. Himabindu, Manjusha R., and Parameswaran, L., “Detection and Removal of RainDrop from Images Using DeepLearning”, Computational Vision and Bio-Inspired Computing. Springer International Publishing, Cham, 2020.[Abstract]


Dynamic climatic conditions like rain, affects the performance of vision algorithms which are used for surveillance and analysis tasks. Removal of rain-drops is challenging for single image as the rain drops affect the entire image and makes it difficult to identify the background affected by the rain. Thus, removal of rain from still pictures is a complex and challenging task. The rain drops affect the visibility and clarity of the image which makes it difficult to read and analyze the information present in the image. In this paper, we identified and restored the rain drop affected regions using a deep learning architecture.

More »»

2019

Manjusha R. and Dr. Latha Parameswaran, “Design of an image skeletonization based algorithm for overcrowd detection in smart building”, Lecture Notes in Computational Vision and Biomechanics, vol. 30. Springer Netherlands, pp. 615-629, 2019.[Abstract]


Crowd analysis has found its significance in varied applications from security purposes to commercial use. This proposed algorithm aims at contour extraction from skeleton of the foreground image for identifying and counting people and for providing crowd alert in the given scene. The proposed algorithm is also compared with other conventional algorithms like HoG with SVM classifier, Haar cascade and Morphological Operator. Experimental results show that the proposed method aids better crowd analysis than the other three algorithms on varied datasets with varied illumination and varied concentration of people. © Springer Nature Switzerland AG 2019.

More »»

2018

S. L. Nair, Manjusha R., and Dr. Latha Parameswaran, “Kernel Based Approaches for Context Based Image Annotatıon”, Computational Vision and Bio Inspired Computing. Springer International Publishing, Cham, 2018.[Abstract]


The Exploration of contextual information is very important for any automatic image annotation system. In this work a method based on kernels and keyword propagation technique is proposed. Automatic annotation with a set of keywords for each image is carried out by learning the image semantics. The similarity between the images is calculated by Hellinger's kernel and Radial Bias Function kernel(RBF)kernel. The images are labelled with multiple keywords using contextual keyword propagation. The results of using the two kernels on the set of features extracted are analysed. The annotation results obtained were validated based on confusion matrix and were found to have a good accuracy. The main advantage of this method is that it can propagate multiple keywords and no definite structure for the annotation keywords has to be considered

More »»

2018

V. Pranav, Manjusha R., and Latha, P., “Design of an algorithm for people identification using facial descriptors”, Lecture Notes in Computational Vision and Biomechanics, vol. 28. Springer Netherlands, pp. 1117-1128, 2018.[Abstract]


The proposed work aims at identifying and greeting people. A new technique is introduced that incorporates the facial features and KNN classifier. Since human face is the one which is said to be the most representative, the features of the face (eyes, nose and mouth) are extracted and are used for training the classifier. The proposed frame work consists of four phases: Facial Features Detection (FFD), Detected Features Positioning (DFP), Descriptive Features Extraction (DFE) and Face Identification (FI). The proposed algorithm can be used in a wide variety of scenarios such as campus, office etc. after being trained with the corresponding dataset. The performance of the system is analyzed for various scenarios. Good average accuracy of 96.05% has been achieved. © 2018, Springer International Publishing AG.

More »»

2016

S. Athira, Manjusha R., and Dr. Latha Parameswaran, “Scene understanding in images”, Advances in Intelligent Systems and Computing, vol. 530. pp. 261-271, 2016.[Abstract]


Scene understanding targets on the automatic identification of thoughts, opinion, emotions, and sentiment of the scene with polarity. The sole aim of scene understanding is to build a system which infer and understand the image or a video just like how humans do. In the paper, we propose two algorithms- Eigenfaces and Bezier Curve based algorithms for scene understanding in images. The work focuses on a group of people and thus, targets to perceive the sentiment of the group. The proposed algorithm consist of three different phases. In the first phase, face detection is performed. In the second phase, sentiment of each person in the image is identified and are combined to identify the overall sentiment in the third phase. Experimental results show Bezier curve approach gives better performance than Eigenfaces approach in recognizing the sentiments in multiple faces. © Springer International Publishing AG 2016.

More »»

Publication Type: Journal Article

Year of Publication Title

2018

M. Padmashini, Manjusha R., and Dr. Latha Parameswaran, “Vision Based Algorithm for People Counting using Deep Learning”, International Journal of Engineering and Technology(UAE), vol. 7, pp. 74-80, 2018.[Abstract]


Estimating the number of people in a particular scene has always been an important topic of research in computer vision and digital image processing. People counting has wide applications in scenario ranging from analyzing the customer's choice and improving the quality of service in retail stores, supermarkets and shopping malls to managing human resources and optimizing the energy usage in office buildings. While there exists algorithms for counting people in a scene, some algorithm have set their benchmark in performance with respect to efficiency, flexibility and accuracy. In this paper, an attempt has been made to perform people counting using Deep Neural Networks (DNN) on comparison with existing image processing based algorithms like Histogram of Oriented Gradients with Support Vector Machine (HoG with SVM), Local Binary Pattern (LBP) based Adaboost classifier and contour based people detection. The proposed DNN based approach has higher accuracy at 90% and less false negatives. © 2018 Authors.

More »»

2015

C. K. Kumar, Manjusha R., and Parameswaran, L., “Comparision of image classification methods on event data”, vol. 10, pp. 29631 - 29640, 2015.[Abstract]


The aim of this work is to classify images related to social events. With advances in digital image processing, automated classification of event related images over large categories of dataset is possible only if the name of the event is known. The purpose of the paper is to identify different events in a given set of images with the help of visual content. We compare the performance of Global (GIST) as well as Local Descriptors (SIFT) which is helpful in achieving this classification and retrieval of images. The performances of both the approaches are assessed.

More »»

2015

S. L. Nair, Manjusha R., and Dr. Latha Parameswaran, “A survey on context based image annotation techniques”, International Journal of Applied Engineering Research, vol. 10, pp. 29845-29856, 2015.[Abstract]


The importance of image acquisition and then analysing them for various purposes is increasing everyday.Image annotation and retrieval is a vital process for analysis of large data. Context based annotation systems labels the images based on the context of the scene and provides accurate results for automatic annotation compared to the earlier Content based systems and thus has become a very important research domain in image processing. Many approaches and representations are proposed and developed for context based image annotation.This paper provides anoverview of some of the important approaches and representations of objects and their relationship used widely for context based image annotation. © Research India Publications.

More »»
Faculty Research Interest: